hallucinations
Occurrences in AI models where the output includes convincingly crafted but factually incorrect or nonsensical information.
- AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models
- Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection
- Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
- Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
- CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
- Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
- Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
- Discovering Compositional Hallucinations in LVLMs
- Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
- ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
- From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
- Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
- HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving
- Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning
- Incentivizing Truthful Language Models via Peer Elicitation Games
- Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
- LLM-PySC2: Starcraft II learning environment for Large Language Models
- Learning to Steer: Input-dependent Steering for Multimodal LLMs
- One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
- Prohibiting Generative AI in any Form of Weapon Control
- Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
- The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
- What’s in Common? Multimodal Models Hallucinate When Reasoning Across Scenes
- Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations
- Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
- Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs