HFEPX Daily Archive: 2026-02-25

Research Utility Snapshot

Papers Published On This Date

• Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

  Hanna Yukhymenko, Anton Alexandrov, Martin Vechev · Feb 25, 2026

  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

  Sumerian transliteration is a conventional system for representing a scholar's interpretation of a tablet in the Latin script.

• Improving Parametric Knowledge Access in Reasoning Language Models

  Melody Ma, John Hewitt · Feb 25, 2026

  We study reasoning for accessing world knowledge stored in a language model's parameters.

• 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

  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

  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.

• DySCO: Dynamic Attention-Scaling Decoding for Long-Context LMs

  Xi Ye, Wuwei Zhang, Fangcong Yin, Howard Yen, Danqi Chen · Feb 25, 2026

  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 modes

• Dynamic Personality Adaptation in Large Language Models via State Machines

  Leon Pielage, Ole Hätscher, Mitja Back, Bernhard Marschall, Benjamin Risse · Feb 25, 2026

  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

  Large Language Models (LLMs) are increasingly used to ``professionalize'' workplace communication, often at the cost of linguistic identity.

• 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

  Object hallucination is a critical issue in Large Vision-Language Models (LVLMs), where outputs include objects that do not appear in the input image.

• 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

  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

  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

  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

  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

  We introduce DLT-Corpus, the largest domain-specific text collection for Distributed Ledger Technology (DLT) research to date: 2.98 billion tokens from 22.12 million documents spanning scientific literature (37,440 publications), United Sta

• 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

  Low-resource automatic speech recognition (ASR) continues to pose significant challenges, primarily due to the limited availability of transcribed data for numerous languages.

• A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT

  Louis Estève, Christophe Servan, Thomas Lavergne, Agata Savary · Feb 25, 2026

  Diversity has been gaining interest in the NLP community in recent years.

• CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models

  Miyu Oba, Saku Sugawara · Feb 25, 2026

  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

  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 r

• 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

  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

  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 m

• 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

  Sarcasm detection in multilingual and code-mixed environments remains a challenging task for natural language processing models due to structural variations, informal expressions, and low-resource linguistic availability.

• 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

  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

  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

  Since individuals may struggle to recall all life details and often confuse events, establishing a system to assist users in recalling forgotten experiences is essential.

• Distill and Align Decomposition for Enhanced Claim Verification

  Jabez Magomere, Elena Kochkina, Samuel Mensah, Simerjot Kaur, Fernando Acero · Feb 25, 2026

  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

  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

  Representing, comparing, and measuring the distance between probability distributions is a key task in computational statistics and machine learning.

• xai-cola: A Python library for sparsifying counterfactual explanations

  Lin Zhu, Lei You · Feb 25, 2026

  Counterfactual explanation (CE) is an important domain within post-hoc explainability.

• 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

  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

  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

  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

  Long Horizon

  Chain-of-Thought (CoT) distillation from Large Language Models (LLMs) often induces "overthinking" in Small Language Models (SLMs), leading to performance degradation and excessive token consumption.

• Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs

  Heng Wang, Changxing Wu · Feb 25, 2026

  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

  In a previous work, we introduced the fuzzy Ethical Decision-Making framework (fEDM), a risk-based ethical reasoning architecture grounded in fuzzy logic.

• The ASIR Courage Model: A Phase-Dynamic Framework for Truth Transitions in Human and AI Systems

  Hyo Jin Kim · Feb 25, 2026

  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

  We describe our end-to-end system for Bengali long-form speech recognition (ASR) and speaker diarization submitted to the DL Sprint 4.0 competition on Kaggle.

• 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

  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

  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

  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

  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

  Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems.

• Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning

  Tomoya Kawabe, Rin Takano · Feb 25, 2026

  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

  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 h

• 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

  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

  Pairwise Preference

  Image captioning remains a fundamental task for vision language understanding, yet ground-truth supervision still relies predominantly on human-annotated references.

• Sparsity Induction for Accurate Post-Training Pruning of Large Language Models

  Minhao Jiang, Zhikai Li, Xuewen Liu, Jing Zhang, Mengjuan Chen · Feb 25, 2026

  Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency.

• PPCR-IM: A System for Multi-layer DAG-based Public Policy Consequence Reasoning and Social Indicator Mapping

  Zichen Song, Weijia Li · Feb 25, 2026

  For each policy episode, the system outputs a structured record containing the DAG, indicator mappings, and three evaluation measures: an expected-indicator coverage score, a discovery rate for overlooked but relevant indicators, and a rela

• Mitigating Structural Noise in Low-Resource S2TT: An Optimized Cascaded Nepali-English Pipeline with Punctuation Restoration

  Tangsang Chongbang, Pranesh Pyara Shrestha, Amrit Sarki, Anku Jaiswal · Feb 25, 2026

  We first establish highly proficient ASR and NMT components: a Wav2Vec2-XLS-R-300m model achieved a state-of-the-art 2.72% CER on OpenSLR-54, and a multi-stage fine-tuned MarianMT model reached a 28.32 BLEU score on the FLORES-200 benchmark

• Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion

  Yexing Du, Youcheng Pan, Zekun Wang, Zheng Chu, Yichong Huang · Feb 25, 2026

  Experimental results demonstrate that our framework surpasses all existing methods on the Multi30K multimodal machine translation benchmark, achieving new state-of-the-art results.

• Multi-dimensional Assessment and Explainable Feedback for Counselor Responses to Client Resistance in Text-based Counseling with LLMs

  Anqi Li, Ruihan Wang, Zhaoming Chen, Yuqian Chen, Yu Lu · Feb 25, 2026

  Although current NLP research has examined overall counseling quality and general therapeutic skills, it fails to provide granular evaluations of high-stakes moments where clients exhibit resistance.

• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination

  Chenyv Liu, Wentao Tan, Lei Zhu, Fengling Li, Jingjing Li · Feb 25, 2026

  Long Horizon

  Reinforcement learning enhances physical grounding through exploration yet typically relies on external reward signals that remain isolated from the agent's internal states.

• RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning

  Yukun Chen, Jiaming Li, Longze Chen, Ze Gong, Jingpeng Li · Feb 25, 2026

  Rubric Rating

  Extensive experiments on various visual reasoning benchmarks show that RuCL yields a remarkable +7.83% average improvement over the Qwen2.5-VL-7B model, achieving a state-of-the-art accuracy of 60.06%.

• When More Is Less: A Systematic Analysis of Spatial and Commonsense Information for Visual Spatial Reasoning

  Muku Akasaka, Soyeon Caren Han · Feb 25, 2026

  In this paper, we conduct a hypothesis-driven analysis of information injection for VSR across three representative VLMs and two public benchmarks.

• Virtual Biopsy for Intracranial Tumors Diagnosis on MRI

  Xinzhe Luo, Shuai Shao, Yan Wang, Jiangtao Wang, Yutong Bai · Feb 25, 2026

  To address these challenges, we construct the ICT-MRI dataset - the first public biopsy-verified benchmark with 249 cases across four categories.

• Structurally Aligned Subtask-Level Memory for Software Engineering Agents

  Kangning Shen, Jingyuan Zhang, Chenxi Sun, Wencong Zeng, Yang Yue · Feb 25, 2026

  Long Horizon

  Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.

• MixSarc: A Bangla-English Code-Mixed Corpus for Implicit Meaning Identification

  Kazi Samin Yasar Alam, Md Tanbir Chowdhury, Tamim Ahmed, Ajwad Abrar, Md Rafid Haque · Feb 25, 2026

  We benchmark transformer-based models and evaluate zero-shot large language models under structured prompting.

• Retrieval Challenges in Low-Resource Public Service Information: A Case Study on Food Pantry Access

  Touseef Hasan, Laila Cure, Souvika Sarkar · Feb 25, 2026

  We conduct a pilot evaluation study using community-sourced queries to examine system behavior in realistic scenarios.

• Exploring Human-Machine Coexistence in Symmetrical Reality

  Zhenliang Zhang · Feb 25, 2026

  In the context of the evolution of artificial intelligence (AI), the interaction between humans and AI entities has become increasingly salient, challenging the conventional human-centric paradigms of human-machine interaction.

• Power and Limitations of Aggregation in Compound AI Systems

  Nivasini Ananthakrishnan, Meena Jagadeesan · Feb 25, 2026

  In this work, we investigate the power and limitations of aggregation within a stylized principal-agent framework.

• Revisiting RAG Retrievers: An Information Theoretic Benchmark

  Wenqing Zheng, Dmitri Kalaev, Noah Fatsi, Daniel Barcklow, Owen Reinert · Feb 25, 2026

  Existing benchmarks primarily compare entire RAG pipelines or introduce new datasets, providing little guidance on selecting or combining retrievers themselves.

Recent Daily Archives