https://www.opentrain.ai/papers/optimsyn-influence-guided-rubrics-optimization-for-synthetic-data-generation--arxiv-2604.00536/2026-06-15T19:32:52.759Z https://www.opentrain.ai/papers/towards-reliable-truth-aligned-uncertainty-estimation-in-large-language-models--arxiv-2604.00445/2026-06-17T18:23:34.265Z https://www.opentrain.ai/papers/llm-essay-scoring-under-holistic-and-analytic-rubrics-prompt-effects-and-bias--arxiv-2604.00259/2026-06-16T18:45:38.038Z https://www.opentrain.ai/papers/do-language-models-know-when-they-ll-refuse-probing-introspective-awareness-of-s--arxiv-2604.00228/2026-06-12T23:20:12.332Z https://www.opentrain.ai/papers/four-generations-of-quantum-biomedical-sensors--arxiv-2603.29944/2026-06-09T18:38:09.802Z https://www.opentrain.ai/papers/rewrite-the-news-tracing-editorial-reuse-across-news-agencies--arxiv-2603.29937/2026-06-17T17:39:30.637Z https://www.opentrain.ai/papers/towards-empowering-consumers-through-sentence-level-readability-scoring-in-germa--arxiv-2603.29861/2026-06-15T13:08:39.685Z https://www.opentrain.ai/papers/eneide-a-high-quality-silver-standard-dataset-for-named-entity-recognition-and-l--arxiv-2603.29801/2026-06-15T06:04:40.291Z https://www.opentrain.ai/papers/when-can-we-trust-llm-graders-calibrating-confidence-for-automated-assessment--arxiv-2603.29559/2026-06-16T16:03:16.809Z https://www.opentrain.ai/papers/bringing-up-a-bilingual-babylm-investigating-multilingual-language-acquisition-u--arxiv-2603.29552/2026-06-10T21:17:29.630Z https://www.opentrain.ai/papers/distilling-human-aligned-privacy-sensitivity-assessment-from-large-language-mode--arxiv-2603.29497/2026-06-16T23:58:07.750Z https://www.opentrain.ai/papers/metriplector-from-field-theory-to-neural-architecture--arxiv-2603.29496/2026-06-16T04:33:35.534Z https://www.opentrain.ai/papers/an-isotropic-approach-to-efficient-uncertainty-quantification-with-gradient-norm--arxiv-2603.29466/2026-06-13T05:05:35.440Z https://www.opentrain.ai/papers/authorship-impersonation-via-llm-prompting-does-not-evade-authorship-verificatio--arxiv-2603.29454/2026-06-15T03:48:15.626Z https://www.opentrain.ai/papers/security-in-llm-as-a-judge-a-comprehensive-sok--arxiv-2603.29403/2026-06-14T05:11:55.818Z https://www.opentrain.ai/papers/is-my-model-perplexed-for-the-right-reason-contrasting-llms-benchmark-behavior-w--arxiv-2603.29396/2026-05-21T06:32:01.660Z https://www.opentrain.ai/papers/open-machine-translation-for-esperanto--arxiv-2603.29345/2026-06-12T12:06:06.196Z https://www.opentrain.ai/papers/sima-aiunty-caste-audit-in-llm-driven-matchmaking--arxiv-2603.29288/2026-05-11T03:26:31.926Z https://www.opentrain.ai/papers/gistbench-evaluating-llm-user-understanding-via-evidence-based-interest-verifica--arxiv-2603.29112/2026-06-17T07:02:14.613Z https://www.opentrain.ai/papers/polarquant-optimal-gaussian-weight-quantization-via-hadamard-rotation-for-llm-co--arxiv-2603.29078/2026-06-12T11:03:54.114Z https://www.opentrain.ai/papers/theory-of-mind-and-self-attributions-of-mentality-are-dissociable-in-llms--arxiv-2603.28925/2026-06-14T05:58:54.488Z https://www.opentrain.ai/papers/adaptive-block-scaled-data-types--arxiv-2603.28765/2026-06-15T08:52:24.940Z https://www.opentrain.ai/papers/onecomp-one-line-revolution-for-generative-ai-model-compression--arxiv-2603.28845/2026-06-15T21:20:13.870Z https://www.opentrain.ai/papers/episcreen-early-epilepsy-detection-from-electronic-health-records-with-large-lan--arxiv-2603.28698/2026-06-18T05:56:58.870Z https://www.opentrain.ai/papers/the-ultimate-tutorial-for-ai-driven-scale-development-in-generative-psychometric--arxiv-2603.28643/2026-06-15T23:36:54.834Z https://www.opentrain.ai/papers/compressing-transformer-language-models-via-matrix-product-operator-decompositio--arxiv-2603.28534/2026-06-17T23:48:54.671Z https://www.opentrain.ai/papers/earlyscirev-a-dataset-of-early-stage-scientific-revisions-extracted-from-latex-w--arxiv-2603.28515/2026-06-18T02:39:43.462Z https://www.opentrain.ai/papers/isoquant-hardware-aligned-so-4-isoclinic-rotations-for-llm-kv-cache-compression--arxiv-2603.28430/2026-06-15T01:48:26.115Z https://www.opentrain.ai/papers/merge-and-conquer-instructing-multilingual-models-by-adding-target-language-weig--arxiv-2603.28263/2026-06-18T06:15:38.045Z https://www.opentrain.ai/papers/categorical-perception-in-large-language-model-hidden-states-structural-warping--arxiv-2603.28258/2026-06-16T10:04:25.863Z https://www.opentrain.ai/papers/textit-versteasch-du-mi-computational-and-socio-linguistic-perspectives-on-genai--arxiv-2603.28213/2026-06-15T18:33:42.046Z https://www.opentrain.ai/papers/from-reviews-to-requirements-can-llms-generate-human-like-user-stories--arxiv-2603.28163/2026-06-12T10:23:53.609Z https://www.opentrain.ai/papers/who-wrote-the-book-detecting-and-attributing-llm-ghostwriters--arxiv-2603.28054/2026-06-17T18:38:57.649Z https://www.opentrain.ai/papers/on-the-role-of-encoder-depth-pruning-whisper-and-lora-fine-tuning-in-slam-asr--arxiv-2603.27981/2026-06-09T19:43:57.936Z https://www.opentrain.ai/papers/ensemjudge-enhancing-reliability-in-chinese-llm-generated-text-detection-through--arxiv-2603.27949/2026-06-16T01:13:03.495Z https://www.opentrain.ai/papers/kazbyte-adapting-qwen-models-to-kazakh-via-byte-level-adapter--arxiv-2603.27859/2026-06-18T07:21:59.825Z https://www.opentrain.ai/papers/protext-a-benchmark-dataset-for-measuring-mis-gendering-in-long-form-texts--arxiv-2603.27838/2026-06-15T17:52:53.003Z https://www.opentrain.ai/papers/tailnlg-a-multilingual-benchmark-addressing-verbalization-of-long-tail-entities--arxiv-2603.27768/2026-06-16T23:21:43.628Z https://www.opentrain.ai/papers/retromorphic-testing-with-hierarchical-verification-for-hallucination-detection--arxiv-2603.27752/2026-06-18T05:04:14.243Z https://www.opentrain.ai/papers/investigating-the-influence-of-language-on-sycophantic-behavior-of-multilingual--arxiv-2603.27664/2026-06-12T08:51:53.142Z https://www.opentrain.ai/papers/over-refusal-and-representation-subspaces-a-mechanistic-analysis-of-task-conditi--arxiv-2603.27518/2026-06-15T23:51:04.029Z https://www.opentrain.ai/papers/astra-mapping-art-technology-institutions-via-conceptual-axes-text-embeddings-an--arxiv-2603.28816/2026-06-12T10:12:18.853Z https://www.opentrain.ai/papers/scope-tree-based-self-correcting-online-log-parsing-via-syntactic-semantic-colla--arxiv-2603.27247/2026-06-17T12:27:52.225Z https://www.opentrain.ai/papers/magic-words-or-methodical-work-challenging-conventional-wisdom-in-llm-based-poli--arxiv-2603.26898/2026-04-25T16:15:29.554Z https://www.opentrain.ai/papers/weight-tying-biases-token-embeddings-towards-the-output-space--arxiv-2603.26663/2026-06-14T21:55:21.807Z https://www.opentrain.ai/papers/memboost-a-memory-boosted-framework-for-cost-aware-llm-inference--arxiv-2603.26557/2026-06-18T05:13:43.577Z https://www.opentrain.ai/papers/alba-a-european-portuguese-benchmark-for-evaluating-language-and-linguistic-dime--arxiv-2603.26516/2026-06-17T03:25:46.929Z https://www.opentrain.ai/papers/amalia-technical-report-a-fully-open-source-large-language-model-for-european-po--arxiv-2603.26511/2026-04-17T10:41:08.895Z https://www.opentrain.ai/papers/clinical-named-entity-recognition-in-the-portuguese-language-a-benchmark-of-mode--arxiv-2603.26510/2026-06-17T16:25:16.646Z https://www.opentrain.ai/papers/automating-clinical-information-retrieval-from-finnish-electronic-health-records--arxiv-2603.26434/2026-06-17T14:17:30.811Z https://www.opentrain.ai/papers/switch-attention-towards-dynamic-and-fine-grained-hybrid-transformers--arxiv-2603.26380/2026-06-18T07:22:17.196Z https://www.opentrain.ai/papers/a-formal-framework-for-uncertainty-analysis-of-text-generation-with-large-langua--arxiv-2603.26363/2026-06-18T05:40:07.401Z https://www.opentrain.ai/papers/gs-braintext-a-multi-site-brain-imaging-report-dataset-from-generation-scotland--arxiv-2603.26235/2026-06-16T05:08:24.830Z https://www.opentrain.ai/papers/sparse-auto-encoders-and-holism-about-large-language-models--arxiv-2603.26207/2026-06-18T06:21:54.137Z https://www.opentrain.ai/papers/clash-of-the-models-comparing-performance-of-bert-based-variants-for-generic-new--arxiv-2603.26156/2026-04-12T13:08:26.842Z https://www.opentrain.ai/papers/pixelsmile-toward-fine-grained-facial-expression-editing--arxiv-2603.25728/2026-06-16T23:59:12.859Z https://www.opentrain.ai/papers/measuring-what-matters-or-what-s-convenient-robustness-of-llm-based-scoring-syst--arxiv-2603.25674/2026-06-18T04:47:01.536Z https://www.opentrain.ai/papers/beyond-via-analysis-and-estimation-of-the-impact-of-large-language-models-in-aca--arxiv-2603.25638/2026-06-12T08:54:44.445Z https://www.opentrain.ai/papers/deepfan-a-transformer-based-deep-learning-model-for-human-artificial-intelligenc--arxiv-2603.25607/2026-06-16T10:31:26.076Z https://www.opentrain.ai/papers/taac-a-gate-into-trustable-audio-affective-computing--arxiv-2603.25570/2026-06-12T09:45:30.879Z https://www.opentrain.ai/papers/voxtral-tts--arxiv-2603.25551/2026-06-15T19:44:27.807Z https://www.opentrain.ai/papers/nero-net-a-neuroevolutionary-approach-for-the-design-of-adversarially-robust-cnn--arxiv-2603.25517/2026-06-15T06:53:55.653Z https://www.opentrain.ai/papers/lightweight-genai-for-network-traffic-synthesis-fidelity-augmentation-and-classi--arxiv-2603.25507/2026-06-17T16:32:18.414Z https://www.opentrain.ai/papers/an-experimental-comparison-of-the-most-popular-approaches-to-fake-news-detection--arxiv-2603.25501/2026-06-17T14:15:48.674Z https://www.opentrain.ai/papers/translation-asymmetry-in-llms-as-a-data-augmentation-factor-a-case-study-for-6-r--arxiv-2603.25489/2026-06-17T06:18:34.193Z https://www.opentrain.ai/papers/glowq-group-shared-low-rank-approximation-for-quantized-llms--arxiv-2603.25385/2026-06-16T10:34:41.327Z https://www.opentrain.ai/papers/image-rotation-angle-estimation-comparing-circular-aware-methods--arxiv-2603.25351/2026-06-17T17:59:16.447Z https://www.opentrain.ai/papers/adaptive-chunking-optimizing-chunking-method-selection-for-rag--arxiv-2603.25333/2026-06-18T05:35:37.168Z https://www.opentrain.ai/papers/how-pruning-reshapes-features-sparse-autoencoder-analysis-of-weight-pruned-langu--arxiv-2603.25325/2026-06-13T21:31:16.747Z https://www.opentrain.ai/papers/a-gait-foundation-model-predicts-multi-system-health-phenotypes-from-3d-skeletal--arxiv-2603.25283/2026-05-07T15:21:21.024Z https://www.opentrain.ai/papers/comparing-natural-and-synthetic-structured-data-a-study-of-the-passive-verb-alte--arxiv-2603.25227/2026-06-18T05:08:43.742Z https://www.opentrain.ai/papers/translation-or-recitation-calibrating-evaluation-scores-for-machine-translation--arxiv-2603.25222/2026-05-16T03:54:59.618Z https://www.opentrain.ai/papers/a-decade-scale-benchmark-evaluating-llms-clinical-practice-guidelines-detection--arxiv-2603.25196/2026-06-16T16:16:20.013Z https://www.opentrain.ai/papers/cross-preference-learning-for-sentence-level-and-context-aware-machine-translati--arxiv-2603.25183/2026-06-15T10:10:45.042Z https://www.opentrain.ai/papers/to-write-or-to-automate-linguistic-prompts-that-is-the-question--arxiv-2603.25169/2026-06-16T06:44:46.171Z