The Instinctive Bias: Spurious Images lead to Illusion in MLLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing multi-modal large language models (MLLMs) are able to process visual inputs by converting them into visual tokens that share the same latent space as language tokens in LLMs. |
| Approach: | They propose a benchmark that assesses the visual illusion level given spurious images and a pipeline that converts visual inputs into visual tokens. |
| Outcome: | The proposed benchmark shows that MLLMs suffer from an instinctive bias to varying degrees when presented with spurious images. |
Similar Papers
Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal large language models exhibit a pronounced form of visual sycophantic behavior when they process image inputs. |
| Approach: | They propose a technique that allows multimodal large language models to engage in reflective reasoning and determine whether a user’s instruction is misleading or corrective. |
| Outcome: | The proposed model resists misleading instructions but is stubborn even if it is wrong. |
Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios (2025.emnlp-main)
Copied to clipboard
Yunkai Dang, Mengxi Gao, Yibo Yan, Xin Zou, Yanggan Gu, Jungang Li, Jingyu Wang, Peijie Jiang, Aiwei Liu, Jia Liu, Xuming Hu
| Challenge: | Existing studies have focused mainly on visual–textual misalignment, leaving largely unexplored the MLLMs’ ability to preserve an original correct answer when confronted with misleading information. |
| Approach: | They propose a two-stage evaluation pipeline to quantify the response uncertainty phenomenon by eliciting each model’s original response on unperturbed inputs and injecting explicit (false-answer hints) and implicit (contextual contradictions) misleading instructions. |
| Outcome: | The proposed model overturns a correct answer in 65% of cases after receiving a single deceptive cue. |
Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) often rely on spurious correlations, undermining their robustness and generalization. |
| Approach: | They propose a causal mediation-based debiasing framework to address correlation bias in MLLMs . they distinguish core semantics from spurious textual and visual contexts using counterfactual examples . |
| Outcome: | The proposed framework surpasses existing state-of-the-art models on sarcasm detection and sentiment analysis tasks. |
Visual Interference in Speech Evaluation: Cultural Asymmetry and Cross-Modal Bias in MLLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | a new paradigm shifts the paradigm of speech processing from simple transcription to complex social reasoning. |
| Approach: | They construct a cross-modal dataset to examine cultural asymmetry in MLLMs . they find that ML models actively reproduce context-dependent sociolinguistic ideologies based on native audio . |
| Outcome: | The proposed model exhibits cultural asymmetry in anglophone and Korean contexts . the model reproduces sociolinguistic ideologies, consistent with Expectancy Violation Theory . |
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have facilitated the development of Multimodal LLMs. |
| Approach: | They propose a causal framework to interpret unimodal biases in visual question answering problems and a framework to integrate information from different modalities and mitigate biase. |
| Outcome: | The proposed framework analyzes visual question answering (VQA) problems to assess their impact on predictions. |
MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are increasingly used as automatic judges . however, their reliability and vulnerabilities to biases remain underexplored . |
| Approach: | They propose a benchmark to evaluate MLLMs that fail to integrate visual cues . they also introduce a test to evaluate the reliability of MLMLs based on a set of asymmetric evaluation tendencies. |
| Outcome: | Experiments on 26 state-of-the-art MLLMs reveal modality neglect and asymmetric evaluation tendencies . a standardized model with a benchmark enables a fine-grained diagnosis of nine bias types . |
CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models (2024.acl-long)
Copied to clipboard
Fuwen Luo, Chi Chen, Zihao Wan, Zhaolu Kang, Qidong Yan, Yingjie Li, Xiaolong Wang, Siyu Wang, Ziyue Wang, Xiaoyue Mi, Peng Li, Ning Ma, Maosong Sun, Yang Liu
| Challenge: | Multimodal large language models have demonstrated promising results in a variety of tasks that combine vision and language. |
| Approach: | They propose a benchmark to assess the ability of models to use contextual information in free-form text to enhance visual comprehension. |
| Outcome: | The proposed model fails to extract and utilize contextual information to improve understanding of images. |
AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal Large Language Models are increasingly used in Personalized Image Aesthetic Assessment (PIAA) however, their predictions may reflect subtle biases influenced by demographic factors such as gender, age, and education. |
| Approach: | They propose to evaluate MLLMs along two complementary dimensions: (1) stereotype bias and (2) alignment between model outputs and genuine human aesthetic preferences. |
| Outcome: | The proposed benchmark covers three subtasks: aesthetic perception, assessment, empathy and alignment between outputs and genuine human aesthetic preferences. |
Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. |
| Approach: | They propose large vision-Language Models to augment LLMs with visual inputs. |
| Outcome: | The proposed models condition generated text on both an input image and a visual prompt, enabling a variety of use cases such as visual question answering and multimodal chat. |
Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-modal large language models have been used for processing and understanding information from diverse modalities. |
| Approach: | They propose to evaluate the audio-visual capabilities of multi-modal large language models . they focus on effectiveness, efficiency, generalizability, and robustness . |
| Outcome: | The proposed models exhibit strong zero-shot and few-shot generalization abilities . their success relies heavily on the vision modality, which impairs performance when visual input is corrupted or missing. |