Jack Cook, Hyemin S. Lee, Kathryn Le, Junxian Guo, Giovanni Traverso, Anantha P. Chandrakasan, Song Han: Adaptive Block-Scaled Data Types https://arxiv.org/abs/2603.28765 https://arxiv.org/pdf/2603.28765 https://arxiv.org/html/2603.28765

Shuang Zhou, Kai Yu, Zaifu Zhan, Huixue Zhou, Min Zeng, Feng Xie, Zhiyi Sha, Rui Zhang: EpiScreen: Early Epilepsy Detection from Electronic Health Records with Large Language Models https://arxiv.org/abs/2603.28698 https://arxiv.org/pdf/2603.28698 https://arxiv.org/html/2603.28698

Pavel \v{S}indel\'a\v{r}, D\'avid Slivka, Christopher Bouma, Filip Pr\'a\v{s}il, Ond\v{r}ej Bojar: Training data generation for context-dependent rubric-based short answer grading https://arxiv.org/abs/2603.28537 https://arxiv.org/pdf/2603.28537 https://arxiv.org/html/2603.28537

Younes Javanmard, Tanmoy Pandit, Masoud Mardani: Compressing Transformer Language Models via Matrix Product Operator Decomposition: A Case Study on PicoGPT https://arxiv.org/abs/2603.28534 https://arxiv.org/pdf/2603.28534 https://arxiv.org/html/2603.28534

Shuwen Xu, Yao Xu, Jiaxiang Liu, Chenhao Yuan, Wenshuo Peng, Jun Zhao, Kang Liu: GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum https://arxiv.org/abs/2603.28533 https://arxiv.org/pdf/2603.28533 https://arxiv.org/html/2603.28533

L\'eane Jourdan, Julien Aubert-B\'educhaud, Yannis Chupin, Marah Baccari, Florian Boudin: EarlySciRev: A Dataset of Early-Stage Scientific Revisions Extracted from LaTeX Writing Traces https://arxiv.org/abs/2603.28515 https://arxiv.org/pdf/2603.28515 https://arxiv.org/html/2603.28515

Feng Nie, Zhixiu Ye, Sifa Xie, Shuang Wu, Xin Yuan, Liang Yao, Jiazhen Peng, Xu Cheng: TIEG-Youpu Solution for NeurIPS 2022 WikiKG90Mv2-LSC https://arxiv.org/abs/2603.28512 https://arxiv.org/pdf/2603.28512 https://arxiv.org/html/2603.28512

Chowdhury, Beg, Khan, Raiyan, Hasan, Mahmud: Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification https://arxiv.org/abs/2603.28488 https://arxiv.org/pdf/2603.28488 https://arxiv.org/html/2603.28488

Kosei Fushimi, Kazunobu Serizawa, Junya Ikemoto, Kazumune Hashimoto: Structural-Ambiguity-Aware Translation from Natural Language to Signal Temporal Logic https://arxiv.org/abs/2603.28426 https://arxiv.org/pdf/2603.28426 https://arxiv.org/html/2603.28426

Edoardo Signoroni, Pavel Rychl\'y: LombardoGraphia: Automatic Classification of Lombard Orthography Variants https://arxiv.org/abs/2603.28418 https://arxiv.org/pdf/2603.28418 https://arxiv.org/html/2603.28418

Zhu, Jia, Lan, Ren, Gu, Jiang, Wang, Xu, Luo: Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design https://arxiv.org/abs/2603.28376 https://arxiv.org/pdf/2603.28376 https://arxiv.org/html/2603.28376

Soufiane Jhilal, Eleonora Pasqua, Caterina Marchesi, Riccardo Corradi, Martina Galletti: Tailoring AI-Driven Reading Scaffolds to the Distinct Needs of Neurodiverse Learners https://arxiv.org/abs/2603.28370 https://arxiv.org/pdf/2603.28370 https://arxiv.org/html/2603.28370

Urja Khurana, Michiel van der Meer, Enrico Liscio, Antske Fokkens, Pradeep K. Murukannaiah: Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP https://arxiv.org/abs/2603.28351 https://arxiv.org/pdf/2603.28351 https://arxiv.org/html/2603.28351

Du, Ge, Hu, Yang, Cai, Huang, Yuan, Cheng, Xie, Chen, Li, Xie, Dong, Wu, Huang, Yang, Wang, Zhou, Li, Guo, Chen: Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization https://arxiv.org/abs/2603.28342 https://arxiv.org/pdf/2603.28342 https://arxiv.org/html/2603.28342

Lujun Li, Lama Sleem, Yangjie Xu, Yewei Song, Aolin Jia, Jerome Francois, Radu State: The Necessity of Setting Temperature in LLM-as-a-Judge https://arxiv.org/abs/2603.28304 https://arxiv.org/pdf/2603.28304 https://arxiv.org/html/2603.28304