https://www.opentrain.ai/papers/pidp-attack-combining-prompt-injection-with-database-poisoning-attacks-on-retrie--arxiv-2603.25164/2026-06-18T05:30:20.146Z https://www.opentrain.ai/papers/do-llms-know-what-they-know-measuring-metacognitive-efficiency-with-signal-detec--arxiv-2603.25112/2026-06-10T00:28:41.096Z https://www.opentrain.ai/papers/exons-detect-identifying-and-amplifying-exonic-tokens-via-hidden-state-discrepan--arxiv-2603.24981/2026-06-17T20:05:23.687Z https://www.opentrain.ai/papers/synthetic-rewriting-as-a-quality-multiplier-evidence-from-portuguese-continued-p--arxiv-2603.24826/2026-06-17T00:45:47.860Z https://www.opentrain.ai/papers/evaluating-fine-tuned-llm-model-for-medical-transcription-with-small-low-resourc--arxiv-2603.24772/2026-06-17T10:10:01.901Z https://www.opentrain.ai/papers/fine-tuning-a-large-language-model-for-systematic-review-screening--arxiv-2603.24767/2026-06-17T16:28:18.839Z https://www.opentrain.ai/papers/training-llms-for-multi-step-tool-orchestration-with-constrained-data-synthesis--arxiv-2603.24709/2026-06-18T01:20:56.247Z https://www.opentrain.ai/papers/anti-i2v-safeguarding-your-photos-from-malicious-image-to-video-generation--arxiv-2603.24570/2026-06-13T23:51:55.226Z https://www.opentrain.ai/papers/analysing-the-safety-pitfalls-of-steering-vectors--arxiv-2603.24543/2026-06-18T04:47:22.969Z https://www.opentrain.ai/papers/samasamayik-a-parallel-dataset-for-hindi-sanskrit-machine-translation--arxiv-2603.24307/2026-06-17T18:57:50.794Z https://www.opentrain.ai/papers/accelerating-diffusion-based-video-editing-via-heterogeneous-caching-beyond-full--arxiv-2603.24260/2026-06-18T05:54:22.490Z https://www.opentrain.ai/papers/a-visual-observation-on-the-geometry-of-umap-projections-of-the-difference-vecto--arxiv-2603.24150/2026-06-17T00:15:45.623Z https://www.opentrain.ai/papers/medaiddialog-a-multilingual-multi-turn-medical-dialogue-dataset-for-accessible-h--arxiv-2603.24132/2026-06-17T23:22:43.342Z https://www.opentrain.ai/papers/grounding-arabic-llms-in-the-doha-historical-dictionary-retrieval-augmented-unde--arxiv-2603.23972/2026-06-18T04:19:16.803Z https://www.opentrain.ai/papers/how-vulnerable-are-edge-llms--arxiv-2603.23822/2026-06-06T18:01:34.072Z https://www.opentrain.ai/papers/placid-privacy-preserving-large-language-models-for-acronym-clinical-inference-a--arxiv-2603.23678/2026-06-14T16:10:26.301Z https://www.opentrain.ai/papers/ethio-asr-joint-multilingual-speech-recognition-and-language-identification-for--arxiv-2603.23654/2026-06-16T14:04:14.755Z https://www.opentrain.ai/papers/edge-radar-material-classification-under-geometry-shifts--arxiv-2603.23342/2026-06-17T01:16:58.878Z https://www.opentrain.ai/papers/not-all-tokens-are-created-equal-query-efficient-jailbreak-fuzzing-for-llms--arxiv-2603.23269/2026-06-06T16:55:38.683Z https://www.opentrain.ai/papers/sparser-faster-lighter-transformer-language-models--arxiv-2603.23198/2026-06-17T19:59:18.674Z https://www.opentrain.ai/papers/multilingual-kokorochat-a-multi-llm-ensemble-translation-method-for-creating-a-m--arxiv-2603.22913/2026-06-17T21:39:23.183Z https://www.opentrain.ai/papers/echokv-efficient-kv-cache-compression-via-similarity-based-reconstruction--arxiv-2603.22910/2026-06-17T14:41:50.141Z https://www.opentrain.ai/papers/efficient-hallucination-detection-adaptive-bayesian-estimation-of-semantic-entro--arxiv-2603.22812/2026-06-17T23:03:30.494Z https://www.opentrain.ai/papers/who-spoke-what-when-evaluating-spoken-language-models-for-conversational-asr-wit--arxiv-2603.22709/2026-06-09T23:01:29.060Z https://www.opentrain.ai/papers/multi-method-validation-of-large-language-model-medical-translation-across-high--arxiv-2603.22642/2026-05-22T06:09:22.470Z https://www.opentrain.ai/papers/understanding-llm-performance-degradation-in-multi-instance-processing-the-roles--arxiv-2603.22608/2026-06-18T04:19:13.639Z https://www.opentrain.ai/papers/generating-and-evaluating-sustainable-procurement-criteria-for-the-swiss-public--arxiv-2603.22513/2026-06-18T04:20:22.539Z https://www.opentrain.ai/papers/rashid-a-cipher-based-framework-for-exploring-in-context-language-learning--arxiv-2603.22497/2026-05-22T07:49:22.674Z https://www.opentrain.ai/papers/functional-component-ablation-reveals-specialization-patterns-in-hybrid-language--arxiv-2603.22473/2026-05-30T23:06:36.207Z https://www.opentrain.ai/papers/greater-accessibility-can-amplify-discrimination-in-generative-ai--arxiv-2603.22260/2026-05-22T06:37:54.040Z https://www.opentrain.ai/papers/spa-a-simple-but-tough-to-beat-baseline-for-knowledge-injection--arxiv-2603.22213/2026-06-18T06:00:11.408Z https://www.opentrain.ai/papers/enhancing-document-level-machine-translation-via-filtered-synthetic-corpora-and--arxiv-2603.22186/2026-06-11T02:39:43.378Z https://www.opentrain.ai/papers/multiperspectivity-as-a-resource-for-narrative-similarity-prediction--arxiv-2603.22103/2026-05-22T08:11:45.937Z https://www.opentrain.ai/papers/autoregressive-vs-masked-diffusion-language-models-a-controlled-comparison--arxiv-2603.22075/2026-06-12T17:27:47.718Z https://www.opentrain.ai/papers/on-the-challenges-and-opportunities-of-learned-sparse-retrieval-for-code--arxiv-2603.22008/2026-06-17T03:13:59.717Z https://www.opentrain.ai/papers/lrc-weathernet-lidar-radar-and-camera-fusion-network-for-real-time-weather-type--arxiv-2603.21987/2026-06-17T13:44:31.215Z https://www.opentrain.ai/papers/bhdd-a-burmese-handwritten-digit-dataset--arxiv-2603.21966/2026-06-06T07:38:41.737Z https://www.opentrain.ai/papers/slurp-tn-resource-for-tunisian-dialect-spoken-language-understanding--arxiv-2603.21940/2026-06-18T03:36:29.359Z