REVIEW 6 cited by
Source Attribution in Retrieval-Augmented Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Source Attribution in Retrieval-Augmented Generation
read the original abstract
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.
Forward citations
Cited by 6 Pith papers
-
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a tra...
-
In-Context Credit Assignment via the Core
Algorithms based on the least core approximate stable credit assignments for AI-generated content using orders of magnitude fewer LLM calls than alternatives.
-
Barriers to Counterfactual Credit Attribution for Autoregressive Models
CCA does not compose autoregressively and retrofitting requires exponential query complexity under weak optimality.
-
MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution
MaxShapley computes fair document attributions in generative QA by reducing Shapley value calculation to polynomial time via a max-sum utility, matching exact Shapley quality on HotPotQA, MuSiQUE, and MS MARCO while u...
-
LegalCheck: Retrieval- and Context-Augmented Generation for Drafting Municipal Legal Advice Letters
LegalCheck automates drafting of municipal legal advice letters via RAG and CAG, producing near-final drafts in minutes with 80-100% coverage of essential legal reasoning in an Amsterdam deployment.
-
LegalCheck: Retrieval- and Context-Augmented Generation for Drafting Municipal Legal Advice Letters
LegalCheck applies RAG and CAG to generate draft legal advice letters from laws and precedents, achieving 80-100% coverage of essential reasoning in minutes during a municipal deployment.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.