HFEPX Daily Archive: 2026-02-21

Research Utility Snapshot

Papers Published On This Date

• 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

Recent Daily Archives