Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
Despite their impressive capabilities, multimodal large language models (MLLMs) are prone to hallucinations, i.e., the generated content that is nonsensical or unfaithful to input sources. Unlike in LLMs, hallucinations in MLLMs often stem from the sensitivity of text decoder to visual tokens, leading to a phenomenon akin to "amnesia" about visual information. To address this issue, we propose MemVR, a novel decoding paradigm inspired by common cognition: when the memory of an image seen the moment before is forgotten, people will look at it again for factual answers. Following this principle, we treat visual tokens as supplementary evidence, re-injecting them into the MLLM through Feed Forward Network (FFN) as "key-value memory" at the middle trigger layer. This "look-twice" mechanism occurs when the model exhibits high uncertainty during inference, effectively enhancing factual alignment. Comprehensive experimental evaluations demonstrate that MemVR significantly mitigates hallucination across various MLLMs and excels in general benchmarks without incurring additional time overhead. The implementation is available from https://github.com/1zhou-Wang/MemVR
Code (1)
Tasks
DecoderHallucinationSimilar Papers 제목 키워드 기반
Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation
An embodied task such as embodied question answering (EmbodiedQA), requires an agent to explore the environment and collect clues to answer a given question that related with specific objects in the scene. The solution o…
Common Sense ReasoningEmbodied Question AnsweringQuestion AnsweringVisual Question Answering (VQA)Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models
Where should the question go in a vision-language model (VLM) prompt: before the image or after it? Intuition says before: knowing what is asked should tell the model where to look. Yet across visual question answering b…
Visual Question AnsweringLook Twice: Training-Free Evidence Highlighting for Knowledge-based Visual Question Answering
Knowledge-based Visual Question Answering (KB-VQA) requires Multimodal Large Language Models (MLLMs) to identify and combine fine-grained visual cues with retrieved textual evidence. However, retrieval often introduces n…
ReadTwice: Reading Very Large Documents with Memories
Knowledge-intensive tasks such as question answering often require assimilating information from different sections of large inputs such as books or article collections. We propose ReadTwice, a simple and effective techn…
Question AnsweringThink Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection
Self-detection for Large Language Models (LLMs) seeks to evaluate the trustworthiness of the LLM's output by leveraging its own capabilities, thereby alleviating the issue of output hallucination. However, existing self-…
HallucinationLanguage ModellingLarge Language Model