Eneko Valero, Maria Ribalta i Albado, Oscar Sainz, Naiara Perez, German Rigau: Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights https://arxiv.org/abs/2603.28263 https://arxiv.org/pdf/2603.28263 https://arxiv.org/html/2603.28263

Pannitto, Kahane, Dobrovoljc, Battaglia, Guillaume, Mauri, Zucchini: Coconstructions in spoken data: UD annotation guidelines and first results https://arxiv.org/abs/2603.28261 https://arxiv.org/pdf/2603.28261 https://arxiv.org/html/2603.28261

Jon-Paul Cacioli: Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries https://arxiv.org/abs/2603.28258 https://arxiv.org/pdf/2603.28258 https://arxiv.org/html/2603.28258

Verena Platzgummer, John McCrae, Sina Ahmadi: \textit{Versteasch du mi?} Computational and Socio-Linguistic Perspectives on GenAI, LLMs, and Non-Standard Language https://arxiv.org/abs/2603.28213 https://arxiv.org/pdf/2603.28213 https://arxiv.org/html/2603.28213

Yijin Wang, Fandi Sun: Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis https://arxiv.org/abs/2603.28205 https://arxiv.org/pdf/2603.28205 https://arxiv.org/html/2603.28205

Li, Li, Feng, Fu, Dong, Yang, Chen, Feng, Cao, Guo, Du: DongYuan: An LLM-Based Framework for Integrative Chinese and Western Medicine Spleen-Stomach Disorders Diagnosis https://arxiv.org/abs/2603.28191 https://arxiv.org/pdf/2603.28191 https://arxiv.org/html/2603.28191

Shadman Sakib, Oishy Fatema Akhand, Tasnia Tasneem, Shohel Ahmed: From Reviews to Requirements: Can LLMs Generate Human-Like User Stories? https://arxiv.org/abs/2603.28163 https://arxiv.org/pdf/2603.28163 https://arxiv.org/html/2603.28163

Anudeex Shetty, Qiongkai Xu, Olga Ohrimenko, Jey Han Lau: Who Wrote the Book? Detecting and Attributing LLM Ghostwriters https://arxiv.org/abs/2603.28054 https://arxiv.org/pdf/2603.28054 https://arxiv.org/html/2603.28054

Sercan Karaka\c{s}: Transfer Learning for an Endangered Slavic Variety: Dependency Parsing in Pomak Across Contact-Shaped Dialects https://arxiv.org/abs/2603.28033 https://arxiv.org/pdf/2603.28033 https://arxiv.org/html/2603.28033

Xinran Zhang: Rethinking Atomic Decomposition for LLM Judges: A Prompt-Controlled Study of Reference-Grounded QA Evaluation https://arxiv.org/abs/2603.28005 https://arxiv.org/pdf/2603.28005 https://arxiv.org/html/2603.28005

Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar: On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR https://arxiv.org/abs/2603.27981 https://arxiv.org/pdf/2603.27981 https://arxiv.org/html/2603.27981

Zhuoshang Wang, Yubing Ren, Guoyu Zhao, Xiaowei Zhu, Hao Li, Yanan Cao: EnsemJudge: Enhancing Reliability in Chinese LLM-Generated Text Detection through Diverse Model Ensembles https://arxiv.org/abs/2603.27949 https://arxiv.org/pdf/2603.27949 https://arxiv.org/html/2603.27949

Shuhei Kondo, Katsuhito Sudoh, Yuji Matsumoto: Top-down string-to-dependency Neural Machine Translation https://arxiv.org/abs/2603.27938 https://arxiv.org/pdf/2603.27938 https://arxiv.org/html/2603.27938

Matteo Guida, Yulia Otmakhova, Eduard Hovy, Lea Frermann: Article and Comment Frames Shape the Quality of Online Comments https://arxiv.org/abs/2603.27889 https://arxiv.org/pdf/2603.27889 https://arxiv.org/html/2603.27889

Benno Weck, Pablo Puentes, Andrea Poltronieri, Satyajeet Prabhu, Dmitry Bogdanov: HumMusQA: A Human-written Music Understanding QA Benchmark Dataset https://arxiv.org/abs/2603.27877 https://arxiv.org/pdf/2603.27877 https://arxiv.org/html/2603.27877

Rauan Akylzhanov: KazByte: Adapting Qwen models to Kazakh via Byte-level Adapter https://arxiv.org/abs/2603.27859 https://arxiv.org/pdf/2603.27859 https://arxiv.org/html/2603.27859

Dario Paape: What can LLMs tell us about the mechanisms behind polarity illusions in humans? Experiments across model scales and training steps https://arxiv.org/abs/2603.27855 https://arxiv.org/pdf/2603.27855 https://arxiv.org/html/2603.27855

Natapong Nitarach: Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3 https://arxiv.org/abs/2603.27844 https://arxiv.org/pdf/2603.27844 https://arxiv.org/html/2603.27844

Hadas Kotek, Margit Bowler, Patrick Sonnenberg, Yu'an Yang: ProText: A benchmark dataset for measuring (mis)gendering in long-form texts https://arxiv.org/abs/2603.27838 https://arxiv.org/pdf/2603.27838 https://arxiv.org/html/2603.27838

Zhiwen You, Xi Chen, Aniket Vashishtha, Simo Du, Gabriel Erion-Barner, Hongyuan Mei, Hao Peng, Yue Guo: Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning https://arxiv.org/abs/2603.27820 https://arxiv.org/pdf/2603.27820 https://arxiv.org/html/2603.27820

Andrei Popescu-Belis: Conversational Agents and the Understanding of Human Language: Reflections on AI, LLMs, and Cognitive Science https://arxiv.org/abs/2603.27809 https://arxiv.org/pdf/2603.27809 https://arxiv.org/html/2603.27809

Conrad Borchers, Luiz Rodrigues, Newarney Torrez\~ao da Costa, Cleon Xavier, Rafael Ferreira Mello: Understanding Teacher Revisions of Large Language Model-Generated Feedback https://arxiv.org/abs/2603.27806 https://arxiv.org/pdf/2603.27806 https://arxiv.org/html/2603.27806

Draetta, Oliverio, Ram\'on-Ferrer, Balestrucci, Corallo, Badenes-Olmedo, Mazzei, Stranisci, Damiano: TailNLG: A Multilingual Benchmark Addressing Verbalization of Long-Tail Entities https://arxiv.org/abs/2603.27768 https://arxiv.org/pdf/2603.27768 https://arxiv.org/html/2603.27768

Boxi Yu, Yuzhong Zhang, Liting Lin, Lionel Briand, Emir Mu\~noz: Retromorphic Testing with Hierarchical Verification for Hallucination Detection in RAG https://arxiv.org/abs/2603.27752 https://arxiv.org/pdf/2603.27752 https://arxiv.org/html/2603.27752

Fengxiang Li, et al.: KAT-Coder-V2 Technical Report https://arxiv.org/abs/2603.27703 https://arxiv.org/pdf/2603.27703 https://arxiv.org/html/2603.27703

Yuxuan Gu, Lunjun Liu, Xiaocheng Feng, Kun Zhu, Weihong Zhong, Lei Huang, Bing Qin: Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation? https://arxiv.org/abs/2603.27694 https://arxiv.org/pdf/2603.27694 https://arxiv.org/html/2603.27694

Bayan Abdullah Aldahlawi, A. B. M. Ashikur Rahman, Irfan Ahmad: Investigating the Influence of Language on Sycophantic Behavior of Multilingual LLMs https://arxiv.org/abs/2603.27664 https://arxiv.org/pdf/2603.27664 https://arxiv.org/html/2603.27664

Adi Cohen, Yuval Pinter: The Degree of Language Diacriticity and Its Effect on Tasks https://arxiv.org/abs/2603.27653 https://arxiv.org/pdf/2603.27653 https://arxiv.org/html/2603.27653

Tewodros Kederalah Idris, Roald Eiselen, Prasenjit Mitra: Budget-Xfer: Budget-Constrained Source Language Selection for Cross-Lingual Transfer to African Languages https://arxiv.org/abs/2603.27651 https://arxiv.org/pdf/2603.27651 https://arxiv.org/html/2603.27651

Shi Qiu, et al.: PRBench: End-to-end Paper Reproduction in Physics Research https://arxiv.org/abs/2603.27646 https://arxiv.org/pdf/2603.27646 https://arxiv.org/html/2603.27646

Rodney Jehu-Appiah: Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents https://arxiv.org/abs/2603.27626 https://arxiv.org/pdf/2603.27626 https://arxiv.org/html/2603.27626

Yuxi Wang, Jungyeul Park: A gentle tutorial and a structured reformulation of Bock's algorithm for minimum directed spanning trees https://arxiv.org/abs/2603.27530 https://arxiv.org/pdf/2603.27530 https://arxiv.org/html/2603.27530

Duanyi Yao, Changyue Li, Zhicong Huang, Cheng Hong, Songze Li: Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models https://arxiv.org/abs/2603.27522 https://arxiv.org/pdf/2603.27522 https://arxiv.org/html/2603.27522

Utsav Maskey, Mark Dras, Usman Naseem: Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs https://arxiv.org/abs/2603.27518 https://arxiv.org/pdf/2603.27518 https://arxiv.org/html/2603.27518

Feng, Su, Zhang, Wang, Zhang, Wang, Fang, Zhang, Li, Cai, Ye, Chen, Yong, Zhou, Qian, Xie, Hooi, Liu, Zhou: AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents https://arxiv.org/abs/2603.27490 https://arxiv.org/pdf/2603.27490 https://arxiv.org/html/2603.27490