HFEPX Fortnight Archive: 2026-F04

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 335 papers for HFEPX Fortnight Archive: 2026-F04. Dominant protocol signals include automatic metrics, simulation environments, human evaluation, with frequent benchmark focus on Retrieval, MATH and metric focus on accuracy, cost. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.

Papers Published On This Date

• Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition

  Minxue Tang, Yangyang Yu, Aolin Ding, Maziyar Baran Pouyan, Taha Belkhouja Yujia Bao · Feb 22, 2026

  Recognizing implicit visual and textual patterns is essential in many real-world applications of modern AI.

• PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification

  Isun Chehreh, Ebrahim Ansari · Feb 22, 2026

  Data collection involved 60,000 raw posts from various Persian social media platforms, followed by rigorous preprocessing and hybrid annotation combining ChatGPT-based few-shot prompting with human verification.

• Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations

  Dongming Jiang, Yi Li, Songtao Wei, Jinxin Yang, Ayushi Kishore · Feb 22, 2026

  Long Horizon

  Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows.

• Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering

  Maryam Amirizaniani, Alireza Salemi, Hamed Zamani · Feb 22, 2026

  Pairwise Preference Long Horizon

  Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context.

• Retrieval Augmented Enhanced Dual Co-Attention Framework for Target Aware Multimodal Bengali Hateful Meme Detection

  Raihan Tanvir, Md. Golam Rabiul Alam · Feb 22, 2026

  Hateful content on social media increasingly appears as multimodal memes that combine images and text to convey harmful narratives.

• Next Reply Prediction X Dataset: Linguistic Discrepancies in Naively Generated Content

  Simon Münker, Nils Schwager, Kai Kugler, Michael Heseltine, Achim Rettinger · Feb 22, 2026

  The increasing use of Large Language Models (LLMs) as proxies for human participants in social science research presents a promising, yet methodologically risky, paradigm shift.

• TurkicNLP: An NLP Toolkit for Turkic Languages

  Sherzod Hakimov · Feb 22, 2026

  Natural language processing for the Turkic language family, spoken by over 200 million people across Eurasia, remains fragmented, with most languages lacking unified tooling and resources.

• Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playing

  Maciej Świechowski, Adam Żychowski, Jacek Mańdziuk · Feb 22, 2026

  The main results indicate that three of the evaluated models generally perform well across most experimental settings, with performance degradation observed as the evaluation horizon increases (i.e., with a higher number of game steps).

• Beyond Behavioural Trade-Offs: Mechanistic Tracing of Pain-Pleasure Decisions in an LLM

  Francesca Bianco, Derek Shiller · Feb 22, 2026

  This work supports a more evidence-driven (a) debate on AI sentience and welfare, and (b) governance when setting policy, auditing standards, and safety safeguards.

• Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs

  Wenqiu Tang, Zhen Wan, Takahiro Komamizu, Ichiro Ide · Feb 22, 2026

  Personality control in Role-Playing Agents (RPAs) is commonly achieved via training-free methods that inject persona descriptions and memory through prompts or retrieval-augmented generation, or via supervised fine-tuning (SFT) on persona-s

• VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval

  Diogo Glória-Silva, David Semedo, João Maglhães · Feb 22, 2026

  Long Horizon

  Our evaluation shows that VIGiA outperforms existing state-of-the-art models on all tasks in a conversational plan guidance setting, reaching over 90\% accuracy on plan-aware VQA.

• A Dataset for Named Entity Recognition and Relation Extraction from Art-historical Image Descriptions

  Stefanie Schneider, Miriam Göldl, Julian Stalter, Ricarda Vollmer · Feb 22, 2026

  The dataset is released as UIMA XMI Common Analysis Structure (CAS) files with accompanying images and bibliographic metadata, and can be used to benchmark and fine-tune NER and RE systems, including zero- and few-shot setups with Large Lan

• AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG

  Qijie You, Wenkai Yu, Wentao Zhang · Feb 22, 2026

  Long Horizon

  With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction.

• How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders

  Michael McCoubrey, Angelo Salatino, Francesco Osborne, Enrico Motta · Feb 22, 2026

  In recent years, there has been a growing use of generative AI, and large language models (LLMs) in particular, to support both the assessment and generation of scientific work.

• Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models

  Kainan Liu, Yong Zhang, Ning Cheng, Yun Zhu, Yanmeng Wang · Feb 22, 2026

  Extensive experiments across natural language understanding (NLU) and natural language generation (NLG) tasks demonstrate that Astra consistently outperforms existing PEFT baselines across 16 benchmarks and even surpasses full fine-tuning (

• Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models

  Seong Hah Cho, Junyi Li, Anna Leshinskaya · Feb 22, 2026

  Among the characteristics of value representation in humans is that they distinguish among value of different kinds.

