hallucinations

Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation ICML 2025 Between Reality and AI Hallucinations: Reimagining the Sacred Soundscape of Ming Rituals NeurIPS 2025 DAMA: Data- and Model-aware Alignment of Multi-modal LLMs ICML 2025 Eliciting Language Model Behaviors with Investigator Agents ICML 2025 FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees ICML 2025 Hierarchical Graph Tokenization for Molecule-Language Alignment ICML 2025 LOGO — Long cOntext aliGnment via efficient preference Optimization ICML 2025 Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models ICML 2025 Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance ICML 2025 Position: Retrieval-augmented systems can be dangerous medical communicators ICML 2025 Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods ICML 2025 RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning ICML 2025 RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing ICML 2025 Robust Multimodal Large Language Models Against Modality Conflict ICML 2025 Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification ICML 2025 SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding ICML 2025 Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models ICLR 2025 Spatial Reasoning with Denoising Models ICML 2025 Steer LLM Latents for Hallucination Detection ICML 2025 The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering ICML 2025 Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage ICML 2025 TruthFlow: Truthful LLM Generation via Representation Flow Correction ICML 2025 What Limits Bidirectional Model’s Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning ICML 2025 MoE-RBench: Towards Building Reliable Language Models with Sparse Mixture-of-Experts ICML 2024 A Closer Look at the Limitations of Instruction Tuning ICML 2024