- Importance of Prompt Optimisation for Error Detection in Medical Notes Using Language Models
Craig Myles, Patrick Schrempf, David Harris-Birtill · Feb 25, 2026 · Citations: 0
We show that automatic prompt optimisation with Genetic-Pareto (GEPA) improves error detection over the baseline accuracy performance from 0.669 to 0.785 with GPT-5 and 0.578 to 0.690 with Qwen3-32B, approaching the performance of medical…
- Sydney Telling Fables on AI and Humans: A Corpus Tracing Memetic Transfer of Persona between LLMs
Jiří Milička, Hana Bednářová · Feb 25, 2026 · Citations: 0
The way LLM-based entities conceive of the relationship between AI and humans is an important topic for both cultural and safety reasons.
- VeRO: An Evaluation Harness for Agents to Optimize Agents
Varun Ursekar, Apaar Shanker, Veronica Chatrath, Yuan, Xue · Feb 25, 2026 · Citations: 0
An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles.
- Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models
Binchi Zhang, Xujiang Zhao, Jundong Li, Haifeng Chen, Zhengzhang Chen · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads
Shaswat Patel, Vishvesh Trivedi, Yue Han, Yihuai Hong, Eunsol Choi · Feb 25, 2026 · Citations: 0
Across four multilingual benchmarks (MMLU-ProX, MGSM, MLQA, and XQuaD) and two model families (Qwen-2.5 and Llama-3.1), we demonstrate that masking RTH induces bigger performance drop than masking Retrieval Heads (RH).
- A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection
Mirza Raquib, Asif Pervez Polok, Kedar Nath Biswas, Rahat Uddin Azad, Saydul Akbar Murad · Feb 25, 2026 · Citations: 0
Evaluation uses multiple metrics, including accuracy, precision, recall, F1-score, Hamming loss, Cohens kappa, and AUC-ROC.
- How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
Yingqian Cui, Zhenwei Dai, Bing He, Zhan Shi, Hui Liu · Feb 25, 2026 · Citations: 0
Long Horizon
First, we observe pervasive shortcut behavior, where they achieve high accuracy without relying on latent reasoning.
- Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
Gustaw Opiełka, Hannes Rosenbusch, Claire E. Stevenson · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context
Aishwarya Verma, Laud Ammah, Olivia Nercy Ndlovu Lucas, Andrew Zaldivar, Vinodkumar Prabhakaran · Feb 25, 2026 · Citations: 0
Stereotype repositories are critical to assess generative AI model safety, but currently lack adequate global coverage.
- Detecting Hate and Inflammatory Content in Bengali Memes: A New Multimodal Dataset and Co-Attention Framework
Rakib Ullah, Mominul islam, Md Sanjid Hossain, Md Ismail Hossain · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Scaling In, Not Up? Testing Thick Citation Context Analysis with GPT-5 and Fragile Prompts
Arno Simons · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Decoder-based Sense Knowledge Distillation
Qitong Wang, Mohammed J. Zaki, Georgios Kollias, Vasileios Kalantzis · Feb 25, 2026 · Citations: 0
Extensive experiments on diverse benchmarks demonstrate that DSKD significantly enhances knowledge distillation performance for decoders, enabling generative models to inherit structured semantics while maintaining efficient training.
- Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
Hanna Yukhymenko, Anton Alexandrov, Martin Vechev · Feb 25, 2026 · Citations: 0
The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks.
- SumTablets: A Transliteration Dataset of Sumerian Tablets
Cole Simmons, Richard Diehl Martinez, Dan Jurafsky · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Improving Parametric Knowledge Access in Reasoning Language Models
Melody Ma, John Hewitt · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang · Feb 25, 2026 · Citations: 0
Long Horizon
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks.
- LiCQA : A Lightweight Complex Question Answering System
Sourav Saha, Dwaipayan Roy, Mandar Mitra · Feb 25, 2026 · Citations: 0
The results of our experiments show that LiCQA significantly outperforms these two state-of-the-art systems on benchmark data with noteworthy reduction in latency.
