Large Language Models

Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis ACL 2025 Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains ACL 2025 Decoding Semantic Representations in the Brain Under Language Stimuli with Large Language Models COLING 2025 Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models EMNLP 2025 DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations EMNLP 2025 Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection WACV 2025 Decoupling Metacognition from Cognition: A Framework for Quantifying Metacognitive Ability in LLMs AAAI 2025 Deduce and Select Evidences with Language Models for Training-Free Video Goal Inference WACV 2025 Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models EMNLP 2025 DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning EMNLP 2025 DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process ACL 2025 DeepRTL2: A Versatile Model for RTL-Related Tasks ACL 2025 DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts ICML 2025 Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision ICML 2025 Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks ACL 2025 DeFine: Decision-Making with Analogical Reasoning over Factor Profiles ACL 2025 Definition Generation for Word Meaning Modeling: Monolingual, Multilingual, and Cross-Lingual Perspectives EMNLP 2025 Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model ACL 2025 Deliberation in Latent Space via Differentiable Cache Augmentation ICML 2025 Deloitte (Drocks) at the Financial Misinformation Detection Challenge Task: Enhancing Misinformation Detection through Instruction-Tuned Models COLING 2025 DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability EMNLP 2025 Delta Decompression for MoE-based LLMs Compression ICML 2025 DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic EMNLP 2025 De-mark: Watermark Removal in Large Language Models ICML 2025 Dementia Through Different Eyes: Explainable Modeling of Human and LLM Perceptions for Early Awareness EMNLP 2025