hallucination mitigation

Mitigating Object Hallucinations via Sentence-Level Early Intervention ICCV 2025 Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models ACL 2025 MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation ICLR 2025 MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration ACL 2025 Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation ACL 2025 MPVStance: Mitigating Hallucinations in Stance Detection with Multi-Perspective Verification ACL 2025 MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs EMNLP 2025 Multi-Frequency Contrastive Decoding: Alleviating Hallucinations for Large Vision-Language Models EMNLP 2025 Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering CVPR 2025 Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection CVPR 2025 Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding CVPR 2025 On Guardrail Models’ Robustness to Mutations and Adversarial Attacks EMNLP 2025 ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models ICCV 2025 On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation ACL 2025 OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models EMNLP 2025 Pandora’s Box or Aladdin’s Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models ACL 2025 Past Meets Present: Creating Historical Analogy with Large Language Models ACL 2025 PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality EMNLP 2025 Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization EMNLP 2025 Re-Aligning Language to Visual Objects with an Agentic Workflow ICLR 2025 Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling NAACL 2025 Reasoning Enhanced Missing Knowledge Retrieval Augmented Generation Framework for Domain Specific Question Answering IJCNLP 2025 Recognizing Limits: Investigating Infeasibility in Large Language Models EMNLP 2025 Refine Knowledge of Large Language Models via Adaptive Contrastive Learning ICLR 2025 RE-FIN: Retrieval-based Enrichment for Financial data COLING 2025