HFEPX Daily Archive: 2026-02-23

Research Utility Snapshot

Papers Published On This Date

• MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation

  Taha Koleilat, Hojat Asgariandehkordi, Omid Nejati Manzari, Berardino Barile, Yiming Xiao · Feb 23, 2026

  Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts.

• Case-Aware LLM-as-a-Judge Evaluation for Enterprise-Scale RAG Systems

  Mukul Chhabra, Luigi Medrano, Arush Verma · Feb 23, 2026

  Enterprise Retrieval-Augmented Generation (RAG) assistants operate in multi-turn, case-based workflows such as technical support and IT operations, where evaluation must reflect operational constraints, structured identifiers (e.g., error c

• How communicatively optimal are exact numeral systems? Once more on lexicon size and morphosyntactic complexity

  Chundra Cathcart, Arne Rubehn, Katja Bocklage, Luca Ciucci, Kellen Parker van Dam · Feb 23, 2026

  Recent research argues that exact recursive numeral systems optimize communicative efficiency by balancing a tradeoff between the size of the numeral lexicon and the average morphosyntactic complexity (roughly length in morphemes) of numera

• Natural Language Processing Models for Robust Document Categorization

  Radoslaw Roszczyk, Pawel Tecza, Maciej Stodolski, Krzysztof Siwek · Feb 23, 2026

  This article presents an evaluation of several machine learning methods applied to automated text classification, alongside the design of a demonstrative system for unbalanced document categorization and distribution.

• No One Size Fits All: QueryBandits for Hallucination Mitigation

  Nicole Cho, William Watson, Alec Koppel, Sumitra Ganesh, Manuela Veloso · Feb 23, 2026

  Advanced reasoning capabilities in Large Language Models (LLMs) have led to more frequent hallucinations; yet most mitigation work focuses on open-source models for post-hoc detection and parameter editing.

• An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models

  Cathy Shyr, Yan Hu, Rory J. Tinker, Thomas A. Cassini, Kevin W. Byram · Feb 23, 2026

  Expert Verification

  Existing artificial intelligence approaches typically optimize individual components of phenotyping but do not operationalize the full clinical workflow of extracting features from clinical text, standardizing them to Human Phenotype Ontolo

• What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance

  William Watson, Nicole Cho, Sumitra Ganesh, Manuela Veloso · Feb 23, 2026

  We operationalize this insight by constructing a 22-dimension query feature vector covering clause complexity, lexical rarity, and anaphora, negation, answerability, and intention grounding, all known to affect human comprehension.

• InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation

  Yu Li, Pranav Narayanan Venkit, Yada Pruksachatkun, Chien-Sheng Wu · Feb 23, 2026

  Existing evaluation approaches rely on demographic surveys, personality questionnaires, or short AI-led interviews as proxies, but lack direct assessment against what individuals actually said.

• A Very Big Video Reasoning Suite

  Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thaddäus Wiedemer · Feb 23, 2026

  We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities.

• KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration

  Mohammad Amanlou, Erfan Shafiee Moghaddam, Yasaman Amou Jafari, Mahdi Noori, Farhan Farsi · Feb 23, 2026

  Results show that KNIGHT enables token- and cost-efficient generation from a reusable graph representation, achieves high quality across these criteria, and yields model rankings aligned with MMLU-style benchmarks, while supporting topic-sp

• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization

  Mert Cemri, Shubham Agrawal, Akshat Gupta, Shu Liu, Audrey Cheng · Feb 23, 2026

  The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operators within evolutionary loops.

• To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering

  Zaifu Zhan, Min Zeng, Shuang Zhou, Yiran Song, Xiaoyi Chen · Feb 23, 2026

  Two open-source LLMs (Llama-3.1-8B and Qwen-2.5-7B) were evaluated on four biomedical QA benchmarks-HeadQA, MedQA-USMLE, MedMCQA, and PubMedQA.

• NanoKnow: How to Know What Your Language Model Knows

  Lingwei Gu, Nour Jedidi, Jimmy Lin · Feb 23, 2026

  Towards the goal of understanding how knowledge is encoded by LLMs, we release NanoKnow, a benchmark dataset that partitions questions from Natural Questions and SQuAD into splits based on whether their answers are present in nanochat's pre

• BabyLM Turns 4 and Goes Multilingual: Call for Papers for the 2026 BabyLM Workshop

  Leshem Choshen, Ryan Cotterell, Mustafa Omer Gul, Jaap Jumelet, Tal Linzen · Feb 23, 2026

  For the workshop, we call for papers related to the overall theme of BabyLM, which includes training efficiency, small-scale training datasets, cognitive modeling, model evaluation, and architecture innovation.

• How Retrieved Context Shapes Internal Representations in RAG

  Samuel Yeh, Sharon Li · Feb 23, 2026

  Retrieval-augmented generation (RAG) enhances large language models (LLMs) by conditioning generation on retrieved external documents, but the effect of retrieved context is often non-trivial.

• Multilingual Large Language Models do not comprehend all natural languages to equal degrees

  Natalia Moskvina, Raquel Montero, Masaya Yoshida, Ferdy Hubers, Paolo Morosi · Feb 23, 2026

  Large Language Models (LLMs) play a critical role in how humans access information.

• Structured Prompt Language: Declarative Context Management for LLMs

  Wen G. Gong · Feb 23, 2026

  SPL-flow extends SPL into resilient agentic pipelines with a three-tier provider fallback strategy (Ollama -> OpenRouter -> self-healing retry) fully transparent to the .spl script.

• Entropy in Large Language Models

  Marco Scharringhausen · Feb 23, 2026

  In this study, the output of large language models (LLM) is considered an information source generating an unlimited sequence of symbols drawn from a finite alphabet.

• Position: General Alignment Has Hit a Ceiling; Edge Alignment Must Be Taken Seriously

  Han Bao, Yue Huang, Xiaoda Wang, Zheyuan Zhang, Yujun Zhou · Feb 23, 2026

  We take the position that the dominant paradigm of General Alignment, which compresses diverse human values into a single scalar reward, reaches a structural ceiling in settings with conflicting values, plural stakeholders, and irreducible

• AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization

  Fahmida Liza Piya, Rahmatollah Beheshti · Feb 23, 2026

  We present AgenticSum, an inference-time, agentic framework that separates context selection, generation, verification, and targeted correction to reduce hallucinated content.

• gencat: Generative computerized adaptive testing

  Wanyong Feng, Andrew Lan · Feb 23, 2026

  Pairwise Preference

  We train the model in a two-step process, first via Supervised Fine-Tuning and then via preference optimization for knowledge-response alignment.

• QUIETT: Query-Independent Table Transformation for Robust Reasoning

  Gaurav Najpande, Tampu Ravi Kumar, Manan Roy Choudhury, Neha Valeti, Yanjie Fu · Feb 23, 2026

  Experiments on four benchmarks, WikiTQ, HiTab, NQ-Table, and SequentialQA show consistent gains across models and reasoning paradigms, with particularly strong improvements on a challenge set of structurally diverse, unseen questions.

• Exploring Anti-Aging Literature via ConvexTopics and Large Language Models

  Lana E. Yeganova, Won G. Kim, Shubo Tian, Natalie Xie, Donald C. Comeau · Feb 23, 2026

  Common clustering and topic modeling approaches such as K-means or LDA remain sensitive to initialization and prone to local optima, limiting reproducibility and evaluation.

• Cross-lingual Matryoshka Representation Learning across Speech and Text

  Yaya Sy, Dioula Doucouré, Christophe Cerisara, Irina Illina · Feb 23, 2026

  We introduce large-scale data curation pipelines and new benchmarks, compare modeling strategies, and show that modality fusion within a frozen text Matryoshka model performs best.

• Contextual Safety Reasoning and Grounding for Open-World Robots

  Zachary Ravichandran, David Snyder, Alexander Robey, Hamed Hassani, Vijay Kumar · Feb 23, 2026

  Web Browsing

  Traditional safety approaches enforce fixed constraints in user-specified contexts, limiting their ability to handle the open-ended contextual variability of real-world deployment.

• ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting

  Yuxing Tian, Fengran Mo, Weixu Zhang, Yiyan Qi, Jian-Yun Nie · Feb 23, 2026

  The strong capabilities of recent Large Language Models (LLMs) have made them highly effective for zero-shot re-ranking task.

• Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval

  Yibo Yan, Jiahao Huo, Guanbo Feng, Mingdong Ou, Yi Cao · Feb 23, 2026

  We begin by examining the benchmark landscape, and subsequently dive into the methodological evolution, categorizing approaches into three primary aspects: multimodal embedding models, multimodal reranker models, and the integration of Retr

• Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming

  Ian Steenstra, Paola Pedrelli, Weiyan Shi, Stacy Marsella, Timothy W. Bickmore · Feb 23, 2026

  Red Team

  Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the complex, longitudinal risks inherent in therapeutic dialogue.

• When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

  Krzysztof Adamkiewicz, Brian Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue · Feb 23, 2026

  Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following.

• Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling

  Xiang Li, Zikai Wei, Yiyan Qi, Wanyun Zhou, Xiang Liu · Feb 23, 2026

  Financial market movements are often driven by discrete financial events conveyed through news, whose impacts are heterogeneous, abrupt, and difficult to capture under purely numerical prediction objectives.

• DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning

  Zhongwei Wan, Yun Shen, Zhihao Dou, Donghao Zhou, Yu Zhang · Feb 23, 2026

  Experiments on multiple reasoning benchmarks demonstrate consistent improvements in accuracy and pass@k, highlighting the importance of dual-scale diversity for deep exploration in RLVR.

• Denotational Semantics for ODRL: Knowledge-Based Constraint Conflict Detection

  Daham Mustafa, Diego Collarana, Yixin Peng, Rafiqul Haque, Christoph Lange-Bever · Feb 23, 2026

  We validate it with 154 benchmarks across six knowledge base families (GeoNames, ISO 3166, W3C DPV, a GDPR-derived taxonomy, BCP 47, and ISO 639-3) and four structural KBs targeting adversarial edge cases.

• Axis Decomposition for ODRL: Resolving Dimensional Ambiguity in Policy Constraints through Interval Semantics

  Daham Mustafa, Diego Collarana, Yixin Peng, Rafiqul Haque, Christoph Lange-Bever · Feb 23, 2026

  For these operands, a single scalar constraint admits one interpretation per axis, making policy evaluation non-deterministic.

• SHIELD: Semantic Heterogeneity Integrated Embedding for Latent Discovery in Clinical Trial Safety Signals

  Francois Vandenhende, Anna Georgiou, Theodoros Psaras, Ellie Karekla · Feb 23, 2026

  We present SHIELD, a novel methodology for automated and integrated safety signal detection in clinical trials.

• SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation

  Jingzhuo Wu, Jiajun Zhang, Keyan Jin, Dehua Ma, Junbo Wang · Feb 23, 2026

  Multi Agent

  This limitation stems from the inability of current single-model and static multi-agent systems to perceive and adapt to stylistic variations.

• MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning

  Wall Kim, Chaeyoung Song, Hanul Kim · Feb 23, 2026

  Recently, TabPFN has gained attention as a foundation model for tabular data.

• Keyboards for the Endangered Idu Mishmi Language

  Akhilesh Kakolu Ramarao · Feb 23, 2026

  We present a mobile and desktop keyboard suite for Idu Mishmi, an endangered Trans-Himalayan language spoken by approximately 11,000 people in Arunachal Pradesh, India.

• NILE: Formalizing Natural-Language Descriptions of Formal Languages

  Tristan Kneisel, Marko Schmellenkamp, Fabian Vehlken, Thomas Zeume · Feb 23, 2026

  This is motivated from educational scenarios where learners describe a formal language (presented, e.g., by a finite state automaton, regular expression, pushdown automaton, context-free grammar or in set notation) in natural language, and

• Continuous Telemonitoring of Heart Failure using Personalised Speech Dynamics

  Yue Pan, Xingyao Wang, Hanyue Zhang, Liwei Liu, Changxin Li · Feb 23, 2026

  Long Horizon

  The model's high sensitivity was further corroborated by additional follow-up data, confirming its efficacy in predicting HF deterioration and its potential to secure patient safety in remote, home-based settings.

• KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge

  Alex Robertson, Huizhi Liang, Mahbub Gani, Rohit Kumar, Srijith Rajamohan · Feb 23, 2026

  Existing benchmarks are limited by static and narrow questions, leading to limited coverage and misleading evaluations.

• Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding

  Roberto Tacconelli · Feb 23, 2026

  An out-of-distribution (OOD) evaluation on a document published after the model's training cutoff confirms these gains are not memorization artifacts, achieving 0.723 bpb on unseen text.

• Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning

  Borisiuk Anna, Andrey Savchenko, Alexander Panchenko, Elena Tutubalina · Feb 23, 2026

  In this paper, we introduce DUAL (Dual Unlearning Evaluation across Training Stages), a benchmark of 28.6k Wikidata-derived triplets annotated with fact popularity using Wikipedia link counts and LLM-based salience scores.

• Eye-Tracking-while-Reading: A Living Survey of Datasets with Open Library Support

  Deborah N. Jakobi, David R. Reich, Paul Prasse, Jana M. Hofmann, Lena S. Bolliger · Feb 23, 2026

  Eye-tracking-while-reading corpora are a valuable resource for many different disciplines and use cases.

• DEEP: Docker-based Execution and Evaluation Platform

  Sergio Gómez González, Miguel Domingo, Francisco Casacuberta · Feb 23, 2026

  Comparative evaluation of several systems is a recurrent task in researching.

• Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering

  Wuzhenghong Wen, Bowen Zhou, Jinwen Huang, Xianjie Wu, Yuwei Sun · Feb 23, 2026

  Experiments on multiple TKGQA benchmarks demonstrate consistent improvements over multiple baselines.

• Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework

  Yibo Yan, Mingdong Ou, Yi Cao, Xin Zou, Jiahao Huo · Feb 23, 2026

  Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications.

• Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining

  Jeffrey Li, Josh Gardner, Doug Kang, Fangping Shi, Karanjeet Singh · Feb 23, 2026

  This suggests a simple intervention: by taking a Union over different extractors, we can increase the token yield of DCLM-Baseline by up to 71% while maintaining benchmark performance.

• Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation

  Rizhuo Huang, Yifan Feng, Rundong Xue, Shihui Ying, Jun-Hai Yong · Feb 23, 2026

  Expert Verification

  Additionally, we present \textbf{HyperDocRED}, a rigorously annotated benchmark for document-level knowledge hypergraph extraction.

• How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1

  Yinuo Xu, Shuo Lu, Jianjie Cheng, Meng Wang, Qianlong Xie · Feb 23, 2026

  Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation.

• Classroom Final Exam: An Instructor-Tested Reasoning Benchmark

  Chongyang Gao, Diji Yang, Shuyan Zhou, Xichen Yan, Luchuan Song · Feb 23, 2026

  Long Horizon

  We introduce \CFE{} (\textbf{C}lassroom \textbf{F}inal \textbf{E}xam), a multimodal benchmark for evaluating the reasoning capabilities of large language models across more than 20 STEM domains.

• Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference

  Arindam Khaled · Feb 23, 2026

  In this work, we propose "Pyramid MoA", a hierarchical Mixture-of-Agents architecture that uses a lightweight Router to dynamically escalate queries only when necessary.

• Can Large Language Models Replace Human Coders? Introducing ContentBench

  Michael Haman · Feb 23, 2026

  Critique Edit

  This paper introduces ContentBench, a public benchmark suite that helps answer this replacement question by tracking how much agreement low-cost LLMs achieve and what they cost on the same interpretive coding tasks.

• PuppetChat: Fostering Intimate Communication through Bidirectional Actions and Micronarratives

  Emma Jiren Wang, Siying Hu, Zhicong Lu · Feb 23, 2026

  As a primary channel for sustaining modern intimate relationships, instant messaging facilitates frequent connection across distances.

• SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning

  Zelin He, Boran Han, Xiyuan Zhang, Shuai Zhang, Haotian Lin · Feb 23, 2026

  As collecting data for knowledge injection fine-tuning is costly, we further leverage a reinforcement learning-based approach with verifiable rewards (RLVR) to elicit knowledge-rich traces without human supervision, then transfer such an in

• OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents

  Ruicheng Ao, David Simchi-Levi, Xinshang Wang · Feb 23, 2026

  Whether AI agents can perform this task remains untested.

• Personalized Prediction of Perceived Message Effectiveness Using Large Language Model Based Digital Twins

  Jasmin Han, Janardan Devkota, Joseph Waring, Amanda Luken, Felix Naughton · Feb 23, 2026

  Rubric Rating

  Perceived message effectiveness (PME) by potential intervention end-users is important for selecting and optimizing personalized smoking cessation intervention messages for mobile health (mHealth) platform delivery.

Recent Daily Archives