# CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction

arXiv: https://arxiv.org/abs/2504.15629 · HTML: https://mlsanity.com/paper/2504.15629/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [Training Language Models to Generate Text with Citations via Fine-grained Rewards](https://mlsanity.com/paper/2402.04315/) (2024)
- [Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse](https://mlsanity.com/paper/2409.11242/) (2024)
- [CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation](https://mlsanity.com/paper/2406.05365/) (2024)
- [FACTOID: FACtual enTailment fOr hallucInation Detection](https://mlsanity.com/paper/2403.19113/) (2024)

## Built on by (most cited first, 8 of 8)

- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [Generation-Time vs. Post-hoc Citation: A Holistic Evaluation of LLM Attribution](https://mlsanity.com/paper/2509.21557/) (2025)
- [A Large-Language-Model Framework for Automated Humanitarian Situation Reporting](https://mlsanity.com/paper/2512.19475/) (2025)
- [RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems](https://mlsanity.com/paper/2605.10862/) (2026)
- [Rule-Based Explanations for Retrieval-Augmented LLM Systems](https://mlsanity.com/paper/2510.22689/) (2025)
- [DS@GT ARC at LongEval: Citation Integrity and Factual Grounding in Scientific QA](https://mlsanity.com/paper/2607.14400/) (2026)
- [AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents](https://mlsanity.com/paper/2609.05802/) (2026)
- [CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense](https://mlsanity.com/paper/2609.15660/) (2026)

## Abstract (arXiv)

Retrieval Augmented Generation (RAG) has emerged as a powerful application of Large Language Models (LLMs), revolutionizing information search and consumption. RAG systems combine traditional search capabilities with LLMs to generate comprehensive answers to user queries, ideally with accurate citations. However, in our experience of developing a RAG product, LLMs often struggle with source attribution, aligning with other industry studies reporting citation accuracy rates of only about 74% for popular generative search engines. To address this, we present efficient post-processing algorithms to improve citation accuracy in LLM-generated responses, with minimal impact on latency and cost. Our approaches cross-check generated citations against retrieved articles using methods including keyword + semantic matching, fine tuned model with BERTScore, and a lightweight LLM-based technique. Our experimental results demonstrate a relative improvement of 15.46% in the overall accuracy metrics of our RAG system. This significant enhancement potentially enables a shift from our current larger language model to a relatively smaller model that is approximately 12x more cost-effective and 3x faster in inference time, while maintaining comparable performance. This research contributes to enhancing the reliability and trustworthiness of AI-generated content in information retrieval and summarization tasks which is critical to gain customer trust especially in commercial products.