Papers › Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via...

Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance

21 Nov 2024arXiv:2411.14279archive 2025-07-28

Haozhe Zhao, Shuzheng Si, Liang Chen, Yichi Zhang, Maosong Sun, Mingjia Zhang, Baobao Chang

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on images and ineffective visual comprehension. We identify two primary reasons for this bias: 1. Different scales of training data between the pretraining stage of LLM and multimodal alignment stage. 2. The learned inference bias due to short-term dependency of text data. Therefore, we propose LACING, a systemic framework designed to address the language bias of LVLMs with muLtimodal duAl-attention meChanIsm (MDA) aNd soft-image Guidance (IFG). Specifically, MDA introduces a parallel dual-attention mechanism that enhances the integration of visual inputs across the model. IFG introduces a learnable soft visual prompt during training and inference to replace visual inputs, designed to compel LVLMs to prioritize text inputs. Then, IFG further proposes a novel decoding strategy using the soft visual prompt to mitigate the model's over-reliance on adjacent text inputs. Comprehensive experiments demonstrate that our method effectively debiases LVLMs from their language bias, enhancing visual comprehension and reducing hallucinations without requiring additional training resources or data. The code and model are available at [lacing-lvlm.github.io](https://lacing-lvlm.github.io).

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Visual Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet LLaVA1.5-13B-MDA GPT-4 score 39.90 #113 of 231 Archive leaderboard report
Visual Question Answering MM-Vet LLaVA1.5-13B-MDA Params 13B #113 of 231 Archive leaderboard report
Visual Question Answering MM-Vet LLaVA1.5-7B-MDA GPT-4 score 35.20 #161 of 231 Archive leaderboard report
Visual Question Answering MM-Vet LLaVA1.5-7B-MDA Params 7B #161 of 231 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections