Papers with bias mitigation methods
Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Despite efforts to mitigate social bias in large language models, representational harms such as stereotyping continue to exist in both open and closed-source models. |
| Approach: | They propose a method to modify model activations in forward passes by applying steering vectors to a BBQ dataset and comparing their results to bias mitigation methods. |
| Outcome: | The proposed method outperforms 3 other bias mitigation methods on the BBQ dataset and shows the lowest impact on MMLU scores. |
Social-Group-Agnostic Bias Mitigation via the Stereotype Content Model (2023.acl-long)
Copied to clipboard
Ali Omrani, Alireza Salkhordeh Ziabari, Charles Yu, Preni Golazizian, Brendan Kennedy, Mohammad Atari, Heng Ji, Morteza Dehghani
| Challenge: | Existing methods for mitigating bias require social-group-specific word pairs for each social attribute (e.g., gender) Existing approaches require only one social attribute, rendering them impractical and costly . |
| Approach: | They propose that stereotype content models capture the underlying connection between bias and stereotypes by embedding only two psychological dimensions of warmth and competence. |
| Outcome: | The proposed method performs comparably to group-specific debiasing on multiple bias benchmarks, but has theoretical and practical advantages over existing methods. |
Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns (2023.eacl-main)
Copied to clipboard
| Challenge: | a number of studies have focused on gender bias in language models, but these methods fail to detect it. |
| Approach: | They propose to use gender bias in coreference resolution to evaluate gender bias . they propose to construct an annotated quadruple-level dataset with 4008 instances . |
| Outcome: | The proposed method is able to detect gender bias in a quadruple dataset . previous methods failed to detect bias or cancel it, the authors argue . |
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reduce disparities in model outcomes have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training. |
| Approach: | They propose to use certified word substitution robustness methods to improve equality of odds and equality of opportunity on multiple text classification tasks. |
| Outcome: | The proposed methods improve equality of odds and equality of opportunity on multiple text classification tasks. |
Identifying and Mitigating Annotation Bias in Natural Language Understanding using Causal Mediation Analysis (2024.findings-acl)
Copied to clipboard
Sitiporn Sae Lim, Can Udomcharoenchaikit, Peerat Limkonchotiwat, Ekapol Chuangsuwanich, Sarana Nutanong
| Challenge: | Current NLU models obtain state-of-the-art accuracy on in-distribution benchmarks, but they use annotation bias to make predictions, negatively affecting the models' generalizability. |
| Approach: | They apply causal mediation analysis to gauge how much each component mediates annotation biases and use causal-grounded masking and gradient unlearning to mitigate bias. |
| Outcome: | The proposed methods improve the model's robustness against annotation bias even after employing other training-time debiasing techniques. |
A negative case analysis of visual grounding methods for VQA (2020.acl-main)
Copied to clipboard
| Challenge: | Existing Visual Question Answering (VQA) methods exploit dataset biases and spurious statistical correlations instead of producing correct answers for the right reasons. |
| Approach: | They propose to incorporate visual cues to better ground VQA models . they also propose a regularization effect which prevents over-fitting to linguistic priors . |
| Outcome: | The proposed method outperforms existing methods on the Visual Question Answering (VQA) dataset. |
Analyzing Dialectical Biases in LLMs for Knowledge and Reasoning Benchmarks (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Previous work has shown degraded performance of large language models for under-represented English dialects. |
| Approach: | They analyze the effects of typifying “standard” American English language questions as non-”standard” dialectal variants on multiple choice questions. |
| Outcome: | The results show that typifying “standard” American English language questions as non-”standard” dialectal variants can reduce performance 20% . |