{"doi":"10.48550/arxiv.2306.04597","title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","abstract":"Societal biases present in pre-trained large language models are a critical issue as these models have been shown to propagate biases in countless downstream applications, rendering them unfair towards specific groups of people. Since large-scale retraining of these models from scratch is both time and compute-expensive, a variety of approaches have been previously proposed that de-bias a pre-trained model. While the majority of current state-of-the-art debiasing methods focus on changes to the training regime, in this paper, we propose data intervention strategies as a powerful yet simple technique to reduce gender bias in pre-trained models. Specifically, we empirically show that by fine-tuning a pre-trained model on only 10 de-biased (intervened) training examples, the tendency to favor any gender is significantly reduced. Since our proposed method only needs a few training examples, our few-shot debiasing approach is highly feasible and practical. Through extensive experimentation, we show that our debiasing technique performs better than competitive state-of-the-art baselines with minimal loss in language modeling ability.","journal":"arXiv (Cornell University)","year":2023,"id":396638,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9491,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1160181,"name":"Atishay Jain","orcid":"0009-0004-6868-3490","position":1,"is_corresponding":false},{"id":1160182,"name":"Praneetha Vaddamanu","orcid":"0000-0003-4894-9517","position":2,"is_corresponding":false},{"id":550189,"name":"Paul Pu Liang","orcid":"0000-0001-7768-3610","position":3,"is_corresponding":false},{"id":110503,"name":"Louis–Philippe Morency","orcid":"0000-0001-6376-7696","position":4,"is_corresponding":false},{"id":1160828,"name":"Himanshu Thakur","orcid":null,"position":0,"is_corresponding":true}],"reference_count":0,"raw_metadata":null,"created_at":"2026-07-19T01:19:31.472087Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}