提升大模型在多文档摘要中的公平性，避免偏见误导决策。
Improving Fairness of Large Language Models in Multi-document Summarization
- 通过扰动文档集生成偏好对，增强摘要层面公平性。
- 动态调整偏好对权重，实现文档集合层面公平性优化。
- 兼顾摘要质量与公平性，适合需公正输出的场景使用。
多文档摘要中的公平性对于呈现具有多样化社会属性值的文档全景至关重要，可能显著影响决策。例如，若摘要系统过度呈现产品的负面评价，会误导用户忽视优质产品。现有研究从摘要层面和语料层面衡量公平性，但多数方法聚焦于摘要层面。本文提出 FairPO，一种同时关注摘要与语料层面公平性的偏好微调方法。为提升摘要层面公平性，我们通过扰动文档集生成偏好对；为改善语料层面公平性，提出基于公平性的偏好微调，动态调整偏好对权重。实验表明，FairPO 在保持摘要关键质量的同时，优于强基线方法。代码已开源：https://github.com/leehaoyuan/coverage_fairnes。
原文摘要 · Abstract (English)
Fairness in multi-document summarization (MDS) is crucial for providing comprehensive views across documents with diverse social attribute values, which can significantly impact decision-making. For example, a summarization system that tends to overrepresent negative reviews of products can mislead customers into disregarding good products. Previous works measure fairness in MDS at two levels: summary-level and corpus-level. While summary-level fairness focuses on individual summaries, corpus-level fairness focuses on a corpus of summaries. Recent methods primarily focus on summary-level fairness. We propose FairPO, a preference tuning method that focuses on both summary-level and corpus-level fairness in MDS. To improve summary-level fairness, we propose to generate preference pairs by perturbing document sets. To improve corpus-level fairness, we propose fairness-aware preference tuning by dynamically adjusting the weights of preference pairs. Our experiments show that FairPO outperforms strong baselines while maintaining the critical qualities of summaries. The code is available at https://github.com/leehaoyuan/coverage_fairnes.
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。