Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Hallucination-aware intermediate representation edit in large vision-language models

Wei Suo, Hanzu Zhang, Lijun Zhang, Ji Ma, Peng Wang, Yanning Zhang

Abstract

Large Vision-Language Models have demonstrated exceptional performance in multimodal reasoning and complex scene understanding. However, these models still face significant hallucination issues, where outputs contradict visual facts. Recent research on hallucination mitigation has focused on retraining methods and Contrastive Decoding (CD) methods. While both methods perform well, retraining methods require substantial training resources, and CD methods introduce dual inference overhead. These factors hinder their practical applicability. To address the above issue, we propose a framework for dynamically detecting hallucination representations and performing hallucination-eliminating edits on these representations. With minimal additional computational cost, we achieve state-of-the-art performance on existing benchmarks. Extensive experiments demonstrate the effectiveness of our approach, highlighting its efficient and robust hallucination elimination capability and its powerful controllability over hallucinations. Code is available at https://github.com/ASGO-MM/HIRE

Hallucination-aware intermediate representation edit in large vision-language models

Abstract

Large Vision-Language Models have demonstrated exceptional performance in multimodal reasoning and complex scene understanding. However, these models still face significant hallucination issues, where outputs contradict visual facts. Recent research on hallucination mitigation has focused on retraining methods and Contrastive Decoding (CD) methods. While both methods perform well, retraining methods require substantial training resources, and CD methods introduce dual inference overhead. These factors hinder their practical applicability. To address the above issue, we propose a framework for dynamically detecting hallucination representations and performing hallucination-eliminating edits on these representations. With minimal additional computational cost, we achieve state-of-the-art performance on existing benchmarks. Extensive experiments demonstrate the effectiveness of our approach, highlighting its efficient and robust hallucination elimination capability and its powerful controllability over hallucinations. Code is available at https://github.com/ASGO-MM/HIRE

Paper Structure

This paper contains 33 sections, 12 equations, 11 figures, 15 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Large Vision-Language Models
  4. Mitigating Hallucinations in LVLMs
  5. Preliminary
  6. Method
  7. Model Structure
  8. Model Optimization
  9. Data Construction
  10. Training Process
  11. Experiments
  12. Experimental Settings
  13. Results on Benchmarks
  14. Hallucination Regulator
  15. Ablation Study
  16. ...and 18 more sections

Figures (11)

  • Figure 1: Comparison of mainstream hallucination mitigation paradigms. (a) Retraining-based methods: Constructing hallucination-specific datasets and training frameworks. (b) Contrastive decoding methods: Comparing the original probability distribution with a perturbed one. (c) Our method: Editing intermediate representations of LVLMs.
  • Figure 2: Overview of HIRE. Our framework consists of two key components: the Editor, which learns semantic invariance and hallucinatory difference through contrastive learning, and the Router, which learns efficient editing strategies through DPO.
  • Figure 3: Control hallucination via $\alpha$.
  • Figure 4: Some examples of generative and discriminative tasks on the MSCOCO dataset, with hallucinated content highlighted in red and newly added correct content displayed in green.
  • Figure 5: Distribution of original, hallucinated, and edited representations.
  • ...and 6 more figures