https://www.opentrain.ai/papers/adversarial-camouflage--arxiv-2603.21867/2026-06-16T20:40:59.652Z https://www.opentrain.ai/papers/curvzo-adaptive-curvature-guided-sparse-zeroth-order-optimization-for-efficient--arxiv-2603.21725/2026-06-11T15:21:55.608Z https://www.opentrain.ai/papers/tamtrl-teacher-aligned-reward-reshaping-for-multi-turn-reinforcement-learning-in--arxiv-2603.21663/2026-06-14T16:49:16.022Z https://www.opentrain.ai/papers/towards-secure-retrieval-augmented-generation-a-comprehensive-review-of-threats--arxiv-2603.21654/2026-05-07T06:33:54.958Z https://www.opentrain.ai/papers/efficient-zero-shot-ai-generated-image-detection--arxiv-2603.21619/2026-06-13T15:50:34.618Z https://www.opentrain.ai/papers/boxcrete-a-bayesian-optimization-open-source-ai-model-for-concrete-strength-fore--arxiv-2603.21525/2026-06-15T18:35:51.598Z https://www.opentrain.ai/papers/efficient-fine-tuning-methods-for-portuguese-question-answering-a-comparative-st--arxiv-2603.21418/2026-06-17T18:26:25.395Z https://www.opentrain.ai/papers/persona-vectors-in-games-measuring-and-steering-strategies-via-activation-vector--arxiv-2603.21398/2026-06-16T14:49:18.143Z https://www.opentrain.ai/papers/benchmarking-bengali-dialectal-bias-a-multi-stage-framework-integrating-rag-base--arxiv-2603.21359/2026-06-14T01:09:10.701Z https://www.opentrain.ai/papers/timetox-an-llm-based-pipeline-for-automated-extraction-of-time-toxicity-from-cli--arxiv-2603.21335/2026-06-16T21:18:30.717Z https://www.opentrain.ai/papers/b-jet-tagging-using-a-hybrid-edge-convolution-and-transformer-architecture--arxiv-2603.21326/2026-06-13T22:07:39.001Z https://www.opentrain.ai/papers/consroute-consistency-aware-adaptive-query-routing-for-cloud-edge-device-large-l--arxiv-2603.21237/2026-06-12T08:49:22.642Z https://www.opentrain.ai/papers/the-hidden-puppet-master-predicting-human-belief-change-in-manipulative-llm-dial--arxiv-2603.20907/2026-06-09T19:54:09.592Z https://www.opentrain.ai/papers/hici-hierarchical-construction-integration-for-long-context-attention--arxiv-2603.20843/2026-04-20T06:12:26.277Z https://www.opentrain.ai/papers/jubaku-an-adversarial-benchmark-for-exposing-culturally-grounded-stereotypes-in--arxiv-2603.20581/2026-06-17T12:53:04.056Z https://www.opentrain.ai/papers/deescalwild-a-real-world-benchmark-for-automated-de-escalation-training-with-slm--arxiv-2604.13075/2026-06-14T17:18:37.682Z https://www.opentrain.ai/papers/an-industrial-scale-retrieval-augmented-generation-framework-for-requirements-en--arxiv-2603.20534/2026-06-17T23:02:34.659Z https://www.opentrain.ai/papers/current-llms-still-cannot-talk-much-about-grammar-modules-evidence-from-syntax--arxiv-2603.20114/2026-06-16T15:41:02.679Z https://www.opentrain.ai/papers/how-auditory-knowledge-in-llm-backbones-shapes-audio-language-models-a-holistic--arxiv-2603.19195/2026-06-17T11:33:36.794Z https://www.opentrain.ai/papers/adaptive-regime-aware-stock-price-prediction-using-autoencoder-gated-dual-node-t--arxiv-2603.19136/2026-06-17T20:39:24.328Z https://www.opentrain.ai/papers/dapt-a-dual-path-framework-for-multilingual-multi-hop-question-answering--arxiv-2603.19097/2026-06-16T05:47:53.616Z https://www.opentrain.ai/papers/serendipity-by-design-evaluating-the-impact-of-cross-domain-mappings-on-human-an--arxiv-2603.19087/2026-06-15T15:10:12.301Z https://www.opentrain.ai/papers/a-dataset-and-resources-for-identifying-patient-health-literacy-information-from--arxiv-2603.19082/2026-06-17T00:23:06.843Z https://www.opentrain.ai/papers/em-garde-a-propose-match-framework-for-proactive-streaming-video-understanding--arxiv-2603.19054/2026-05-27T13:55:36.818Z https://www.opentrain.ai/papers/quantitative-introspection-in-language-models-tracking-internal-states-across-co--arxiv-2603.18893/2026-06-16T14:05:21.043Z https://www.opentrain.ai/papers/a-human-in-on-the-loop-framework-for-accessible-text-generation--arxiv-2603.18879/2026-06-16T14:05:32.404Z https://www.opentrain.ai/papers/detecting-basic-values-in-a-noisy-russian-social-media-text-data-a-multi-stage-c--arxiv-2603.18822/2026-06-15T01:05:33.173Z https://www.opentrain.ai/papers/neurogame-transformer-gibbs-inspired-attention-driven-by-game-theory-and-statist--arxiv-2603.18761/2026-06-16T15:11:34.470Z https://www.opentrain.ai/papers/a-comparative-empirical-study-of-catastrophic-forgetting-mitigation-in-sequentia--arxiv-2603.18641/2026-06-15T16:53:29.841Z https://www.opentrain.ai/papers/mymnist-benchmark-of-petnn-kan-and-classical-deep-learning-models-for-burmese-ha--arxiv-2603.18597/2026-06-13T11:04:29.166Z https://www.opentrain.ai/papers/cross-lingual-llm-judge-transfer-via-evaluation-decomposition--arxiv-2603.18557/2026-06-17T16:29:33.033Z https://www.opentrain.ai/papers/when-names-change-verdicts-intervention-consistency-reveals-systematic-bias-in-l--arxiv-2603.18530/2026-06-17T23:15:12.162Z https://www.opentrain.ai/papers/wasd-locating-critical-neurons-as-sufficient-conditions-for-explaining-and-contr--arxiv-2603.18474/2026-06-18T07:37:57.175Z https://www.opentrain.ai/papers/impact-of-automatic-speech-recognition-quality-on-alzheimer-s-disease-detection--arxiv-2603.18239/2026-06-17T22:49:41.965Z https://www.opentrain.ai/papers/grafite-generative-regression-analysis-framework-for-issue-tracking-and-evaluati--arxiv-2603.18173/2026-06-17T07:01:38.192Z https://www.opentrain.ai/papers/conga-guidelines-for-contextual-gender-annotation-a-framework-for-annotating-gen--arxiv-2603.17962/2026-06-16T07:55:28.980Z https://www.opentrain.ai/papers/discovering-decoupled-functional-modules-in-large-language-models--arxiv-2603.17823/2026-06-17T06:54:16.103Z