arXiv Computer Vision

Melange: A Synthetic Visual Bias Benchmark for Multi-modal Large Language Models

Melange is a synthetic visual bias benchmark designed to evaluate social biases in multi‑modal large language models (MLLMs). It extends the language‑only BBQ dataset by generating controlled visual scenarios that clearly depict target attributes, and validates images through automated VQA screening and human inspection. Using Melange, 23 open‑source MLLMs were tested in text‑only, image‑only, and image‑with‑context settings, revealing that switching from text to vision reduces fairness by an average of 0.291 and that models often choose stereotypical responses when biased answers are made.

arXiv Computer Vision

Sep 16

ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models

The paper introduces ViD, a vision‑dominant gender bias mitigation framework for large vision‑language models. ViD uses causal analysis of attention patterns and dual mechanisms—backdoor adjustment and refined token selection—to suppress bias while preserving reasoning and generation quality. Experiments show a 14.7% reduction in gender bias on FACET and significant improvements on MS COCO image captioning, all without extra training overhead.

By Zhipeng Zhao, Zhaoqiang Wei, Peishun Liu, Youwei Zhao, Ruichun Tang

llms multimodal benchmarks safety

arXiv AI

Jul 20

Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.

By Bo-An Chang, Yu-Chih Chen

llms diffusion nlp reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 15

Mirage Probes: How Vision Models Fake Visual Understanding

arXiv:2606. 13870v1 Announce Type: cross Abstract: Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided.

By Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao, Raz Lapid, Amit LeVi, Allen G. Roush, Ravid Shwartz-Ziv, Hod Lipson

llms diffusion multimodal benchmarks

arXiv AI

Aug 25

Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding

arXiv:2608.21415v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases fro...

By Yisong Xiao, Aishan Liu, Yongxin Huang, Zonghao Ying, Shiji Zhao, Tianlin Li, Yong Han, Jian Yang, Xianglong Liu

llms multimodal benchmarks safety

arXiv AI

Aug 17

BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA

arXiv:2603. 28026v2 Announce Type: replace Abstract: Multimodal multiple-choice question answering (MCQA) provides a standardized and objectively measurable setting for evaluating vision-language models (VLMs).

By Taeyun Roh, Suhyeong Park, Dongyoung Lee, Eunyeong Jo, Wonjune Jang, Junha Jung, Jaewoo Kang

llms nlp efficiency multimodal benchmarks safety

arXiv AI

Oct 1

VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes

arXiv:2605.26380v2 Announce Type: replace-cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90\% accuracy on fine-grained perception benchmarks. How...

By Jingru Chen, Yiming Liu, Mingtao Chen, Sijie Chen, Richeng Xuan, Liang Yang, Zhichao Hu, Fanyang Lu

llms multimodal benchmarks

arXiv AI

Aug 26

Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes

The paper introduces CAIT, a benchmark of 400 synthetic scenes featuring counter‑intuitive actions that challenge multimodal large language models (MLLMs). Human participants and proprietary models like Claude and Gemini perform well, but standard open‑source instruction‑tuned MLLMs fail, largely due to a strong language prior that overrides contradictory visual evidence. The study shows that Chain‑of‑Thought reasoning can help but introduces new issues, while targeted fine‑tuning and structured prompting can reduce reliance on language priors and improve visual grounding.

By Chen Ling, Tongwei Zhang, Hanqian Li, Nai Ding

llms fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Aug 27

Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models

The paper investigates why multimodal large language models (MLLMs) struggle with vision‑centric tasks when visual evidence conflicts with pretrained language knowledge. Using image reconstruction and a new WhatIfVis benchmark, the authors show that MLLMs preserve coarse‑grained visual attributes but fail to consistently use them, and that supervised fine‑tuning and activation patching can improve controllability of visual context sensitivity. The study demonstrates that the main bottleneck lies in the models’ inability to reliably regulate their reliance on visual evidence rather than in visual perception itself.

By Jiaang Li, Chengzu Li, Zhaochong An, Yifei Yuan, Xi Liu, Serge Belongie, V\'esteinn Sn{\ae}bjarnarson

llms fine-tuning multimodal benchmarks

arXiv AI

Jun 2

Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

arXiv:2606. 02578v1 Announce Type: cross Abstract: Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visual evidence conflicts with textual cues, MLLM judges tend to reward plausible narratives over perceptually correct answers.

By Seojeong Park, Jiho Choi, Junyong Kang, Seonho Lee, Jaeyo Shin, Hyunjung Shim

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jul 24

Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning

arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.

By Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini, Davide Talon, Elisa Ricci

llms nlp fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 8

Diagnosing Visual Ignorance in Vision-Language Models

arXiv:2606. 06890v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence.

By Runyu Zhou, Qi Zhang, Qixun Wang, Yisen Wang

llms multimodal benchmarks

arXiv Computation and Language

Sep 11

Do Vision-Language Models Understand Visual Persuasiveness? A Diagnosis via Visual Persuasive Factors

The paper investigates whether Vision‑Language Models (VLMs) can understand visual persuasiveness by evaluating image‑message pairs that humans consistently judge as persuasive. It introduces Visual Persuasive Factors (VPFs), a taxonomy from cognitive psychology, to quantify visual cues influencing persuasive judgments. Empirical analysis shows VLMs tend to over‑predict persuasiveness, partially reproducing human patterns but often generating false positives, and that VPF‑guided interventions can improve performance only when properly framed.

By Gyuwon Park, Hyounghun Kim

llms multimodal safety

Related stories