- Decoding the Hook: A Multimodal LLM Framework for Analyzing the Hooking Period of Video Ads
Kunpeng Zhang, Poppy Zhang, Shawndra Hill, Amel Awadelkarim · Feb 25, 2026 · Citations: 0
Traditional methods often miss the nuanced interplay of these components, requiring advanced frameworks for thorough evaluation.
- DySCO: Dynamic Attention-Scaling Decoding for Long-Context LMs
Xi Ye, Wuwei Zhang, Fangcong Yin, Howard Yen, Danqi Chen · Feb 25, 2026 · Citations: 0
Across multiple instruction-tuned and reasoning models, DySCO consistently improves performance on challenging long-context reasoning benchmarks, yielding relative gains of up to 25% on MRCR and LongBenchV2 at 128K context length with…
- Dynamic Personality Adaptation in Large Language Models via State Machines
Leon Pielage, Ole Hätscher, Mitja Back, Bernhard Marschall, Benjamin Risse · Feb 25, 2026 · Citations: 0
This work demonstrates the feasibility of modular, personality-adaptive architectures for education, customer support, and broader human-computer interaction.
- When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models
Satyam Kumar Navneet, Joydeep Chandra, Yong Zhang · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors
Lingfeng Ren, Weihao Yu, Runpeng Yu, Xinchao Wang · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- IndicIFEval: A Benchmark for Verifiable Instruction-Following Evaluation in 14 Indic Languages
Thanmay Jayakumar, Mohammed Safi Ur Rahman Khan, Raj Dabre, Ratish Puduppully, Anoop Kunchukuttan · Feb 25, 2026 · Citations: 0
Instruction-following benchmarks remain predominantly English-centric, leaving a critical evaluation gap for the hundreds of millions of Indic language speakers.
- SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
Patrick Tser Jern Kon, Archana Pradeep, Ang Chen, Alexander P. Ellis, Warren Hunt · Feb 25, 2026 · Citations: 0
Long Horizon
Our approach combines supervised fine-tuning on expert-augmented trajectories with agentic reinforcement learning that explicitly discourages degenerative looping and unproductive expert collaboration.
- Confidence-Driven Multi-Scale Model Selection for Cost-Efficient Inference
Bo-Wei Chen, Chung-Chi Chen, An-Zi Yen · Feb 25, 2026 · Citations: 0
Tool Use
Experiments on the Massive Multitask Language Understanding (MMLU) benchmark show that our approach achieves accuracy comparable to the largest model while reducing computational costs by 20\% to 40\%.
- Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models
Christian Nickel, Laura Schrewe, Florian Mai, Lucie Flek · Feb 25, 2026 · Citations: 0
Theory of Mind (ToM) refers to an agent's ability to model the internal states of others.
- DLT-Corpus: A Large-Scale Text Collection for the Distributed Ledger Technology Domain
Walter Hernandez Cruz, Peter Devine, Nikhil Vadgama, Paolo Tasca, Jiahua Xu · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition
Cheng-Yeh Yang, Chien-Chun Wang, Li-Wei Chen, Hung-Shin Lee, Hsin-Min Wang · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT
Louis Estève, Christophe Servan, Thomas Lavergne, Agata Savary · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for Low-dose CT imaging
Jitindra Fartiyal, Pedro Freire, Sergei K. Turitsyn, Sergei G. Solovski · Feb 25, 2026 · Citations: 0
- CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models
Miyu Oba, Saku Sugawara · Feb 25, 2026 · Citations: 0
Most existing benchmarks focus on judging grammatical acceptability, whereas the ability to interpret meanings conveyed by grammatical forms has received much less attention.
- RADAR: Reasoning as Discrimination with Aligned Representations for LLM-based Knowledge Graph Reasoning
Bo Xue, Yuan Jin, Luoyi Fu, Jiaxin Ding, Xinbing Wang · Feb 25, 2026 · Citations: 0
Across four benchmarks, RADAR achieves 5-6% relative gains on link prediction and triple classification over strong LLM baselines, while increasing task-relevant mutual information in intermediate representations by 62.9%, indicating more…
- MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models
Boqi Chen, Xudong Liu, Jiachuan Peng, Marianne Frey-Marti, Bang Zheng · Feb 25, 2026 · Citations: 0
Expert Verification
Multimodal large language models (MLLMs) have shown great potential in medical applications, yet existing benchmarks inadequately capture real-world clinical complexity.
- Large Language Models are Algorithmically Blind
Sohan Venkatesh, Ashish Mahendran Kurapath, Tejas Melkote · Feb 25, 2026 · Citations: 0
Models produce ranges far wider than true confidence intervals yet still fail to contain the true algorithmic mean in the majority of instances; most perform worse than random guessing and the marginal above-random performance of the best…
- Small Wins Big: Comparing Large Language Models and Domain Fine-Tuned Models for Sarcasm Detection in Code-Mixed Hinglish Text
Bitan Majumder, Anirban Sen · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen, Jixing Li · Feb 25, 2026 · Citations: 0
Pairwise Preference
Analysis shows that, by enabling on-policy thinking language selection as an action during RL, ExpLang effectively extends the RL exploration space with diversified language preference and improves the RL exploitation outcome with leveraged…
- DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs
Yanbin Wei, Jiangyue Yan, Chun Kang, Yang Chen, Hua Liu · Feb 25, 2026 · Citations: 0
Pairwise Preference
This ``one-size-fits-all'' strategy often neglects model-specific and task-specific preferences, resulting in inaccurate or over-lengthy responses to graph-related queries.
- Personalized Graph-Empowered Large Language Model for Proactive Information Access
Chia Cheng Chang, An-Zi Yen, Hen-Hsen Huang, Hsin-Hsi Chen · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices
Dezhi Kong, Zhengzhao Feng, Qiliang Liang, Hao Wang, Haofei Sun · Feb 25, 2026 · Citations: 0
To overcome these challenges, we introduce ProactiveMobile, a comprehensive benchmark designed to systematically advance research in this domain.
- Distill and Align Decomposition for Enhanced Claim Verification
Jabez Magomere, Elena Kochkina, Samuel Mensah, Simerjot Kaur, Fernando Acero · Feb 25, 2026 · Citations: 0
Across six evaluation settings, our trained 8B decomposer improves downstream verification performance to (71.75%) macro-F1, outperforming prompt-based approaches ((+1.99), (+6.24)) and existing RL methods ((+5.84)).
- FewMMBench: A Benchmark for Multimodal Few-Shot Learning
Mustafa Dogan, Ilker Kesen, Iacer Calixto, Aykut Erdem, Erkut Erdem · Feb 25, 2026 · Citations: 0
Demonstrations
In this paper, we introduce FewMMBench, a comprehensive benchmark designed to evaluate MLLMs under few-shot conditions, with a focus on In-Context Learning (ICL) and Chain-of-Thought (CoT) prompting.
- Scalable Kernel-Based Distances for Statistical Inference and Integration
Masha Naslidnyk · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- xai-cola: A Python library for sparsifying counterfactual explanations
Lin Zhu, Lei You · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- JSAM: Privacy Straggler-Resilient Joint Client Selection and Incentive Mechanism Design in Differentially Private Federated Learning
Ruichen Xu, Ying-Jun Angela Zhang, Jianwei Huang · Feb 25, 2026 · Citations: 0
Extensive evaluations on MNIST and CIFAR-10 demonstrate that JSAM achieves up to 15% improvement in test accuracy compared to existing unbiased selection mechanisms while maintaining cost efficiency across varying data heterogeneity levels.
- DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion
Marcel Lamott, Saifullah Saifullah, Nauman Riaz, Yves-Noel Weweler, Tobias Alt-Veit · Feb 25, 2026 · Citations: 0
We evaluate across eleven benchmarks spanning key information extraction, question answering, document classification, and document layout analysis.
- Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem
Heejin Jo · Feb 25, 2026 · Citations: 0
Large language models consistently fail the "car wash problem," a viral reasoning benchmark requiring implicit physical constraint inference.
- D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models
Shunsuke Ubukata · Feb 25, 2026 · Citations: 0
Long Horizon
In this study, we propose Disciplined Chain-of-Thought (D-CoT), a novel framework that enforces a structured reasoning process using control tags -- such as <TEMP_LOW> for fact-checking and <TEMP_HIGH> for multi-perspective exploration --…
- Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs
Heng Wang, Changxing Wu · Feb 25, 2026 · Citations: 0
Experimental results on PDTB demonstrate that our approach significantly improves IDRR performance, while human evaluation further confirms that the generated explanations enhance model interpretability.
