Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models
cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/salaniz/pycocoevalcap
Terminology
Sources
- GPT-4 Technical Report
- Qwen2.5-VL Technical Report
- VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
- MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models
- Gemini: A Family of Highly Capable Multimodal Models
- How Multimodal Large Language Models Support Access to Visual Information: A Diary Study With Blind and Low Vision People
- Probing Cross-modal Information Hubs in Audio-Visual LLMs
- Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
- AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
- The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
- In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
- Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
- Do Audio-Visual Large Language Models Really See and Hear?
- From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
- Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models
- LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models
- Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation
- Qwen2.5-Omni Technical Report
- Qwen3-Omni Technical Report
- Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering