Large Language Models

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models EMNLP 2025 Understanding the Repeat Curse in Large Language Models from a Feature Perspective ACL 2025 Understanding Verbatim Memorization in LLMs Through Circuit Discovery ACL 2025 Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization NAACL 2025 Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors NAACL 2025 Unifying Large Language Models and Knowledge Graphs for efficient Regulatory Information Retrieval and Answer Generation COLING 2025 Unifying Specialized Visual Encoders for Video Language Models ICML 2025 Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference EMNLP 2025 Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights ACL 2025 UnitCoder: Scalable Code Synthesis from Pre-training Corpora EMNLP 2025 Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs EMNLP 2025 Universal Length Generalization with Turing Programs ICML 2025 UNLEARN Efficient Removal of Knowledge in Large Language Models NAACL 2025 Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation ACL 2025 Unlearning LLM-Based Speech Recognition Models Interspeech 2025 Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context NAACL 2025 Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts NAACL 2025 Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering ACL 2025 Unlocking Post-hoc Dataset Inference with Synthetic Data ICML 2025 Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection ICML 2025 Unlocking the Planning Capabilities of Large Language Models with Maximum Diversity Fine-tuning NAACL 2025 Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems NAACL 2025 Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models ACL 2025 Unnatural Languages Are Not Bugs but Features for LLMs ICML 2025 Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models ACL 2025