# CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs

arXiv: https://arxiv.org/abs/2411.12713 · HTML: https://mlsanity.com/paper/2411.12713/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- First posted on arXiv 19 Nov 2024.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)
- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Built on by (most cited first, 12 of 12)

- [ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing](https://mlsanity.com/paper/2506.19848/) (2025)
- [MaLoRA: Gated Modality LoRA for Key-Space Alignment in Multimodal LLM Fine-Tuning](https://mlsanity.com/paper/2510.26721/) (2025)
- [CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2506.23590/) (2025)
- [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025)
- [Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection](https://mlsanity.com/paper/2509.03113/) (2025)
- [Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding](https://mlsanity.com/paper/2512.19070/) (2025)
- [Instruction-Evidence Contrastive Dual-Stream Decoding for Grounded Vision-Language Reasoning](https://mlsanity.com/paper/2604.25809/) (2026)
- [VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision](https://mlsanity.com/paper/2609.27948/) (2026)
- [Fusion to Enhance: Fusion Visual Encoder to Enhance Multimodal Language Model](https://mlsanity.com/paper/2509.00664/) (2025)
- [CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering](https://mlsanity.com/paper/2605.04641/) (2026)
- [Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models](https://mlsanity.com/paper/2608.14797/) (2026)
- [What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes](https://mlsanity.com/paper/2609.16646/) (2026)

## Abstract (arXiv)

Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and autonomous systems. Despite previous efforts to mitigate hallucinations, a persistent issue remains: visual defect from vision-language misalignment, creating a bottleneck in visual processing capacity. To address this challenge, we develop Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs (CATCH), based on the Information Bottleneck theory. CATCH introduces Complementary Visual Decoupling (CVD) for visual information separation, Non-Visual Screening (NVS) for hallucination detection, and Adaptive Token-level Contrastive Decoding (ATCD) for hallucination mitigation. CATCH addresses issues related to visual defects that cause diminished fine-grained feature perception and cumulative hallucinations in open-ended scenarios. It is applicable to various visual question-answering tasks without requiring any specific data or prior knowledge, and generalizes robustly to new tasks without additional training, opening new possibilities for advancing LVLM in various challenging applications.