Large Language Models

Towards a Unified Paradigm of Concept Editing in Large Language Models EMNLP 2025 Towards Automated Error Discovery: A Study in Conversational AI EMNLP 2025 Towards Better Evaluation for Generated Patent Claims ACL 2025 Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models NAACL 2025 Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting COLING 2025 Towards Comprehensive Evaluation of Open-Source Language Models: A Multi-Dimensional, User-Driven Approach ACL 2025 Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models NAACL 2025 Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States ACL 2025 Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs NAACL 2025 Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning ICML 2025 Towards Enforcing Company Policy Adherence in Agentic Workflows EMNLP 2025 Towards Enhanced Immersion and Agency for LLM-based Interactive Drama ACL 2025 Towards Evaluation of Language Models with Skill Dimensions: A Case Study on Narrative Question Answering EMNLP 2025 Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction EMNLP 2025 Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative Framework ACL 2025 Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models EMNLP 2025 Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception ACL 2025 Towards Harmonized Uncertainty Estimation for Large Language Models ACL 2025 Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey EMNLP 2025 Towards Inclusive Arabic LLMs: A Culturally Aligned Benchmark in Arabic Large Language Model Evaluation COLING 2025 Towards Infinite-Long Prefix in Transformer EMNLP 2025 Towards Knowledge-Guided Biomedical Lay Summarization using Large Language Models NAACL 2025 Towards Lifelong Model Editing via Simulating Ideal Editor ICML 2025 Towards LLM-powered Attentive Listener: A Pragmatic Approach through Quantity Self-Repair ACL 2025 Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond ICML 2025