提出新方法Open-DeBias，能有效缓解语言模型中未知偏见问题。
Open-DeBias: Toward Mitigating Open-Set Bias in Language Models
- 用适配器模块实现数据与参数高效去偏
- 在多个数据集上提升准确率，尤其对模糊样本改善近48%
- 零样本迁移至韩语任务仍保持84%准确率，跨语言通用性强
大语言模型在问答任务中表现卓越，但常携带有害偏见，影响公平性与可信度。现有去偏方法多局限于预定义类别，难以应对新出现或特定情境的偏见。为此，本文首次提出开放集偏见检测与缓解问题，构建OpenBiasBench基准，覆盖已知与未见过的偏见类别。提出Open-DeBias方法，利用适配器模块，在仅使用少量训练数据的情况下，有效缓解社会与刻板印象偏见，并泛化至未见偏见。相比当前最优方法BMBI，Open-DeBias在BBQ数据集模糊子集上提升近48%，在明确子集上提升6%；同一适配器零样本迁移到韩语BBQ任务，准确率达84%。大量实验证明其在StereoSet、CrowS-Pairs等任务中同样有效，展现强鲁棒性、多语言能力与通用去偏潜力。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have achieved remarkable success on question answering (QA) tasks, yet they often encode harmful biases that compromise fairness and trustworthiness. Most existing bias mitigation approaches are restricted to predefined categories, limiting their ability to address novel or context-specific emergent biases. To bridge this gap, we tackle the novel problem of open-set bias detection and mitigation in text-based QA. We introduce OpenBiasBench, a comprehensive benchmark designed to evaluate biases across a wide range of categories and subgroups, encompassing both known and previously unseen biases. Additionally, we propose Open-DeBias, a novel, data-efficient, and parameter-efficient debiasing method that leverages adapter modules to mitigate existing social and stereotypical biases while generalizing to unseen ones. Compared to the state-of-the-art BMBI method, Open-DeBias improves QA accuracy on BBQ dataset by nearly $48\%$ on ambiguous subsets and $6\%$ on disambiguated ones, using adapters fine-tuned on just a small fraction of the training data. Remarkably, the same adapters, in a zero-shot transfer to Korean BBQ, achieve $84\%$ accuracy, demonstrating robust language-agnostic generalization. Through extensive evaluation, we also validate the effectiveness of Open-DeBias across a broad range of NLP tasks, including StereoSet and CrowS-Pairs, highlighting its robustness, multilingual strength, and suitability for general-purpose, open-domain bias mitigation. The project page is available at: https://sites.google.com/view/open-debias25
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。