https://www.opentrain.ai/papers/adaptive-guidance-for-retrieval-augmented-masked-diffusion-models--arxiv-2603.17677/2026-06-12T15:18:55.446Z https://www.opentrain.ai/papers/from-isolated-scoring-to-collaborative-ranking-a-comparison-native-framework-for--arxiv-2603.17588/2026-06-14T15:06:02.253Z https://www.opentrain.ai/papers/zipper-lora-dynamic-parameter-decoupling-for-speech-llm-based-multilingual-speec--arxiv-2603.17558/2026-06-16T09:43:22.158Z https://www.opentrain.ai/papers/detecting-the-machine-a-comprehensive-benchmark-of-ai-generated-text-detectors-a--arxiv-2603.17522/2026-06-18T07:22:16.153Z https://www.opentrain.ai/papers/safetutors-benchmarking-pedagogical-safety-in-ai-tutoring-systems--arxiv-2603.17373/2026-05-13T14:16:10.735Z https://www.opentrain.ai/papers/beyond-bouba-kiki-multidimensional-semantic-signals-are-deeply-woven-into-the-fa--arxiv-2603.17306/2026-06-16T21:49:45.517Z https://www.opentrain.ai/papers/opera-online-data-pruning-for-efficient-retrieval-model-adaptation--arxiv-2603.17205/2026-05-17T18:10:21.988Z https://www.opentrain.ai/papers/vqkv-high-fidelity-and-high-ratio-cache-compression-via-vector-quantization--arxiv-2603.16435/2026-06-15T03:19:29.203Z https://www.opentrain.ai/papers/attention-guided-evidence-grounding-for-spoken-question-answering--arxiv-2603.16292/2026-06-16T15:54:22.993Z https://www.opentrain.ai/papers/frequency-matters-fast-model-agnostic-data-curation-for-pruning-and-quantization--arxiv-2603.16105/2026-06-03T09:53:10.366Z https://www.opentrain.ai/papers/prompt-engineering-for-scale-development-in-generative-psychometrics--arxiv-2603.15909/2026-06-01T10:53:10.045Z https://www.opentrain.ai/papers/slovke-a-large-scale-dataset-and-llm-evaluation-for-slovak-keyphrase-extraction--arxiv-2603.15523/2026-06-14T01:19:50.435Z https://www.opentrain.ai/papers/datasets-for-verb-alternations-across-languages-blm-templates-and-data-augmentat--arxiv-2603.15295/2026-06-17T08:53:42.790Z https://www.opentrain.ai/papers/attention-residuals--arxiv-2603.15031/2026-06-18T07:23:54.991Z https://www.opentrain.ai/papers/directional-routing-in-transformers--arxiv-2603.14923/2026-06-16T14:20:53.433Z https://www.opentrain.ai/papers/informative-perturbation-selection-for-uncertainty-aware-post-hoc-explanations--arxiv-2603.14894/2026-06-09T19:21:53.713Z https://www.opentrain.ai/papers/llms-as-signal-detectors-sensitivity-bias-and-the-temperature-criterion-analogy--arxiv-2603.14893/2026-06-16T03:45:42.575Z https://www.opentrain.ai/papers/developing-an-english-efik-corpus-and-machine-translation-system-for-digitizatio--arxiv-2603.14873/2026-06-02T07:46:13.586Z https://www.opentrain.ai/papers/video-detector-a-dual-phase-vision-based-system-for-real-time-traffic-intersecti--arxiv-2603.14861/2026-06-17T23:10:36.366Z https://www.opentrain.ai/papers/pcodetrans-translate-decompiled-pseudocode-to-compilable-and-executable-equivale--arxiv-2603.14855/2026-06-15T05:42:33.769Z https://www.opentrain.ai/papers/ablate-and-rescue-a-causal-analysis-of-residual-stream-hyper-connections--arxiv-2603.14833/2026-06-18T02:52:32.420Z https://www.opentrain.ai/papers/lapro-dta-latent-dual-view-drug-representations-and-salient-protein-feature-extr--arxiv-2603.14792/2026-06-12T21:00:25.825Z https://www.opentrain.ai/papers/information-asymmetry-across-language-varieties-a-case-study-on-cantonese-mandar--arxiv-2603.14782/2026-06-17T20:30:09.605Z https://www.opentrain.ai/papers/p-2-rag-efficient-privacy-preserving-rag-service-supporting-arbitrary-top-k-retr--arxiv-2603.14778/2026-06-18T01:03:54.047Z https://www.opentrain.ai/papers/ho-sfl-hybrid-order-split-federated-learning-with-backprop-free-clients-and-dime--arxiv-2603.14773/2026-06-16T14:05:32.241Z https://www.opentrain.ai/papers/towards-privacy-preserving-machine-translation-at-the-inference-stage-a-new-task--arxiv-2603.14756/2026-06-15T01:32:24.691Z https://www.opentrain.ai/papers/criterion-referenceability-determines-llm-as-a-judge-validity-across-physics-ass--arxiv-2603.14732/2026-06-16T15:33:01.902Z https://www.opentrain.ai/papers/adaptertune-zero-initialized-low-rank-adapters-for-frozen-vision-transformers--arxiv-2603.14706/2026-06-18T03:17:35.308Z https://www.opentrain.ai/papers/creative-convergence-or-imitation-genre-specific-homogeneity-in-llm-generated-ch--arxiv-2603.14430/2026-06-16T23:21:35.902Z https://www.opentrain.ai/papers/bit-mcts-a-theme-based-bidirectional-mcts-approach-to-chinese-fiction-generation--arxiv-2603.14410/2026-06-14T12:37:39.149Z https://www.opentrain.ai/papers/exposing-long-tail-safety-failures-in-large-language-models-through-efficient-di--arxiv-2603.14355/2026-06-14T16:47:32.843Z https://www.opentrain.ai/papers/motivation-in-large-language-models--arxiv-2603.14347/2026-06-16T08:19:23.566Z https://www.opentrain.ai/papers/qimeng-codev-sva-training-specialized-llms-for-hardware-assertion-generation-via--arxiv-2603.14239/2026-06-18T02:10:15.799Z https://www.opentrain.ai/papers/vavanagi-a-community-run-platform-for-documentation-of-the-hula-language-in-papu--arxiv-2603.14210/2026-06-11T17:08:40.596Z https://www.opentrain.ai/papers/selective-fine-tuning-of-gpt-architectures-for-parameter-efficient-clinical-text--arxiv-2603.14183/2026-06-16T08:54:01.015Z https://www.opentrain.ai/papers/the-gelato-dataset-for-legislative-ner--arxiv-2603.14130/2026-06-13T07:32:06.679Z https://www.opentrain.ai/papers/oasissimp-an-open-source-asian-english-sentence-simplification-dataset--arxiv-2603.14111/2026-06-16T03:57:32.197Z https://www.opentrain.ai/papers/cmhl-contrastive-multi-head-learning-for-emotionally-consistent-text-classificat--arxiv-2603.14078/2026-06-17T18:02:19.194Z