hallucination mitigation

Regularized Contrastive Decoding with Hard Negative Samples for LLM Hallucination Mitigation EMNLP 2025 ReLoop: “Seeing Twice and Thinking Backwards” via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding EMNLP 2025 Removal of Hallucination on Hallucination: Debate-Augmented RAG ACL 2025 Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models ACL 2025 RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction EMNLP 2025 RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data AAAI 2025 RRHF-V: Ranking Responses to Mitigate Hallucinations in Multimodal Large Language Models with Human Feedback COLING 2025 SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs EMNLP 2025 SARA: Salience-Aware Reinforced Adaptive Decoding for Large Language Models in Abstractive Summarization ACL 2025 Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension ICCV 2025 Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding CVPR 2025 Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models ICLR 2025 Semantic Contribution-Aware Adaptive Retrieval for Black-Box Models EMNLP 2025 SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine NAACL 2025 Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs EMNLP 2025 SHARP: Steering Hallucination in LVLMs via Representation Engineering EMNLP 2025 SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs ACL 2025 Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation EMNLP 2025 SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models EMNLP 2025 Synthetic Paths to Integral Truth: Mitigating Hallucinations Caused by Confirmation Bias with Synthetic Data COLING 2025 TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems ACL 2025 Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples Interspeech 2025 The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination ACL 2025 Think and Recall: Layer-Level Prompting for Lifelong Model Editing EMNLP 2025 Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking ACL 2025