• TriTopic: Tri-Modal Graph-Based Topic Modeling with Iterative Refinement and Archetypes

  Roman Egger · Feb 22, 2026

  In benchmarks across 20 Newsgroups, BBC News, AG News, and Arxiv, TriTopic achieves the highest NMI on every dataset (mean NMI 0.575 vs.

• Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer

  Chenhang Cui, An Zhang, Yuxin Chen, Gelei Deng, Jingnan Zheng · Feb 22, 2026

  Long Horizon

  Across diverse mathematics and perception benchmarks, SNRF consistently enhances LVLM inference performance while preserving perceptual capabilities.

• IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning

  Yinhan He, Yaochen Zhu, Mingjia Shi, Wendy Zheng, Lin Su · Feb 22, 2026

  Extensive empirical evaluations demonstrate that information-aware advantage shaping is a powerful and general direction for token-efficient post-training.

• Uncovering Context Reliance in Unstructured Knowledge Editing

  Zisheng Zhou, Mengqi Zhang, Shiguang Wu, Xiaotian Ye, Chi Zhang · Feb 22, 2026

  Evaluations show that COIN reduces Context Reliance by 45.2% and outperforms strong baselines by 23.6% in editing success rate, highlighting the vital role of mitigating Context Reliance for robust editing.

• Learning to Detect Language Model Training Data via Active Reconstruction

  Junjie Oscar Yin, John X. Morris, Vitaly Shmatikov, Sewon Min, Hannaneh Hajishirzi · Feb 22, 2026

  Detecting LLM training data is generally framed as a membership inference attack (MIA) problem.

• Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks

  Wilson Y. Lee · Feb 22, 2026

  Long Horizon

  Why do language agents fail on tasks they are capable of solving?

• Benchmark Test-Time Scaling of General LLM Agents

  Xiaochuan Li, Ryan Ming, Pranav Setlur, Abhijay Paladugu, Andy Tang · Feb 22, 2026

  LLM agents are increasingly expected to function as general-purpose systems capable of resolving open-ended user requests.

• Whisper: Courtside Edition Enhancing ASR Performance Through LLM-Driven Context Generation

  Yonathan Ron, Shiri Gilboa, Tammuz Dubnov · Feb 21, 2026

  Multi Agent

  We introduce Whisper: Courtside Edition, a novel multi-agent large language model (LLM) pipeline that enhances Whisper transcriptions without retraining.

• Yor-Sarc: A gold-standard dataset for sarcasm detection in a low-resource African language

  Toheeb Aduramomi Jimoh, Tabea De Wille, Nikola S. Nikolov · Feb 21, 2026

  Pairwise Preference

  One annotator pair achieved almost perfect agreement ($κ= 0.8743$; $93.8\%$ raw agreement), exceeding a number of reported benchmarks for English sarcasm research works.

• MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Elastic LLMs

  Dongwei Wang, Jinhee Kim, Seokho Han, Denis Gudovskiy, Yohei Nakata · Feb 21, 2026

  Changing runtime complexity on cloud and edge devices necessitates elastic large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based on available computational resources.

• Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning

  Abhinaba Basu · Feb 21, 2026

  Personal AI agents incur substantial cost via repeated LLM calls.

• DeepInnovator: Triggering the Innovative Capabilities of LLMs

  Tianyu Fan, Fengji Zhang, Yuxiang Zheng, Bei Chen, Xinyao Niu · Feb 21, 2026

  The application of Large Language Models (LLMs) in accelerating scientific discovery has garnered increasing attention, with a key focus on constructing research agents endowed with innovative capability, i.e., the ability to autonomously g

• AAVGen: Precision Engineering of Adeno-associated Viral Capsids for Renal Selective Targeting

  Mohammadreza Ghaffarzadeh-Esfahani, Yousof Gheisari · Feb 21, 2026

  Adeno-associated viruses (AAVs) are promising vectors for gene therapy, but their native serotypes face limitations in tissue tropism, immune evasion, and production efficiency.

• TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning

  Yujiao Yang · Feb 21, 2026

  Extensive experiments across multiple reasoning benchmarks demonstrate that the proposed framework provides multi-level, verifiable explanations, including executable reasoning structures for individual instances, feasible-region representa

• [b]=[d]-[t]+[p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic

  Kwanghee Choi, Eunjung Yeo, Cheol Jun Cho, David Harwath, David R. Mortensen · Feb 21, 2026

  Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored.

