language model

Textual Unlearning Gives a False Sense of Unlearning ICML 2025 The 2025 ReproNLP Shared Task on Reproducibility of Evaluations in NLP: Overview and Results ACL 2025 The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation ICCV 2025 “The dentist is an involved parent, the bartender is not”: Revealing Implicit Biases in QA with Implicit BBQ AACL 2025 The Foundations of Tokenization: Statistical and Computational Concerns ICLR 2025 The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces NAACL 2025 The Good, the Bad and the Constructive: Automatically Measuring Peer Review’s Utility for Authors EMNLP 2025 The Hallucination Tax of Reinforcement Finetuning EMNLP 2025 The KoLMogorov Test: Compression by Code Generation ICLR 2025 The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion CVPR 2025 The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages IJCNLP 2025 The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units NAACL 2025 The Missing Cause: An Analysis of Causal Attributions in Reporting on Palestine COLING 2025 The Nakba Lexicon: Building a Comprehensive Dataset from Palestinian Literature COLING 2025 The Pursuit of Empathy: Evaluating Small Language Models for PTSD Dialogue Support EMNLP 2025 The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking EMNLP 2025 The Scene Language: Representing Scenes with Programs, Words, and Embeddings CVPR 2025 Thesis Proposal: Efficient Methods for Natural Language Generation/Understanding Systems IJCNLP 2025 The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology EMNLP 2025 Think and Recall: Layer-Level Prompting for Lifelong Model Editing EMNLP 2025 ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models EMNLP 2025 Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series EMNLP 2025 Time to Revisit Exact Match EMNLP 2025 TinyTim: a family of language models for divergent generation NeurIPS 2025 TitleTrap: Probing Presentation Bias in LLM-Based Scientific Reviewing AACL 2025