https://www.opentrain.ai/papers/neptam-a-nepali-tamang-parallel-corpus-and-baseline-machine-translation-experime--arxiv-2603.14053/2026-06-04T11:56:26.729Z https://www.opentrain.ai/papers/probing-neural-audio-codecs-for-distinctions-among-english-nuclear-tunes--arxiv-2603.14035/2026-06-17T09:36:42.830Z https://www.opentrain.ai/papers/large-language-models-reproduce-racial-stereotypes-when-used-for-text-annotation--arxiv-2603.13891/2026-06-17T08:27:55.187Z https://www.opentrain.ai/papers/pmiscore-an-unsupervised-approach-to-quantify-dialogue-engagement--arxiv-2603.13796/2026-06-09T14:11:54.338Z https://www.opentrain.ai/papers/ghananlp-parallel-corpora-comprehensive-multilingual-resources-for-low-resource--arxiv-2603.13793/2026-06-09T19:10:00.985Z https://www.opentrain.ai/papers/generate-then-correct-single-shot-global-correction-for-aspect-sentiment-quad-pr--arxiv-2603.13777/2026-06-14T17:40:16.480Z https://www.opentrain.ai/papers/causal-tracing-of-audio-text-fusion-in-large-audio-language-models--arxiv-2603.13768/2026-06-16T13:00:01.313Z https://www.opentrain.ai/papers/quarkmedbench-a-real-world-scenario-driven-benchmark-for-evaluating-large-langua--arxiv-2603.13691/2026-06-15T04:14:19.937Z https://www.opentrain.ai/papers/privacy-preserving-topic-wise-sentiment-analysis-of-the-iran-israel-usa-conflict--arxiv-2603.13655/2026-06-17T10:00:56.611Z https://www.opentrain.ai/papers/developing-the-psycogmetrics-ai-lab-to-evaluate-large-language-models-and-advanc--arxiv-2603.13126/2026-06-17T23:31:42.449Z https://www.opentrain.ai/papers/when-llm-judge-scores-look-good-but-best-of-n-decisions-fail--arxiv-2603.12520/2026-06-14T22:25:56.670Z https://www.opentrain.ai/papers/marked-pedagogies-examining-linguistic-biases-in-personalized-automated-writing--arxiv-2603.12471/2026-06-16T14:44:37.095Z https://www.opentrain.ai/papers/llm-augmented-therapy-normalization-and-aspect-based-sentiment-analysis-for-trea--arxiv-2603.12343/2026-06-17T07:01:56.761Z https://www.opentrain.ai/papers/separable-neural-architectures-as-a-primitive-for-unified-predictive-and-generat--arxiv-2603.12244/2026-06-14T21:35:24.480Z https://www.opentrain.ai/papers/neural-thickets-diverse-task-experts-are-dense-around-pretrained-weights--arxiv-2603.12228/2026-06-17T07:21:11.537Z https://www.opentrain.ai/papers/rdnet-region-proportion-aware-dynamic-adaptive-salient-object-detection-network--arxiv-2603.12215/2026-06-16T20:46:19.065Z https://www.opentrain.ai/papers/clasp-defending-hybrid-large-language-models-against-hidden-state-poisoning-atta--arxiv-2603.12206/2026-06-15T13:56:24.493Z https://www.opentrain.ai/papers/isocompute-playbook-optimally-scaling-sampling-compute-for-llm-rl--arxiv-2603.12151/2026-05-28T05:31:56.280Z https://www.opentrain.ai/papers/linking-perception-confidence-and-accuracy-in-mllms--arxiv-2603.12149/2026-06-17T09:00:47.033Z https://www.opentrain.ai/papers/sommbench-assessing-sommelier-expertise-of-language-models--arxiv-2603.12117/2026-06-16T22:06:21.981Z https://www.opentrain.ai/papers/to-words-and-beyond-probing-large-language-models-for-sentence-level-psycholingu--arxiv-2603.12105/2026-06-15T22:00:03.249Z https://www.opentrain.ai/papers/human-centred-llm-privacy-audits-findings-and-frictions--arxiv-2603.12094/2026-06-12T10:12:56.244Z https://www.opentrain.ai/papers/beyond-convolution-a-taxonomy-of-structured-operators-for-learning-based-image-p--arxiv-2603.12067/2026-06-14T17:21:24.708Z https://www.opentrain.ai/papers/coarse-guided-visual-generation-via-weighted-h-transform-sampling--arxiv-2603.12057/2026-06-16T22:19:55.257Z https://www.opentrain.ai/papers/translationese-as-a-rational-response-to-translation-task-difficulty--arxiv-2603.12050/2026-06-17T15:15:30.723Z https://www.opentrain.ai/papers/just-use-xml-revisiting-joint-translation-and-label-projection--arxiv-2603.12021/2026-06-18T07:21:56.921Z https://www.opentrain.ai/papers/btzsc-a-benchmark-for-zero-shot-text-classification-across-cross-encoders-embedd--arxiv-2603.11991/2026-06-16T14:05:15.215Z https://www.opentrain.ai/papers/chil-l-grader-calibrated-human-in-the-loop-short-answer-grading--arxiv-2603.11957/2026-06-15T16:10:36.625Z https://www.opentrain.ai/papers/large-language-models-for-biomedical-article-classification--arxiv-2603.11780/2026-06-13T07:36:20.684Z https://www.opentrain.ai/papers/legal-dc-benchmarking-retrieval-augmented-generation-for-legal-documents--arxiv-2603.11772/2026-05-06T08:27:59.747Z https://www.opentrain.ai/papers/truth-as-a-compression-artifact-in-language-model-training--arxiv-2603.11749/2026-06-16T15:42:36.530Z https://www.opentrain.ai/papers/semi-synthetic-parallel-data-for-translation-quality-estimation-a-case-study-of--arxiv-2603.11743/2026-06-16T21:06:55.158Z https://www.opentrain.ai/papers/utilitymax-prompting-a-formal-framework-for-multi-objective-large-language-model--arxiv-2603.11583/2026-06-18T06:10:57.297Z https://www.opentrain.ai/papers/can-small-language-models-use-what-they-retrieve-an-empirical-study-of-retrieval--arxiv-2603.11513/2026-05-06T14:26:13.695Z https://www.opentrain.ai/papers/beyond-polarity-multi-dimensional-llm-sentiment-signals-for-wti-crude-oil-future--arxiv-2603.11408/2026-06-16T01:02:32.111Z https://www.opentrain.ai/papers/temporal-text-classification-with-large-language-models--arxiv-2603.11295/2026-06-09T12:24:40.442Z https://www.opentrain.ai/papers/artificial-intelligence-for-sentiment-analysis-of-persian-poetry--arxiv-2603.11254/2026-06-10T00:25:52.427Z https://www.opentrain.ai/papers/a-systematic-study-of-pseudo-relevance-feedback-with-llms--arxiv-2603.11008/2026-06-10T00:30:53.669Z