V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:K7NA5V4Vrecord.jsonopen to challenge →
read the original abstract
Large vision-language models (LVLMs) suffer from hallucination, resulting in misalignment between the output textual response and the input visual content. Recent research indicates that the over-reliance on the Large Language Model (LLM) backbone, as one cause of the LVLM hallucination, inherently introduces bias from language priors, leading to insufficient context attention to the visual inputs. We tackle this issue of hallucination by mitigating such over-reliance through preference learning. We propose Vision-guided Direct Preference Optimization (V-DPO) to enhance visual context learning at training time. To interpret the effectiveness and generalizability of V-DPO on different types of training data, we construct a synthetic dataset containing both response- and image-contrast preference pairs, compared against existing human-annotated hallucination samples. Our approach achieves significant improvements compared with baseline methods across various hallucination benchmarks. Our analysis indicates that V-DPO excels in learning from image-contrast preference data, demonstrating its superior ability to elicit and understand nuances of visual context. Our code is publicly available at https://github.com/YuxiXie/V-DPO.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs
Introduces VidPair-Halluc benchmark of 1K background-controlled adversarial video pairs and 11K QA pairs generated via PairFlow pipeline to evaluate hallucination in LVMs.
-
P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
P²-DPO generates on-policy preference pairs targeting focus-and-enhance perception and visual robustness, combined with a calibration loss, to reduce hallucinations in LVLMs more effectively than human-feedback baselines.
-
Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models
Audio-Contrastive Preference Optimization (ACPO) mitigates audio hallucination in AVLMs via output-contrastive and input-contrastive objectives that enforce faithful audio grounding.
-
Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation
TLVS mitigates hallucinations in LVLMs via token-level extraction and visual-sensitivity-adaptive steering applied only at critical decoding steps.
-
Online Self-Calibration Against Hallucination in Vision-Language Models
OSCAR exploits the generative-discriminative gap in LVLMs to build online preference data with MCTS and dual-granularity rewards for DPO-based calibration, claiming SOTA hallucination reduction and improved multimodal...
-
When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs
Hallucinations in LVLMs largely arise from textual priors in prompts, and can be reduced by fine-tuning with preference optimization on grounded vs. hallucinated response pairs.
-
Hallucination of Multimodal Large Language Models: A Survey
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.