HFEPX Daily Archive: 2026-02-22

Research Utility Snapshot

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.

Recent Daily Archives