Large Language Models

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens EMNLP 2025 from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors ACL 2025 From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models ICML 2025 From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing EMNLP 2025 From Causal Parrots to Causal Prophets? Towards Sound Causal Reasoning with Large Language Models NAACL 2025 From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning ICML 2025 From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline ICML 2025 From Curiosity to Clarity : Exploring the Impact of Consecutive Why-Questions NAACL 2025 From Data to Knowledge: Evaluating How Efficiently Language Models Learn Facts ACL 2025 From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium ICML 2025 From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning ICCV 2025 From English to Second Language Mastery: Enhancing LLMs with Cross-Lingual Continued Instruction Tuning ACL 2025 From Evidence Mining to Meta-Prediction: a Gradient of Methodologies for Task-Specific Challenges in Psychological Assessment NAACL 2025 From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notes EMNLP 2025 From General Reward to Targeted Reward: Improving Open-ended Long-context Generation Models EMNLP 2025 From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse EMNLP 2025 From Imitation to Introspection: Probing Self-Consciousness in Language Models ACL 2025 From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors EMNLP 2025 From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models NAACL 2025 From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set ICML 2025 From Language to Cognition: How LLMs Outgrow the Human Language Network EMNLP 2025 From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection ICML 2025 From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding EMNLP 2025 From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications ICML 2025 From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs ACL 2025