Papers
AICD Bench: A Challenging Benchmark for AI-Generated Code Detection
Daniil Orel, Dilshod Azizov, Indraneil Paul et al.
Sycophancy Hides Linearly in the Attention Heads
Rifo Ahmad Genadi, Munachiso Samuel Nwadike, Nurdaulet Mukhituly et al.
Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs
Chi Zhang, Wenxuan Ding, Jiale Liu et al.
Query Decomposition for RAG: Balancing Exploration-Exploitation
Roxana Petcu, Kenton Murray, Daniel Khashabi et al.
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
Aashiq Muhamed, Leonardo F. R. Ribeiro, Markus Dreyer et al.
Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact
Hyunji Lee, Seunghyun Yoon, Yunjae Won et al.
The Relevance of Value Systems for Offensive Language Detection
Michael Wiegand, Elisabeth Eder, Josef Ruppenhofer
Offline Preference Optimization via Maximum Marginal Likelihood Estimation
Saeed Najafi, Alona Fyshe
Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization
Mizanur Rahman, Mohammed Saidul Islam, Md Tahmid Rahman Laskar et al.
Emotionally Charged, Logically Blurred: AI-driven Emotional Framing Impairs Human Fallacy Detection
Yanran Chen, Lynn Greschner, Roman Klinger et al.
ConLID: Supervised Contrastive Learning for Low-Resource Language Identification
Negar Foroutan, Jakhongir Saydaliev, Grace Kim et al.
Principled Self-Correction in Discrete Diffusion: A UCB-Guided Framework for Text Generation
Masaki Asada, Makoto Miwa
MAQuA: Multi-outcome Adaptive Question-Asking for Mental Health using Item Response Theory
Vasudha Varadarajan, Hui Xu, Rebecca Astrid Böhme et al.
Continual Neural Topic Model
Charu Karakkaparambil James, Waleed Mustafa, Marcio Monteiro et al.
How Do LLMs Generate Contrastive Sentiments? A Mechanistic Perspective
Van Bach Nguyen, Jörg Schlötterer, Christin Seifert
Beyond Blind Following: Evaluating Robustness of LLM Agents under Imperfect Guidance
Yao Fu, Ran Qiu, Xinhe Wang et al.
CacheNotes: Task-Aware Key-Value Cache Compression for Reasoning-Intensive Knowledge Tasks
Giulio Corallo, Orion Weller, Fabio Petroni et al.
Elections go bananas: A First Large-scale Multilingual Study of Pluralia Tantum using LLMs
Elena Spaziani, Kamyar Zeinalipour, Pierluigi Cassotti et al.
Explaining Generalization of AI-Generated Text Detectors Through Linguistic Analysis
Yuxi Xia, Kinga Stańczak, Benjamin Roth
CoReTab: Improving Multimodal Table Understanding with Code-driven Reasoning
Van-Quang Nguyen, Takayuki Okatani
The Pluralistic Moral Gap: Understanding Moral Judgment and Value Differences between Humans and Large Language Models
Giuseppe Russo, Debora Nozza, Paul Röttger et al.
Unintended Memorization of Sensitive Information in Fine-Tuned Language Models
Marton Szep, Jorge Marin Ruiz, Georgios Kaissis et al.
SciRAG: Adaptive, Citation-Aware, and Outline-Guided Retrieval and Synthesis for Scientific Literature
Hang Ding, Yilun Zhao, Tiansheng Hu et al.
KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking
Vítor Lourenço, Aline Paes, Tillman Weyde et al.
Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks
Sergey Pankratov, Dan Alistarh