https://www.opentrain.ai/papers/tosss-a-cve-based-software-security-benchmark-for-large-language-models--arxiv-2603.10969/2026-06-15T20:14:24.969Z https://www.opentrain.ai/papers/when-fine-tuning-fails-and-when-it-generalises-role-of-data-diversity-and-mixed--arxiv-2603.10904/2026-06-16T14:20:19.211Z https://www.opentrain.ai/papers/lookaheadkv-fast-and-accurate-kv-cache-eviction-by-glimpsing-into-the-future-wit--arxiv-2603.10899/2026-06-13T09:54:57.788Z https://www.opentrain.ai/papers/pivotattack-rethinking-the-search-trajectory-in-hard-label-text-attacks-via-pivo--arxiv-2603.10842/2026-06-17T20:16:27.705Z https://www.opentrain.ai/papers/speaker-verification-with-speech-aware-llms-evaluation-and-augmentation--arxiv-2603.10827/2026-06-17T19:21:59.746Z https://www.opentrain.ai/papers/towards-intelligent-spectrum-management-spectrum-demand-estimation-using-graph-n--arxiv-2603.10802/2026-06-17T13:16:59.712Z https://www.opentrain.ai/papers/interpretable-chinese-metaphor-identification-via-llm-assisted-mipvu-rule-script--arxiv-2603.10784/2026-06-16T16:05:45.879Z https://www.opentrain.ai/papers/taking-shortcuts-for-categorical-vqa-using-super-neurons--arxiv-2603.10781/2026-06-16T15:41:04.403Z https://www.opentrain.ai/papers/large-language-models-as-annotators-for-machine-translation-quality-estimation--arxiv-2603.10775/2026-06-14T03:11:17.584Z https://www.opentrain.ai/papers/macereason-math-a-dataset-of-high-quality-multilingual-math-problems-ready-for-r--arxiv-2603.10767/2026-05-09T23:35:40.626Z https://www.opentrain.ai/papers/uav-traffic-scene-understanding-a-regulation-embedded-multi-modal-network-and-a--arxiv-2603.10722/2026-05-10T02:33:24.808Z https://www.opentrain.ai/papers/prism-differential-subspace-steering-for-prompt-highlighting-in-large-language-m--arxiv-2603.10705/2026-06-16T15:57:31.786Z https://www.opentrain.ai/papers/ails-ntua-at-semeval-2026-task-8-evaluating-multi-turn-rag-conversations--arxiv-2603.10524/2026-06-15T11:14:20.237Z https://www.opentrain.ai/papers/designing-service-systems-from-textual-evidence--arxiv-2603.10400/2026-05-15T20:54:38.252Z https://www.opentrain.ai/papers/maximizing-mutual-information-between-prompt-and-response-improves-llm-performan--arxiv-2603.19294/2026-06-18T07:22:24.136Z https://www.opentrain.ai/papers/vidia2std-a-parallel-corpus-and-methods-for-low-resource-vietnamese-dialect-to-s--arxiv-2603.10211/2026-06-16T02:41:28.355Z https://www.opentrain.ai/papers/remix-reinforcement-routing-for-mixtures-of-loras-in-llm-finetuning--arxiv-2603.10160/2026-06-16T14:05:21.191Z https://www.opentrain.ai/papers/lost-in-backpropagation-the-lm-head-is-a-gradient-bottleneck--arxiv-2603.10145/2026-06-17T00:57:19.388Z https://www.opentrain.ai/papers/the-generation-recognition-asymmetry-six-dimensions-of-a-fundamental-divide-in-f--arxiv-2603.10139/2026-06-11T09:25:15.284Z https://www.opentrain.ai/papers/hardware-efficient-approximate-convolution-with-tunable-error-tolerance-for-cnns--arxiv-2603.10100/2026-05-22T05:46:11.705Z https://www.opentrain.ai/papers/benchmarking-political-persuasion-risks-across-frontier-large-language-models--arxiv-2603.09884/2026-06-17T08:27:36.450Z https://www.opentrain.ai/papers/do-what-i-say-a-spoken-prompt-dataset-for-instruction-following--arxiv-2603.09881/2026-06-17T09:50:29.815Z https://www.opentrain.ai/papers/n-gram-like-language-models-predict-reading-time-best--arxiv-2603.09872/2026-05-22T07:52:16.728Z https://www.opentrain.ai/papers/a-graph-based-approach-to-spectrum-demand-prediction-using-hierarchical-attentio--arxiv-2603.09859/2026-06-17T07:38:12.870Z https://www.opentrain.ai/papers/scenebench-an-audio-understanding-benchmark-grounded-in-assistive-and-industrial--arxiv-2603.09853/2026-06-16T11:16:31.233Z https://www.opentrain.ai/papers/correction-of-transformer-based-models-with-smoothing-pseudo-projector--arxiv-2603.09815/2026-06-17T07:12:46.636Z https://www.opentrain.ai/papers/rbtact-rebuttal-as-supervision-for-actionable-review-feedback-generation--arxiv-2603.09723/2026-06-16T09:53:57.998Z https://www.opentrain.ai/papers/mugen-evaluating-and-improving-multi-audio-understanding-of-large-audio-language--arxiv-2603.09714/2026-06-17T02:39:05.532Z https://www.opentrain.ai/papers/build-borrow-or-just-fine-tune-a-political-scientist-s-guide-to-choosing-nlp-mod--arxiv-2603.09595/2026-05-19T20:42:09.625Z https://www.opentrain.ai/papers/cyberthreat-eval-can-large-language-models-automate-real-world-threat-research--arxiv-2603.09452/2026-06-16T02:40:55.641Z https://www.opentrain.ai/papers/loocomp-leverage-leave-one-out-strategy-to-encoder-only-transformer-for-efficien--arxiv-2603.09222/2026-06-17T08:42:50.854Z https://www.opentrain.ai/papers/from-word2vec-to-transformers-text-derived-composition-embeddings-for-filtering--arxiv-2603.08881/2026-06-16T15:14:34.819Z https://www.opentrain.ai/papers/multigrascco-a-multilingual-anonymization-benchmark-with-annotations-of-personal--arxiv-2603.08879/2026-04-09T01:55:15.335Z https://www.opentrain.ai/papers/fish-audio-s2-technical-report--arxiv-2603.08823/2026-06-17T16:35:12.956Z https://www.opentrain.ai/papers/how-far-can-unsupervised-rlvr-scale-llm-training--arxiv-2603.08660/2026-06-16T15:11:37.868Z https://www.opentrain.ai/papers/weakly-supervised-teacher-student-framework-with-progressive-pseudo-mask-refinem--arxiv-2603.08605/2026-06-16T14:05:22.403Z https://www.opentrain.ai/papers/a-dataset-for-probing-translationese-preferences-in-english-to-swedish-translati--arxiv-2603.08450/2026-06-13T13:01:22.353Z