 Mitigating Voter Attribute Bias for Fair Opinion AggregationAAAI/ACM Conference on AI, Ethics, and Society (AIES), 2023 |
 Uncovering and Quantifying Social Biases in Code GenerationNeural Information Processing Systems (NeurIPS), 2023 |
 Explanation-based Finetuning Makes Models More Robust to Spurious CuesAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Trustworthy Human Computation: A SurveyArtificial Intelligence Review (Artif Intell Rev), 2022 |
 Generating Data to Mitigate Spurious Correlations in Natural Language
Inference DatasetsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
