Papers with bias mitigation strategies
Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education (2025.naacl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have potential to automate hiring but inherent biases may lead to unfair hiring practices. |
| Approach: | They evaluate how factors such as gender, race, and educational background influence model decisions. |
| Outcome: | The proposed model reduces biases related to gender and race, but implicit biase concerning educational background remains significant. |
STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that assess explicit and implicit biases are based on a single scenario . a dataset of 450 offensive progressions contains 2,700 sentences of varying severity . |
| Approach: | They evaluate a dataset of offensive progressions that contain 2,700 sentences . they find that even the best-performing models detect bias inconsistently . |
| Outcome: | The proposed dataset shows that even the best-performing models detect bias inconsistently . aligning models with human judgments on STOP can improve answer rates on sensitive tasks by 191% . |
Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speech (2024.naacl-long)
Copied to clipboard
| Challenge: | Automatic speech recognition systems fail to accurately interpret speech patterns deviating from typical fluency, leading to critical usability issues and misinterpretations. |
| Approach: | They evaluate six leading automatic speech recognition systems based on a real-world dataset and a synthetic dataset derived from the widely-used LibriSpeech benchmark. |
| Outcome: | The six leading speech recognition systems were evaluated on a real-world dataset and a synthetic dataset derived from the widely-used LibriSpeech benchmark. |
Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Algorithmic fairness has traditionally adopted the mathematically convenient perspective of racial color-blindness. |
| Approach: | They propose a benchmark suite of eight different scenarios to assess group difference awareness. |
| Outcome: | The proposed model demonstrates that group difference awareness is a distinct dimension to fairness where existing bias mitigation strategies may backfire. |
Debiasing the Fine-Grained Classification Task in LLMs with Bias-Aware PEFT (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to mitigate label biases such as retraining, post-hoc adjustment, and parameter-efficient fine-tuning fail to address prediction propensity and discriminative ability biase. |
| Approach: | They propose a bias-aware optimization framework that incorporates two distinct label balance constraints with a PEFT strategy targeting an intermediate layer to mitigate this issue. |
| Outcome: | The proposed approach outperforms or matches the performance of full-parameter fine-tuning and LoRA, achieving superior results with lower perplexity. |
Cognitive Bias in Decision-Making with LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models inherit societal biases against protected groups and can be subject to functionally resembling cognitive bias. |
| Approach: | They propose a framework to uncover, evaluate, and mitigate cognitive bias in large language models by using a dataset containing 13,465 prompts to evaluate LLM decisions on different cognitive biases. |
| Outcome: | The proposed framework uncovers, evaluates, and mitigates cognitive bias in large language models, particularly in high-stakes decision-making tasks. |
Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplification and Resistance in Multi-Agent Based LLM-as-Judge (2025.findings-emnlp)
Copied to clipboard
Chiyu Ma, Enpei Zhang, Yilun Zhao, Wenjun Liu, Yaning Jia, Peijun Qing, Lin Shi, Arman Cohan, Yujun Yan, Soroush Vosoughi
| Challenge: | LLM-as-Judge frameworks provide scalable alternative to human evaluation . but the question of how intrinsic biases manifest in these settings remains unexplored . |
| Approach: | They conduct systematic analysis of four bias types in multi-agent LLM-as-Judge frameworks . they find debate framework amplifies biases sharply after initial debate . |
| Outcome: | The proposed frameworks amplify biases after debate and show they are stronger in meta-judge scenarios. |