# CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs

arXiv: https://arxiv.org/abs/2603.21524 · HTML: https://mlsanity.com/paper/2603.21524/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 30 of 31)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [Evaluating and Mitigating Discrimination in Language Model Decisions](https://mlsanity.com/paper/2312.03689/) (2023)
- [FA*IR: A Fair Top-k Ranking Algorithm](https://mlsanity.com/paper/1706.06368/) (2017)
- [Debiasing Pre-trained Contextualised Embeddings](https://mlsanity.com/paper/2101.09523/) (2021)
- [A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning](https://mlsanity.com/paper/2203.11933/) (2022)
- [An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models](https://mlsanity.com/paper/2110.08527/) (2021)
- [A Survey on Fairness in Large Language Models](https://mlsanity.com/paper/2308.10149/) (2023)
- [Ranking with Fairness Constraints](https://mlsanity.com/paper/1704.06840/) (2017)
- [Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes](https://mlsanity.com/paper/2402.01981/) (2024)
- [ROBBIE: Robust Bias Evaluation of Large Generative Language Models](https://mlsanity.com/paper/2311.18140/) (2023)
- [Measuring Implicit Bias in Explicitly Unbiased Large Language Models](https://mlsanity.com/paper/2402.04105/) (2024)
- [Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models](https://mlsanity.com/paper/2405.10431/) (2024)
- [Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation](https://mlsanity.com/paper/2005.00965/) (2020)
- [Category Theory in Machine Learning](https://mlsanity.com/paper/2106.07032/) (2021)
- [Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting](https://mlsanity.com/paper/2410.19294/) (2024)
- [Intersectional Bias in Causal Language Models](https://mlsanity.com/paper/2107.07691/) (2021)
- [Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.11598/) (2024)
- [A Multi-LLM Debiasing Framework](https://mlsanity.com/paper/2409.13884/) (2024)
- [Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness](https://mlsanity.com/paper/2603.07368/) (2026)
- [Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models](https://mlsanity.com/paper/2402.10353/) (2024)

## Built on by (most cited first, 9 of 9)

- [VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models](https://mlsanity.com/paper/2604.03956/) (2026)
- [G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs](https://mlsanity.com/paper/2604.00419/) (2026)
- [PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs](https://mlsanity.com/paper/2605.01123/) (2026)
- [SafeCommit: Certifying When Memory-Grounded Agents May Safely Act](https://mlsanity.com/paper/2608.04289/) (2026)
- [Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Models](https://mlsanity.com/paper/2606.14647/) (2026)
- [Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs](https://mlsanity.com/paper/2609.10439/) (2026)
- [DePICT: Decision-Preserving Interface for Constrained Downstream Tasks](https://mlsanity.com/paper/2610.03945/) (2026)
- [RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents](https://mlsanity.com/paper/2610.09088/) (2026)
- [REPORT-OPS: Hybrid Evidence-Guided Reporting with Human-Supervised Refinement for HPC](https://mlsanity.com/paper/2610.19222/) (2026)

## Abstract (arXiv)

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.