HFEPX Daily Archive: 2026-02-26

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 60 papers for HFEPX Daily Archive: 2026-02-26. Dominant protocol signals include automatic metrics, simulation environments, human evaluation, with frequent benchmark focus on Retrieval, Auditbench and metric focus on accuracy, latency. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.

Papers Published On This Date

• Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning

  Amita Kamath, Jack Hessel, Khyathi Chandu, Jena D. Hwang, Kai-Wei Chang · Feb 26, 2026

  With a set of curated benchmarks, we demonstrate that: (i) VLMs perform poorly on the aforementioned types of reasoning suppressed in the training data by reporting bias; (ii) contrary to popular belief, scaling data size, model size, and t

• LLM Novice Uplift on Dual-Use, In Silico Biology Tasks

  Chen Bo Calvin Zhang, Christina Q. Knight, Nicholas Kruus, Jason Hausenloy, Pedro Medeiros · Feb 26, 2026

  Large language models (LLMs) perform increasingly well on biology benchmarks, but it remains unclear whether they uplift novice users -- i.e., enable humans to perform better than with internet-only resources.

• A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations

  Soumya Dutta, Smruthi Balaji, Sriram Ganapathy · Feb 26, 2026

  Experiments on three benchmark datasets-IEMOCAP, MELD, and MOSI-show that our proposal achieves 70.9%, 69.5%, and 87.9% weighted F1-scores respectively, outperforming several baseline speech-text ERC systems.

• SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables

  Sungho Park, Jueun Kim, Wook-Shin Han · Feb 26, 2026

  Yet existing benchmarks are small, manually curated - and therefore error-prone - and contain shallow questions that seldom demand more than two hops or invoke aggregations, grouping, or other advanced analytical operations expressible in n

• Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems

  Siyuan Liu, Jiahui Xu, Feng Jiang, Kuang Wang, Zefeng Zhao · Feb 26, 2026

  Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems.

• AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

  Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding · Feb 26, 2026

  Multi Agent

  While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual participants.

• Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

  Pengxiang Li, Dilxat Muhtar, Lu Yin, Tianlong Chen, Shiwei Liu · Feb 26, 2026

  Across math reasoning benchmarks, NAP yields stronger performance under parallel decoding than DLMs trained on standard long CoT data, with gains growing as parallelism increases.

• InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models

  Sayed Mohammadreza Tayaranian Hosseini, Amir Ardakani, Warren J. Gross · Feb 26, 2026

  Our evaluation experiments on Llama models shows that InnerQ maintains a few-shot GSM8K performance comparable to non-quantized KV caches and surpasses prior KV cache quantization methods.

• Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models

  Chungpa Lee, Jy-yong Sohn, Kangwook Lee · Feb 26, 2026

  Demonstrations

  Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations.

• MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations

  Sara Rosenthal, Yannis Katsis, Vraj Shah, Lihong He, Lucian Popa · Feb 26, 2026

  We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models.

• A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

  Usman Anwar, Julianna Piskorz, David D. Baek, David Africa, Jim Weatherall · Feb 26, 2026

  Our central insight is that steganography creates an asymmetry in usable information between agents who can and cannot decode the hidden content (present within a steganographic signal), and this otherwise latent asymmetry can be inferred f

• Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs

  Jayadev Billa · Feb 26, 2026

  Multimodal LLMs can process speech and images, but they cannot hear a speaker's voice or see an object's texture.

• Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent

  Boyang Zhang, Yang Zhang · Feb 26, 2026

  In this work, we introduce an LLM agent designed to evaluate and mitigate such risks through a structured, interpretable pipeline.

• CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery

  Mengze Hong, Di Jiang, Chen Jason Zhang, Zichang Guo, Yawen Li · Feb 26, 2026

  In this work, we present CiteLLM, a specialized agentic platform designed to enable trustworthy reference discovery for grounding author-drafted claims and statements.

• Quantity Convergence, Quality Divergence: Disentangling Fluency and Accuracy in L2 Mandarin Prosody

  Yuqi Shi, Hao Yang, Xiyao Lu, Jinsong Zhang · Feb 26, 2026

  While second language (L2) learners may acquire target syntactic word order, mapping this syntax onto appropriate prosodic structures remains a persistent challenge.

• Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment

  Sanjid Hasan, Risalat Labib, A H M Fuad, Bayazid Hasan · Feb 26, 2026

  Ultimately, this work outlines a highly optimized dual pipeline achieving a $\sim$0.019 Real-Time Factor (RTF), establishing a practical, empirically backed benchmark for low-resource, long-form speech processing.

