Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -
Despite recent advances in Large Vision Language Models (LVLMs), these models still suffer from generating hallucinatory responses that do not align with the visual input provided. To mitigate such hallucinations, we introduce Efficient Contrastive Decoding (ECD), a simple method that leverages probabilistic hallucination detection to shift the output distribution towards contextually accurate answers at inference time. By contrasting token probabilities and hallucination scores, ECD subtracts hallucinated concepts from the original distribution, effectively suppressing hallucinations. Notably, our proposed method can be applied to any open-source LVLM and does not require additional LVLM training. We evaluate our method on several benchmark datasets and across different LVLMs. Our experiments show that ECD effectively mitigates hallucinations, outperforming state-of-the-art methods with respect to performance on LVLM benchmarks and computation time.
Code (0)
등록된 구현이 없습니다.
Tasks
HallucinationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The Mirage of Performance Gains: Why Contrastive Decoding Fails to Address Multimodal Hallucination
Contrastive decoding strategies are widely used to reduce hallucinations in multimodal large language models (MLLMs). These methods work by constructing contrastive samples to induce hallucinations and then suppressing t…
HallucinationRethinking CD: A Reproducibility Study and Extension on the Ineffectiveness of Contrastive Decoding at Mitigating Object Hallucinations in MLLMs
Contrastive decoding (CD) has been proposed as a training-free strategy for mitigating object hallucinations in multimodal large language models (MLLMs), with reported gains on benchmarks such as POPE. However, recent wo…
Visual GroundingASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Multimodal Large Language Model (MLLM) often suffer from hallucinations. They over-rely on partial cues and generate incorrect responses. Recently, methods like Visual Contrastive Decoding (VCD) and Instruction Contrasti…
HallucinationLanguage ModelingLanguage ModellingLarge Language Model+2ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models
Hallucinations in Multimodal Large Language Models (MLLMs) where generated responses fail to accurately reflect the given image pose a significant challenge to their reliability. To address this, we introduce ConVis, a n…
HallucinationMaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding
Large vision-language models (LVLMs) have shown remarkable performance in visual-language understanding for downstream multimodal tasks. While their capabilities are improving, problems emerge simultaneously. Among those…