• Hyperbolic Busemann Neural Networks

  Ziheng Chen, Bernhard Schölkopf, Nicu Sebe · Feb 21, 2026

  Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth.

• EvalSense: A Framework for Domain-Specific LLM (Meta-)Evaluation

  Adam Dejl, Jonathan Pearson · Feb 21, 2026

  Robust and comprehensive evaluation of large language models (LLMs) is essential for identifying effective LLM system configurations and mitigating risks associated with deploying LLMs in sensitive domains.

• Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models

  Abraham Paul Elenjical, Vivek Hruday Kavuri, Vasudeva Varma · Feb 21, 2026

  Pairwise Preference

  We introduce a psychologically grounded metacognitive framework that operationalizes Ann Brown's regulatory cycle (Planning, Monitoring, and Evaluation) as a structured prompting architecture, and study its integration within a lightweight

• BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models

  Thura Aung, Jann Railey Montalan, Jian Gang Ngui, Peerat Limkonchotiwat · Feb 21, 2026

  We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP competencies: understanding (NLU), reasoning (NLR), and generation (NLG).

• MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs

  Chun Yan Ryan Kan, Tommy Tran, Vedant Yadav, Ava Cai, Kevin Zhu · Feb 21, 2026

  Red Team

  Defending LLMs against adversarial jailbreak attacks remains an open challenge.

• ArabicNumBench: Evaluating Arabic Number Reading in Large Language Models

  Anas Alhumud, Abdulaziz Alhammadi, Muhammad Badruddin Khan · Feb 21, 2026

  We present ArabicNumBench, a comprehensive benchmark for evaluating large language models on Arabic number reading tasks across Eastern Arabic-Indic numerals (0-9 in Arabic script) and Western Arabic numerals (0-9).

• The Convergence of Schema-Guided Dialogue Systems and the Model Context Protocol

  Andreas Schlapbach · Feb 21, 2026

  This paper establishes a fundamental convergence: Schema-Guided Dialogue (SGD) and the Model Context Protocol (MCP) represent two manifestations of a unified paradigm for deterministic, auditable LLM-agent interaction.

• Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem

  Lichang Song, Ting Long, Yi Chang · Feb 21, 2026

  Multi Agent

  To overcome this limitation, we reformulate RAG as a cooperative multi-agent decision-making problem and propose Cooperative Retrieval-Augmented Generation (CoRAG), a framework in which the reranker and the generator act as peer decision-ma

• ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models

  Zefang Liu, Chenyang Zhu, Sangwoo Cho, Shi-Xiong Zhang · Feb 21, 2026

  Experimental results across diverse benchmarks demonstrate that ReHear effectively mitigates error propagation, consistently outperforming both supervised and pseudo-labeling baselines.

• Watermarking LLM Agent Trajectories

  Wenlong Meng, Chen Gong, Terry Yue Zhuo, Fan Zhang, Kecen Li · Feb 21, 2026

  Long Horizon

  LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model generation, and manual filtering.

• Semantic Substrate Theory: An Operator-Theoretic Framework for Geometric Semantic Drift

  Stephen Russell · Feb 21, 2026

  Long Horizon

  Most semantic drift studies report multiple signals e.g., embedding displacement, neighbor changes, distributional divergence, and recursive trajectory instability, without a shared explanatory theory that relates them.

• Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM

  Md Badsha Biswas, Ozlem Uzuner · Feb 21, 2026

  Through extensive evaluation on four benchmark datasets with five LLMs, we show that knowledge aggregation not only improves claim verification but also reveals differences in source-specific reasoning.

• From Trial by Fire To Sleep Like a Baby: A Lexicon of Anxiety Associations for 20k English Multiword Expressions

  Saif M. Mohammad · Feb 21, 2026

  Anxiety is the unease about a possible future negative outcome.

• Spilled Energy in Large Language Models

  Adrian Robert Minut, Hazem Dewidar, Iacopo Masi · Feb 21, 2026

  Evaluated on nine benchmarks across state-of-the-art LLMs (including LLaMA, Mistral, and Gemma) and on synthetic algebraic operations (Qwen3), our approach demonstrates robust, competitive hallucination detection and cross-task generalizati

• PolyFrame at MWE-2026 AdMIRe 2: When Words Are Not Enough: Multimodal Idiom Disambiguation

  Nina Hosseini-Kivanani · Feb 20, 2026

  Multimodal models struggle with idiomatic expressions due to their non-compositional meanings, a challenge amplified in multilingual settings.

• DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning

  Fangyuan Xu, Sihao Chen, Zinan Lin, Taiwei Shi, Sydney Graham · Feb 20, 2026

  Differentially private (DP) synthetic data generation plays a pivotal role in developing large language models (LLMs) on private data, where data owners cannot provide eyes-on access to individual examples.

• Diagnosing LLM Reranker Behavior Under Fixed Evidence Pools

  Baris Arat, Emre Sefer · Feb 20, 2026

  Standard reranking evaluations study how a reranker orders candidates returned by an upstream retriever.

• Luna-2: Scalable Single-Token Evaluation with Small Language Models

  Vatsal Goel, Rishon Dsouza, Nikhil Ega, Amey Ramesh Rambatla, Rob Friel · Feb 20, 2026

  Real-time guardrails require evaluation that is accurate, cheap, and fast - yet today's default, LLM-as-a-judge (LLMAJ), is slow, expensive, and operationally non-deterministic due to multi-token generation.

• Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications

  Zhiqin Qian, Ryan Diaz, Sangwon Seo, Vaibhav Unhelkar · Feb 20, 2026

  Pairwise Preference Long Horizon

  When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed.

• VIRAASAT: Traversing Novel Paths for Indian Cultural Reasoning

  Harshul Raj Surana, Arijit Maji, Aryan Vats, Akash Ghosh, Sriparna Saha · Feb 20, 2026

  Existing Cultural benchmarks are (i) Manually crafted, (ii) contain single-hop questions testing factual recall, and (iii) prohibitively costly to scale, leaving this deficiency largely unmeasured.

• RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering

  Deniz Qian, Hung-Ting Chen, Eunsol Choi · Feb 20, 2026

  Our method outperforms baselines, including agentic search approaches, achieving at least 10% relative and 3% absolute gain in complete recall percentage on a multi-answer retrieval dataset (QAMPARI).

• SPQ: An Ensemble Technique for Large Language Model Compression

  Jiamin Yao, Eren Gultepe · Feb 20, 2026

  Applied to LLaMA-2-7B, SPQ achieves up to 75% memory reduction while maintaining or improving perplexity (e.g., WikiText-2 5.47 to 4.91) and preserving accuracy on downstream benchmarks such as C4, TruthfulQA, and GSM8K.

• Subgroups of $U(d)$ Induce Natural RNN and Transformer Architectures

  Joshua Nunley · Feb 20, 2026

  This paper presents a direct framework for sequence models with hidden states on closed subgroups of U(d).

• Validating Political Position Predictions of Arguments

  Jordan Robinson, Angus R. Williams, Katie Atkinson, Anthony G. Cohn · Feb 20, 2026

  Pairwise Preference

  Real-world knowledge representation often requires capturing subjective, continuous attributes -- such as political positions -- that conflict with pairwise validation, the widely accepted gold standard for human evaluation.

• Vichara: Appellate Judgment Prediction and Explanation for the Indian Judicial System

  Pavithra PM Nair, Preethu Rose Anish · Feb 20, 2026

  Vichara surpasses existing judgment prediction benchmarks on both datasets, with GPT-4o mini achieving the highest performance (F1: 81.5 on PredEx, 80.3 on ILDC_expert), followed by Llama-3.1-8B.

• On the "Induction Bias" in Sequence Models

  M. Reza Ebrahimi, Michaël Defferrard, Sunny Panchal, Roland Memisevic · Feb 20, 2026

  Together, these results demonstrate that state tracking remains a fundamental challenge for transformers, even when training and evaluation distributions match.

• Predicting Contextual Informativeness for Vocabulary Learning using Deep Learning

  Tao Wu, Adam Kapelner · Feb 20, 2026

  In summary, we demonstrate that a modern embedding model on neural network architecture, when guided by human supervision, results in a low-cost large supply of near-perfect contexts for teaching vocabulary for a variety of target words.

• PsihoRo: Depression and Anxiety Romanian Text Corpus

  Alexandra Ciobotaru, Ana-Maria Bucur, Liviu P. Dinu · Feb 20, 2026

  Psychological corpora in NLP are collections of texts used to analyze human psychology, emotions, and mental health.

• VeriSoftBench: Repository-Scale Formal Verification Benchmarks for Lean

  Yutong Xin, Qiaochu Chen, Greg Durrett, Işil Dillig · Feb 20, 2026

  However, most benchmarks for LLM-based proof automation are drawn from mathematics in the Mathlib ecosystem, whereas proofs in software verification are developed inside definition-rich codebases with substantial project-specific libraries.

Recent Daily Archives