Rethinking CD: A Reproducibility Study and Extension on the Ineffectiveness of Contrastive Decoding at Mitigating Object Hallucinations in MLLMs

• URL: http://arxiv.org/abs/2607.25196v1
• Date: Tue, 28 Jul 2026 01:55:58 GMT
• Title: Rethinking CD: A Reproducibility Study and Extension on the Ineffectiveness of Contrastive Decoding at Mitigating Object Hallucinations in MLLMs
• Abstract summary: Contrastive decoding (CD) has been proposed as a training-free strategy for mitigating object hallucinations in large language models (MLLMs)<n>We show that the apparent improvements from CD are often spurious and do not consistently translate into stronger visual grounding for reducing hallucinations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 work has questioned whether these gains reflect genuine improvements in visual grounding. In this study, we reproduce and extend the findings of "The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs." Specifically, we test the claim that CD induces a unidirectional output distribution shift in discriminative datasets and examine its generalizability across datasets. We also verify that the adaptive plausibility constraint (APC) reduces sampling to greedy search on both discriminative and generative benchmarks. Beyond reproduction, we rigorously study the effects of CD across generative and discriminative datasets. We conduct several experiments that provide additional insights: we analyze the logit distributions induced by different CD strategies on generative datasets, propose a proxy method and compare its performance against CD techniques, and investigate how hallucination signals propagate through each layer of the expert and amateur models. Experimental results across MME, POPE, and CHAIR using LLaVA and Qwen validate the original claims and show that the apparent improvements from CD are often spurious and do not consistently translate into stronger visual grounding for reducing hallucinations. These findings challenge the effectiveness of current contrastive decoding strategies and motivate the development of more reliable approaches for mitigating hallucinations in MLLMs.

Related papers

• VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing [70.82867621856968]
  Large vision-language models (LVLMs) frequently suffer from Object Hallucination (OH)<n>Recent studies suggest that the hallucination problem may stem from language priors.<n>We propose Visual Contrastive Editing (VCE), a novel post-hoc method that identifies and suppresses hallucinatory tendencies.
  arXiv  Detail & Related papers  (2026-04-21T12:40:07Z)
• Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation [68.41785694664011]
  We propose a plug-and-play framework called Locate-Then-Sparsify for Feature Steering (LTS-FS)<n>It controls the steering intensity according to the hallucination relevance of each layer.<n>Our framework effectively mitigates hallucination while preserving strong performance.
  arXiv  Detail & Related papers  (2026-03-17T09:16:50Z)
• Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization [78.94590726578014]
  multimodal reasoning models (MLRMs) remain prone to hallucinations, and effective solutions are still underexplored.<n>We propose C3PO, a training-based mitigation framework comprising textbfCompression and textbfPreference textbfOptimization.
  arXiv  Detail & Related papers  (2026-02-03T11:00:55Z)
• ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs [50.18087419133284]
  hallucination detection methods leveraging hidden states predominantly focus on static and isolated representations.<n>We introduce a novel metric, the ICR Score, which quantifies the contribution of modules to the hidden states' update.<n>We propose a hallucination detection method, the ICR Probe, which captures the cross-layer evolution of hidden states.
  arXiv  Detail & Related papers  (2025-07-22T11:44:26Z)
• ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM [16.694799255671914]
  Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues.<n>We propose Attention-Steerable Contrastive Decoding (ASCD), which directly steers the attention scores during decoding.
  arXiv  Detail & Related papers  (2025-06-17T17:58:11Z)
• Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models - [1.2499537119440245]
  Efficient Contrastive Decoding (ECD) is a simple method that leverages probabilistic hallucination detection to shift the output distribution towards contextually accurate answers at inference time.<n>Our experiments show that ECD effectively mitigates hallucinations, outperforming state-of-the-art methods with respect to performance on LVLM benchmarks and computation time.
  arXiv  Detail & Related papers  (2025-04-16T14:50:25Z)
• The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs? [51.476751660784174]
  We introduce a series of spurious improvement methods and evaluate their performance against contrastive decoding techniques.<n> Experimental results reveal that the observed performance gains in contrastive decoding are entirely unrelated to its intended goal of mitigating hallucinations.
  arXiv  Detail & Related papers  (2025-04-14T09:25:37Z)
• ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models [15.156359255401812]
  We propose an open-set, dynamic protocol to evaluate hallucinations in large language models (MLLMs)<n>ODE employs a graph-based structure to represent real-world object concepts, their attributes, and the distributional associations between them.<n>It generates varied samples for structured queries that evaluate hallucinations in both generative and discriminative tasks.
  arXiv  Detail & Related papers  (2024-09-14T05:31:29Z)
• Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuning [13.805780090705252]
  We propose a targeted instruction data generation framework named DFTG that tailored to the hallucination specificity of different models.<n>The experimental results on hallucination benchmarks demonstrate that the targeted instruction data generated by our method are more effective in mitigating hallucinations compared to previous datasets.
  arXiv  Detail & Related papers  (2024-04-16T07:14:32Z)
• Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding [25.489832294197797]
  This paper introduces the Instruction Contrastive Decoding (ICD) method, a novel approach designed to reduce hallucinations during LVLM inference. Our method is inspired by our observation that what we call disturbance instructions significantly exacerbate hallucinations in multimodal fusion modules.
  arXiv  Detail & Related papers  (2024-03-27T16:04:47Z)
• Debiasing Multimodal Large Language Models via Penalization of Language Priors [38.97645845493758]
  Multimodal Large Language Models (MLLMs) have become indispensable tools in computer vision and natural language processing.<n>Despite their advancements, our investigation reveals a noteworthy bias: the generated content is often driven more by the inherent priors of the underlying Large Language Models (LLMs) than by the input image.<n>We propose two simple, training-free strategies to rectify these biases and redirect the model's focus toward visual information.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)
• Alleviating Hallucinations of Large Language Models through Induced Hallucinations [67.35512483340837]
  Large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information. We propose a simple textitInduce-then-Contrast Decoding (ICD) strategy to alleviate hallucinations.
  arXiv  Detail & Related papers  (2023-12-25T12:32:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.