- fEDM+: A Risk-Based Fuzzy Ethical Decision Making Framework with Principle-Level Explainability and Pluralistic Validation
Abeer Dyoub, Francesca A. Lisi · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- The ASIR Courage Model: A Phase-Dynamic Framework for Truth Transitions in Human and AI Systems
Hyo Jin Kim · Feb 25, 2026 · Citations: 0
Pairwise Preference
Although initially formulated for human truth-telling under asymmetric stakes, the same phase-dynamic architecture extends to AI systems operating under policy constraints and alignment filters.
- Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization
MD. Sagor Chowdhury, Adiba Fairooz Chowdhury · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
Shiqi Yan, Yubo Chen, Ruiqi Zhou, Zhengxi Yao, Shuai Chen · Feb 25, 2026 · Citations: 0
Demonstrations
Extensive experiments on five KGQA benchmark datasets demonstrate that, to the best of our knowledge, our method achieves state-of-the-art performance, outperforming not only open-source but also even closed-source LLMs.
- Evaluating the relationship between regularity and learnability in recursive numeral systems using Reinforcement Learning
Andrea Silvi, Ponrawee Prasertsom, Jennifer Culbertson, Devdatt Dubhashi, Moa Johansson · Feb 25, 2026 · Citations: 0
Human recursive numeral systems (i.e., counting systems such as English base-10 numerals), like many other grammatical systems, are highly regular.
- Two-Stage Active Distribution Network Voltage Control via LLM-RL Collaboration: A Hybrid Knowledge-Data-Driven Approach
Xu Yang, Chenhui Lin, Xiang Ma, Dong Liu, Ran Zheng · Feb 25, 2026 · Citations: 0
Considering the operational scenarios and requirements in real-world ADNs, in this paper, we propose a hybrid knowledge-data-driven approach that leverages dynamic collaboration between a large language model (LLM) agent and a reinforcement…
- SurGo-R1: Benchmarking and Modeling Contextual Reasoning for Operative Zone in Surgical Video
Guanyi Qin, Xiaozhen Wang, Zhu Zhuo, Chang Han Low, Yuancan Xiao · Feb 25, 2026 · Citations: 0
Expert Verification
Existing AI systems offer binary safety verification or static detection, ignoring the phase-dependent nature of intraoperative reasoning.
- Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
Jianghao Yin, Qin Chen, Kedi Chen, Jie Zhou, Xingjiao Wu · Feb 25, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning
Tomoya Kawabe, Rin Takano · Feb 25, 2026 · Citations: 0
Long Horizon
We present a hierarchical multi-agent LLM-based planner with prompt optimization: an upper layer decomposes tasks and assigns them to lower-layer agents, which generate PDDL problems solved by a classical planner.
- DWA-KD: Dual-Space Weighting and Time-Warped Alignment for Cross-Tokenizer Knowledge Distillation
Duc Trung Vu, Pham Khanh Chi, Dat Phi Van, Linh Ngo Van, Sang Dinh · Feb 25, 2026 · Citations: 0
Extensive experiments across diverse NLP benchmarks demonstrate that DWA-KD outperforms state-of-the-art KD baselines, while ablation studies confirm the complementary contributions of entropy-based token weighting and embedding and final…
- Following the Diagnostic Trace: Visual Cognition-guided Cooperative Network for Chest X-Ray Diagnosis
Shaoxuan Wu, Jingkun Chen, Chong Ma, Cong Shen, Xiao Zhang · Feb 25, 2026 · Citations: 0
Human-AI collaboration seeks to enhance the reliability of diagnostic models by integrating the behaviors of controllable radiologists.
- CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
Zhijiang Tang, Linhua Wang, Jiaxin Qi, Weihao Jiang, Peng Hou · Feb 25, 2026 · Citations: 0
Pairwise Preference
Image captioning remains a fundamental task for vision language understanding, yet ground-truth supervision still relies predominantly on human-annotated references.