Challenge: Existing work on social intelligence using large multimodal models is under-explored due to the prevalence of text-based data in the pretraining stage.
Approach: They propose a structure causal model to mitigate the negative language biases of large multimodal models by preserving beneficial priors.
Outcome: The proposed model minimizes negative language bias while preserving beneficial priors while avoiding spurious correlations between LMMs' internal commonsense knowledge and the given context.

Similar Papers

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.
An Investigation of the (In)effectiveness of Counterfactually Augmented Data (2022.acl-long)

Copied to clipboard

Challenge: Pretrained language models tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data.
Approach: They propose to use counterfactually-augmented data (CAD) to identify robust features that are invariant under distribution shift to train models for OOD generalization.
Outcome: The proposed model can learn robust features that are invariant under distribution shifts, but lacks spurious correlations, and may exacerbate existing correlations.
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.
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.
A Robust Dual-debiasing VQA Model based on Counterfactual Causal Effect (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing VQA models suffer from language bias that indicates a spurious correlation between textual questions and answers.
Approach: They propose a model agnostic dual-debiasing framework that models two types of language bias by separate branches under counterfactual inference framework.
Outcome: The proposed framework significantly reduces language bias and achieves state-of-the-art performance on the benchmark datasets.
CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples (2025.emnlp-main)

Copied to clipboard

Challenge: Spurious correlations are patterns that appear in datasets but do not represent genuine relationships.
Approach: They propose a more general form of counterfactual data augmentation that tackles multiple biases . they propose 'CoBA' that decomposes text into subject-predicate-object triples and modifies them to disrupt spurious correlations.
Outcome: The proposed framework reduces biases and strengthens out-of-distribution resilience.
Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration (2025.naacl-long)

Copied to clipboard

Challenge: Large language models generate biased stances due to spurious correlations and preference towards certain individuals and topics.
Approach: They propose a counterfactual Augmented Calibration Network to calibrate potential bias in stance detection of large language models.
Outcome: The proposed calibration network can mitigate biases of large language models, achieving state-of-the-art results.
Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable Mitigation of Social Biases in LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: a new method to mitigate stereotypical bias in large language models is needed . inherent biases from training on vast Internet datasets can amplify harmful stereotypes .
Approach: They propose a method to identify stereotypical bias in decoder-only transformer models . they apply a localization mechanism that correlates internal activations with a new Context Influence score .
Outcome: The proposed method reduces stereotypical biases on BBQ, StereoSet, and CrowS-Pairs while improving reasoning performance on MMLU by 10%.
A Group Fairness Lens for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods focusing on a few groups lack a comprehensive categorical perspective to evaluate LLMs’ potential biases and unfairness.
Approach: They propose to evaluate LLM biases from a group fairness lens using a hierarchical schema characterizing diverse social groups.
Outcome: The proposed method mitigates biases in LLMs from a group fairness lens and encapsulates target-attribute combinations across multiple dimensions.
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation (2026.acl-long)

Copied to clipboard

Challenge: Large language models excel at generating English counterfactuals but their effectiveness in generating multilingual counterfacts remains unclear.
Approach: They conduct automatic evaluations on both directly generated and derived counterfactuals in six languages and find that cross-lingual perturbations follow common strategic principles.
Outcome: The proposed models show that translation-based counterfactuals offer higher validity than their directly generated counterparts, but still fall short of matching the quality of the original English counterf actuals.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations