Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing

About

Despite the significant progress of Multimodal Large Language Models (MLLMs) across diverse tasks, hallucination -- corresponding to the generation of visually inconsistent objects, attributes, or relations -- remains a major obstacle to their reliable deployment. Unlike pure language models, MLLMs must ground their generation process in visual inputs. However, existing models often suffer from semantic drift during decoding, causing outputs to diverge from visual facts as the sequence length increases. To address this issue, we propose KVSmooth, a training-free and plug-and-play method that mitigates hallucination by performing attention-entropy-guided adaptive smoothing on hidden states. Specifically, KVSmooth applies an exponential moving average (EMA) to both keys and values in the KV-Cache, while dynamically quantifying the sink degree of each token through the entropy of its attention distribution to adaptively adjust the smoothing strength. Unlike computationally expensive retraining or contrastive decoding methods, KVSmooth operates efficiently during inference without additional training or model modification. Extensive experiments demonstrate that KVSmooth significantly reduces hallucination ($\mathit{CHAIR}_{S}$ from $41.8 \rightarrow 18.2$) while improving overall performance ($F_1$ score from $77.5 \rightarrow 79.2$), achieving higher precision and recall simultaneously. In contrast, prior methods often improve one at the expense of the other, validating the effectiveness and generality of our approach.

Siyu Jiang, Feiyang Chen, Xiaojin Zhang, Kun He• 2026

Related benchmarks

TaskDatasetResultRank
Hallucination EvaluationAMBER--
71
Hallucination EvaluationObject-HalBench
CHAIR Score (s)23.7
28
Hallucination MitigationCHAIR
CHAIR_S47.8
24
Object Presence RecognitionOPOPE
Accuracy74.6
21
Efficiency ComparisonCHAIR benchmark
Avg Time (s/caption)3.61
5
Showing 5 of 5 rows

Other info

Follow for update