• Toward Automatic Filling of Case Report Forms: A Case Study on Data from an Italian Emergency Department

  Gabriela Anna Kaczmarek, Pietro Ferrazzi, Lorenzo Porta, Vicky Rubini, Bernardo Magnini · Feb 26, 2026

  We provide an analysis of the data, define the CRF-filling task and metric for its evaluation, and report on pilot experiments where we use an open-source state-of-the-art LLM to automatically execute the task.

• MoDora: Tree-Based Semi-Structured Document Analysis System

  Bangrui Xu, Qihang Yao, Zirui Tang, Xuanhe Zhou, Yeye He · Feb 26, 2026

  Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irregular layouts.

• Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention

  Jeongin Bae, Baeseong Park, Gunho Park, Minsub Kim, Joonhyung Lee · Feb 26, 2026

  Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization.

• Frequency-Ordered Tokenization for Better Text Compression

  Maximilian Kalcher · Feb 26, 2026

  We present frequency-ordered tokenization, a simple preprocessing technique that improves lossless text compression by exploiting the power-law frequency distribution of natural language tokens (Zipf's law).

• Where Vision Becomes Text: Locating the OCR Routing Bottleneck in Vision-Language Models

  Jonathan Steinberg, Oren Gal · Feb 26, 2026

  Vision-language models (VLMs) can read text from images, but where does this optical character recognition (OCR) information enter the language processing stream?

• NoRA: Breaking the Linear Ceiling of Low-Rank Adaptation via Manifold Expansion

  Hung-Hsuan Chen · Feb 26, 2026

  On the SlimOrca benchmark, NoRA breaks this linear barrier: NoRA remarkably at rank 64 (PPL 3.89) outperforms LoRA at rank 512 (PPL 3.90), demonstrating superior spectral efficiency.

• OmniGAIA: Towards Native Omni-Modal AI Agents

  Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Shijian Wang, Guanting Dong · Feb 26, 2026

  Tool Use

  Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world.

• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching

  Roy Miles, Aysim Toker, Andreea-Maria Oncescu, Songcen Xu, Jiankang Deng · Feb 26, 2026

  Long Horizon

  This modular pipeline separates exploration (diffusion) from evaluation and solution synthesis, avoiding monolithic unified hybrids while preserving broad search.

• Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference

  Yushi Ye, Feng Hong, Huangjie Zheng, Xu Chen, Zhiyong Chen · Feb 26, 2026

  Diffusion Large Language Models (DLLMs) promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding.

• Effective QA-driven Annotation of Predicate-Argument Relations Across Languages

  Jonathan Davidov, Aviv Slobodkin, Shmuel Tomi Klein, Reut Tsarfaty, Ido Dagan · Feb 26, 2026

  Explicit representations of predicate-argument relations form the basis of interpretable semantic analysis, supporting reasoning, generation, and evaluation.

• Improving Neural Argumentative Stance Classification in Controversial Topics with Emotion-Lexicon Features

  Mohammad Yeghaneh Abkenar, Weixing Wang, Manfred Stede, Davide Picca, Mark A. Finlayson · Feb 26, 2026

  Argumentation mining comprises several subtasks, among which stance classification focuses on identifying the standpoint expressed in an argumentative text toward a specific target topic.

• Moral Preferences of LLMs Under Directed Contextual Influence

  Phil Blandfort, Tushar Karayil, Urja Pawar, Robert Graham, Alex McKenzie · Feb 26, 2026

  Pairwise Preference

  Moral benchmarks for LLMs typically use context-free prompts, implicitly assuming stable preferences.

• TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought

  Jianmin Li, Ying Chang, Su-Kit Tang, Yujia Liu, Yanwen Wang · Feb 26, 2026

  Additionally, TCM-DiffRAG outperformed directly supervised fine-tuned (SFT) LLMs and other benchmark RAG methods.

• TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models

  Reihaneh Iranmanesh, Saeedeh Davoudi, Pasha Abrishamchian, Ophir Frieder, Nazli Goharian · Feb 26, 2026

  This paper presents a comprehensive evaluation framework for assessing the cultural competence of large language models (LLMs) in Persian.

• Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift

  Hyunwoo Kim, Hanau Yi, Jaehee Bae, Yumin Kim · Feb 26, 2026

  Critique Edit

  NLD-P is formalized as a modular control abstraction that separates provenance, constraint logic, task content, and post-generation evaluation, encoded directly in natural language without reliance on external orchestration code.

• Probing for Knowledge Attribution in Large Language Models

  Ivo Brink, Alexander Boer, Dennis Ulmer · Feb 26, 2026

  Probes trained on AttriWiki data reveal a strong attribution signal, achieving up to 0.96 Macro-F1 on Llama-3.1-8B, Mistral-7B, and Qwen-7B, transferring to out-of-domain benchmarks (SQuAD, WebQuestions) with 0.94-0.99 Macro-F1 without retr

• TherapyProbe: Generating Design Knowledge for Relational Safety in Mental Health Chatbots Through Adversarial Simulation

  Joydeep Chandra, Satyam Kumar Navneet, Yong Zhang · Feb 26, 2026

  Expert Verification Multi Agent

  As mental health chatbots proliferate to address the global treatment gap, a critical question emerges: How do we design for relational safety the quality of interaction patterns that unfold across conversations rather than the correctness

• Imagination Helps Visual Reasoning, But Not Yet in Latent Space

  You Li, Chi Chen, Yanghao Li, Fanhu Zeng, Kaiyu Huang · Feb 26, 2026

  Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models.

• Towards Better RL Training Data Utilization via Second-Order Rollout

  Zhe Yang, Yudong Wang, Rang Li, Zhifang Sui · Feb 26, 2026

  Critique Edit

  Reinforcement Learning (RL) has empowered Large Language Models (LLMs) with strong reasoning capabilities, but vanilla RL mainly focuses on generation capability improvement by training with only first-order rollout (generating multiple res

• AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors

  Abhay Sheshadri, Aidan Ewart, Kai Fronsdal, Isha Gupta, Samuel R. Bowman · Feb 26, 2026

  Demonstrations

  We introduce AuditBench, an alignment auditing benchmark.

• Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction

  Nils Schwager, Simon Münker, Alistair Plum, Achim Rettinger · Feb 26, 2026

  This framework enables a rigorous evaluation of current LLM capabilities with respect to the simulation of social media user behavior.

• Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks

  Jakub Šmíd, Pavel Přibáň, Pavel Král · Feb 26, 2026

  The dataset establishes a new benchmark for Czech ABSA, and our proposed translation-alignment approach offers a scalable solution for adapting ABSA resources to other low-resource languages.

• Human Label Variation in Implicit Discourse Relation Recognition

  Frances Yung, Daniil Ignatev, Merel Scholman, Vera Demberg, Massimo Poesio · Feb 26, 2026

  There is growing recognition that many NLP tasks lack a single ground truth, as human judgments reflect diverse perspectives.

• Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QA

  Fengyu Li, Junhao Zhu, Kaishi Song, Lu Chen, Zhongming Yao · Feb 26, 2026

  Long Horizon

  Experiments on two benchmark datasets show that, with the same LLM backbone, Operation-R1 achieves average absolute accuracy gains of 9.55 and 6.08 percentage points over multi-step preparation baselines, with 79\% table compression and a 2

• Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs

  Siyue Su, Jian Yang, Bo Li, Guanglin Niu · Feb 26, 2026

  Experimental results show that KGT consistently outperforms state-of-the-art methods across multiple benchmarks.

• Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue

  Ning Gao, Wei Zhang, Yuqin Dai, Ling Shi, Ziyin Wang · Feb 26, 2026

  The rapid evolution of Large Language Models (LLMs) has accelerated the transition from conversational chatbots to general agents.

• Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategies

  Shinnosuke Nozue, Yuto Nakano, Yotaro Watanabe, Meguru Takasaki, Shoji Moriya · Feb 26, 2026

  Current approaches to developing persuasive dialogue agents often rely on a limited set of predefined persuasive strategies that fail to capture the complexity of real-world interactions.

• Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

  Qianben Chen, Tianrui Qin, King Zhu, Qiexiang Wang, Chengjun Yu · Feb 26, 2026

  Long Horizon

  Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios.

• dLLM: Simple Diffusion Language Modeling

  Zhanhui Zhou, Lingjie Chen, Hanghang Tong, Dawn Song · Feb 26, 2026

  To address this gap, we introduce dLLM, an open-source framework that unifies the core components of diffusion language modeling -- training, inference, and evaluation -- and makes them easy to customize for new designs.

• Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper

  Hoan My Tran, Xin Wang, Wanying Ge, Xuechen Liu, Junichi Yamagishi · Feb 26, 2026

  Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized by speech generative models.

• Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

  Zhengyang Su, Isay Katsman, Yueqi Wang, Ruining He, Lukasz Heldt · Feb 26, 2026

  In addition, evaluation on academic benchmarks demonstrates that STATIC can considerably improve cold-start performance for generative retrieval.

• ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL

  Xingyu Lu, Jinpeng Wang, YiFan Zhang, Shijie Ma, Xiao Hu · Feb 26, 2026

  Experimental results on 11 perception and reasoning benchmarks show that ContextRL significantly improves knowledge discovery efficiency.

• pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training

  Wenzheng Zhang, Bingzheng Liu, Yang Hu, Xiaoying Bai, Wentao Zhang · Feb 26, 2026

  Quantization-Aware Training from scratch has emerged as a promising approach for building efficient large language models (LLMs) with extremely low-bit weights (sub 2-bit), which can offer substantial advantages for edge deployment.

• TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion

  Donghong Cai, Jiarui Feng, Yanbo Wang, Da Zheng, Yixin Chen · Feb 26, 2026

  Extensive experiments on diverse benchmarks demonstrate the effectiveness of TabDLM compared to strong diffusion- and LLM-based baselines.

• Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA

  Wenwei Li, Ming Xu, Tianle Xia, Lingxiang Hu, Yiding Sun · Feb 26, 2026

  We propose a reinforced co-adaptation framework that jointly optimizes retrieval and generation through two components: (1) Graph-aware Retrieval (GraphRAG), which models entity-relation structure over a high-citation knowledge subgraph for

• Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance

  Weida Liang, Yiyou Sun, Shuyuan Nan, Chuang Li, Dawn Song · Feb 26, 2026

  Through a controlled analysis of paired human-written and model-generated solutions, we identify a systematic dissociation between usage and executability: human- and model-derived strategies differ in structured, domain-dependent ways, lea

• Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training

  Tianle Xia, Ming Xu, Lingxiang Hu, Yiding Sun, Wenwei Li · Feb 26, 2026

  Long Horizon

  Agentic RAG addresses this by enabling LLMs to dynamically decide when and what to retrieve, but current RL-based training methods suffer from sparse outcome rewards that discard intermediate signals and low sample efficiency where failed s

• Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation

  Zihang Xu, Haozhi Xie, Ziqi Miao, Wuxuan Gong, Chen Qian · Feb 26, 2026

  Large reasoning models (LRMs) achieve strong performance through extended reasoning traces, but they often exhibit overthinking behavior for low-complexity queries.

• Ruyi2 Technical Report

  Huan Song, Shuyu Tian, Junyi Hao, Minxiu Xu, Hongjun An · Feb 26, 2026

  Large Language Models (LLMs) face significant challenges regarding deployment costs and latency, necessitating adaptive computing strategies.

• RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format

  Zhehao Huang, Yuhang Liu, Baijiong Lin, Yixin Lou, Zhengbao He · Feb 26, 2026

  Across four instruction-following benchmarks and nine reasoning & general capability benchmarks, RAIN-Merging substantially improves instruction adherence while maintaining reasoning quality.

• Dynamic Level Sets

  Michael Stephen Fiske · Feb 26, 2026

  A mathematical concept is identified and analyzed that is implicit in the 2012 paper Turing Incomputable Computation, presented at the Alan Turing Centenary Conference (Turing 100, Manchester).

• Iterative Prompt Refinement for Dyslexia-Friendly Text Summarization Using GPT-4o

  Samay Bhojwani, Swarnima Kain, Lisong Xu · Feb 26, 2026

  These findings establish an empirical baseline for accessibility-driven NLP summarization and motivate further human-centered evaluation with dyslexic readers.

• Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents

  Ryan Liu, Dilip Arumugam, Cedegao E. Zhang, Sean Escola, Xaq Pitkow · Feb 26, 2026

  This position paper argues that potential blueprints for designing such modular language agents can be found in the existing literature on cognitive models and artificial intelligence (AI) algorithms.

• Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing

  An-Ci Peng, Kuan-Tang Huang, Tien-Hong Lo, Hung-Shin Lee, Hsin-Min Wang · Feb 26, 2026

  Taiwanese Hakka is a low-resource, endangered language that poses significant challenges for automatic speech recognition (ASR), including high dialectal variability and the presence of two distinct writing systems (Hanzi and Pinyin).

Recent Daily Archives