# Source Attribution in Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2507.04480 · HTML: https://mlsanity.com/paper/2507.04480/

## Key facts

- Cited by 7 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 15 of its 19 references that are in the map.
- First posted on arXiv 6 Jul 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, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning](https://mlsanity.com/paper/2110.14049/) (2021)
- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [Inseq: An Interpretability Toolkit for Sequence Generation Models](https://mlsanity.com/paper/2302.13942/) (2023)
- [SEAT: Stable and Explainable Attention](https://mlsanity.com/paper/2211.13290/) (2022)
- [Generic Attention-model Explainability by Weighted Relevance Accumulation](https://mlsanity.com/paper/2308.10240/) (2023)

## Built on by (most cited first, 7 of 7)

- [The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution](https://mlsanity.com/paper/2601.15075/) (2026)
- [MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution](https://mlsanity.com/paper/2512.05958/) (2025)
- [In-Context Credit Assignment via the Core](https://mlsanity.com/paper/2605.06920/) (2026)
- [Barriers to Counterfactual Credit Attribution for Autoregressive Models](https://mlsanity.com/paper/2605.01425/) (2026)
- [LegalCheck: Retrieval- and Context-Augmented Generation for Drafting Municipal Legal Advice Letters](https://mlsanity.com/paper/2605.12012/) (2026)
- [Knowledge Dependency Estimation for Reliable Question Answering](https://mlsanity.com/paper/2605.28047/) (2026)
- [Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval](https://mlsanity.com/paper/2610.02070/) (2026)

## Abstract (arXiv)

While attribution methods, such as Shapley values, are widely used to explain the importance of features or training data in traditional machine learning, their application to Large Language Models (LLMs), particularly within Retrieval-Augmented Generation (RAG) systems, is nascent and challenging. The primary obstacle is the substantial computational cost, where each utility function evaluation involves an expensive LLM call, resulting in direct monetary and time expenses. This paper investigates the feasibility and effectiveness of adapting Shapley-based attribution to identify influential retrieved documents in RAG. We compare Shapley with more computationally tractable approximations and some existing attribution methods for LLM. Our work aims to: (1) systematically apply established attribution principles to the RAG document-level setting; (2) quantify how well SHAP approximations can mirror exact attributions while minimizing costly LLM interactions; and (3) evaluate their practical explainability in identifying critical documents, especially under complex inter-document relationships such as redundancy, complementarity, and synergy. This study seeks to bridge the gap between powerful attribution techniques and the practical constraints of LLM-based RAG systems, offering insights into achieving reliable and affordable RAG explainability.