https://www.opentrain.ai/papers/coach-meets-quorum-a-framework-and-pipeline-for-aligning-user-expert-and-develop--arxiv-2603.08392/2026-05-31T10:07:55.441Z https://www.opentrain.ai/papers/how-much-do-llms-hallucinate-in-document-q-a-scenarios-a-172-billion-token-study--arxiv-2603.08274/2026-06-16T16:08:49.739Z https://www.opentrain.ai/papers/sensivity-of-llms-explanations-to-the-training-randomness-context-class-task-dep--arxiv-2603.08241/2026-06-18T04:17:44.747Z https://www.opentrain.ai/papers/tildeopen-llm-leveraging-curriculum-learning-to-achieve-equitable-language-repre--arxiv-2603.08182/2026-06-16T13:26:22.864Z https://www.opentrain.ai/papers/gender-bias-in-mt-for-a-genderless-language-new-benchmarks-for-basque--arxiv-2603.08153/2026-06-13T06:55:41.236Z https://www.opentrain.ai/papers/toward-robust-llm-based-judges-taxonomic-bias-evaluation-and-debiasing-optimizat--arxiv-2603.08091/2026-06-17T08:27:59.896Z https://www.opentrain.ai/papers/an-efficient-and-effective-evaluator-for-text2sql-models-on-unseen-and-unlabeled--arxiv-2603.07841/2026-06-17T09:27:28.858Z https://www.opentrain.ai/papers/arclight-a-lightweight-llm-inference-architecture-for-many-core-cpus--arxiv-2603.07770/2026-06-18T00:23:27.587Z https://www.opentrain.ai/papers/quadai-at-semeval-2026-task-3-ensemble-learning-of-hybrid-roberta-and-llms-for-d--arxiv-2603.07766/2026-06-18T07:00:14.581Z https://www.opentrain.ai/papers/stylebench-evaluating-speech-language-models-on-conversational-speaking-style-co--arxiv-2603.07599/2026-06-13T17:08:13.270Z https://www.opentrain.ai/papers/a-systematic-comparison-of-training-objectives-for-out-of-distribution-detection--arxiv-2603.07571/2026-06-17T16:26:51.463Z https://www.opentrain.ai/papers/the-dual-stream-transformer-channelized-architecture-for-interpretable-language--arxiv-2603.07461/2026-06-15T00:16:49.283Z https://www.opentrain.ai/papers/image-generation-models-a-technical-history--arxiv-2603.07455/2026-06-17T20:17:19.277Z https://www.opentrain.ai/papers/position-llms-must-use-functor-based-and-rag-driven-bias-mitigation-for-fairness--arxiv-2603.07368/2026-06-17T21:45:03.769Z https://www.opentrain.ai/papers/rilec-detection-and-generation-of-l1-russian-interference-errors-in-english-lear--arxiv-2603.07366/2026-06-16T04:11:14.290Z https://www.opentrain.ai/papers/taiwan-safety-benchmark-and-breeze-guard-toward-trustworthy-ai-for-taiwanese-man--arxiv-2603.07286/2026-06-14T15:00:12.553Z https://www.opentrain.ai/papers/grounding-machine-creativity-in-game-design-knowledge-representations-empirical--arxiv-2603.07101/2026-06-16T05:15:15.712Z https://www.opentrain.ai/papers/language-shapes-mental-health-evaluations-in-large-language-models--arxiv-2603.06910/2026-06-15T20:07:29.937Z https://www.opentrain.ai/papers/supporting-artifact-evaluation-with-llms-a-study-with-published-security-researc--arxiv-2603.06862/2026-06-13T18:21:00.563Z https://www.opentrain.ai/papers/validation-of-a-small-language-model-for-dsm-5-substance-category-classification--arxiv-2603.06836/2026-06-15T17:37:11.080Z https://www.opentrain.ai/papers/transparent-ai-for-mathematics-transformer-based-large-language-models-for-mathe--arxiv-2603.06348/2026-06-15T06:04:33.981Z https://www.opentrain.ai/papers/mapo-mixed-advantage-policy-optimization-for-long-horizon-multi-turn-dialogue--arxiv-2603.06194/2026-06-17T21:45:14.077Z https://www.opentrain.ai/papers/evaluating-austrian-a-level-german-essays-with-large-language-models-for-automat--arxiv-2603.06066/2026-06-17T03:24:25.645Z https://www.opentrain.ai/papers/who-we-are-where-we-are-mental-health-at-the-intersection-of-person-situation-an--arxiv-2603.05953/2026-05-29T08:14:32.935Z https://www.opentrain.ai/papers/lost-in-stories-consistency-bugs-in-long-story-generation-by-llms--arxiv-2603.05890/2026-06-17T19:01:48.330Z https://www.opentrain.ai/papers/confidence-before-answering-a-paradigm-shift-for-efficient-llm-uncertainty-estim--arxiv-2603.05881/2026-06-16T14:47:39.371Z https://www.opentrain.ai/papers/rose-reordered-sparsegpt-for-more-accurate-one-shot-large-language-models-prunin--arxiv-2603.05878/2026-06-14T22:55:24.663Z https://www.opentrain.ai/papers/orion-characterizing-and-programming-apple-s-neural-engine-for-llm-training-and--arxiv-2603.06728/2026-06-14T08:56:15.949Z https://www.opentrain.ai/papers/test-time-adaptation-via-many-shot-prompting-benefits-limits-and-pitfalls--arxiv-2603.05829/2026-06-16T16:08:43.401Z https://www.opentrain.ai/papers/towards-robust-retrieval-augmented-generation-based-on-knowledge-graph-a-compara--arxiv-2603.05698/2026-06-17T15:42:54.397Z https://www.opentrain.ai/papers/poet-x-memory-efficient-llm-training-by-scaling-orthogonal-transformation--arxiv-2603.05500/2026-06-02T09:56:41.118Z https://www.opentrain.ai/papers/the-spike-the-sparse-and-the-sink-anatomy-of-massive-activations-and-attention-s--arxiv-2603.05498/2026-06-08T23:52:54.962Z https://www.opentrain.ai/papers/censored-llms-as-a-natural-testbed-for-secret-knowledge-elicitation--arxiv-2603.05494/2026-06-16T02:33:14.850Z https://www.opentrain.ai/papers/nctb-qa-a-large-scale-bangla-educational-question-answering-dataset-and-benchmar--arxiv-2603.05462/2026-06-18T05:32:43.790Z https://www.opentrain.ai/papers/flashattention-4-algorithm-and-kernel-pipelining-co-design-for-asymmetric-hardwa--arxiv-2603.05451/2026-06-17T16:38:42.119Z https://www.opentrain.ai/papers/persianpunc-a-large-scale-dataset-and-bert-based-approach-for-persian-punctuatio--arxiv-2603.05314/2026-06-17T18:24:39.471Z https://www.opentrain.ai/papers/med-v1-small-language-models-for-zero-shot-and-scalable-biomedical-evidence-attr--arxiv-2603.05308/2026-06-16T18:00:35.842Z