用数学结构设计公平性增强框架，显著降低大模型偏见。
CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs
- 结合范畴论与检索增强生成，从结构上抑制偏见方向。
- 在三个主流大模型上，准确率提升最高达40%，偏见几乎归零。
- 适合关注模型公平性、部署于高风险场景的研究者与工程师。
大语言模型在高风险场景中应用时，常表现出性别、种族和地理等偏见，影响公平性与可信度。以往去偏方法多仅作用于流程单一阶段，导致缓解不彻底且在分布变化下表现脆弱。本文提出CatRAG去偏框架，融合范畴论（functor）与检索增强生成（RAG），实现结构化去偏。其范畴论组件通过保持语义结构的方式，对嵌入空间中的偏见方向进行有原则的投影抑制。在面向问答的偏见基准测试（BBQ）中，针对Meta Llama-3、OpenAI GPT-OSS和Google Gemma-3三款开源模型，CatRAG将准确率最高提升40%（相比基线模型），较已有去偏方法提升超10%，并将偏见分数从基线的60%降至接近零，覆盖性别、国籍、种族及交叉子群体。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are deployed in high-stakes settings but can show demographic, gender, and geographic biases that undermine fairness and trust. Prior debiasing methods, including embedding-space projections, prompt-based steering, and causal interventions, often act at a single stage of the pipeline, resulting in incomplete mitigation and brittle utility trade-offs under distribution shifts. We propose CatRAG Debiasing, a dual-pronged framework that integrates functor with Retrieval-Augmented Generation (RAG) guided structural debiasing. The functor component leverages category-theoretic structure to induce a principled, structure-preserving projection that suppresses bias-associated directions in the embedding space while retaining task-relevant semantics. On the Bias Benchmark for Question Answering (BBQ) across three open-source LLMs (Meta Llama-3, OpenAI GPT-OSS, and Google Gemma-3), CatRAG achieves state-of-the-art results, improving accuracy by up to 40% over the corresponding base models and by more than 10% over prior debiasing methods, while reducing bias scores to near zero (from 60% for the base models) across gender, nationality, race, and intersectional subgroups.
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。