# TokenShapley: Token Level Context Attribution with Shapley Value

arXiv: https://arxiv.org/abs/2507.05261 · HTML: https://mlsanity.com/paper/2507.05261/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 18 Jun 2025.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Studying Large Language Model Generalization with Influence Functions](https://mlsanity.com/paper/2308.03296/) (2023)
- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Towards Efficient Data Valuation Based on the Shapley Value](https://mlsanity.com/paper/1902.10275/) (2019)
- [Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms](https://mlsanity.com/paper/1908.08619/) (2019)
- [Complex Claim Verification with Evidence Retrieved in the Wild](https://mlsanity.com/paper/2305.11859/) (2023)
- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Attribute First, then Generate: Locally-attributable Grounded Text Generation](https://mlsanity.com/paper/2403.17104/) (2024)
- [LLatrieval: LLM-Verified Retrieval for Verifiable Generation](https://mlsanity.com/paper/2311.07838/) (2023)
- ["According to ...": Prompting Language Models Improves Quoting from Pre-Training Data](https://mlsanity.com/paper/2305.13252/) (2023)
- [Influence Functions for Scalable Data Attribution in Diffusion Models](https://mlsanity.com/paper/2410.13850/) (2024)
- [Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation](https://mlsanity.com/paper/2201.10055/) (2022)
- [Retrieving Supporting Evidence for Generative Question Answering](https://mlsanity.com/paper/2309.11392/) (2023)
- [Data Shapley Valuation for Efficient Batch Active Learning](https://mlsanity.com/paper/2104.08312/) (2021)
- [Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering](https://mlsanity.com/paper/2405.17980/) (2024)
- [Nearest Neighbor Speculative Decoding for LLM Generation and Attribution](https://mlsanity.com/paper/2405.19325/) (2024)
- [Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation](https://mlsanity.com/paper/2005.10716/) (2020)
- [SEMQA: Semi-Extractive Multi-Source Question Answering](https://mlsanity.com/paper/2311.04886/) (2023)
- [Efficient Data Shapley for Weighted Nearest Neighbor Algorithms](https://mlsanity.com/paper/2401.11103/) (2024)
- [HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations](https://mlsanity.com/paper/2106.00162/) (2021)

## Built on by (most cited first, 15 of 15)

- [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)
- [RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion](https://mlsanity.com/paper/2601.03378/) (2026)
- [Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models](https://mlsanity.com/paper/2506.17585/) (2025)
- [In-Context Credit Assignment via the Core](https://mlsanity.com/paper/2605.06920/) (2026)
- [Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization](https://mlsanity.com/paper/2512.15765/) (2025)
- [ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training](https://mlsanity.com/paper/2603.29871/) (2026)
- [AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training](https://mlsanity.com/paper/2606.01635/) (2026)
- [TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning](https://mlsanity.com/paper/2602.18905/) (2026)
- [Computational Challenges in Token Economics: Bridging Economic Theory and AI System Design](https://mlsanity.com/paper/2605.17410/) (2026)
- [Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution](https://mlsanity.com/paper/2606.05486/) (2026)
- [MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems](https://mlsanity.com/paper/2606.12918/) (2026)
- [Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation](https://mlsanity.com/paper/2607.22766/) (2026)
- [How Context Attribution Handles What the Model Already Knows](https://mlsanity.com/paper/2607.23804/) (2026)
- [What the Model Cannot See: Covert and Provable Text Invisibility in LLMs](https://mlsanity.com/paper/2610.15883/) (2026)

## Abstract (arXiv)

Large language models (LLMs) demonstrate strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge. Prior work has explored attribution at the sentence level, but these methods fall short when users seek attribution for specific keywords within the response, such as numbers, years, or names. To address this limitation, we propose TokenShapley, a novel token-level attribution method that combines Shapley value-based data attribution with KNN-based retrieval techniques inspired by recent advances in KNN-augmented LLMs. By leveraging a precomputed datastore for contextual retrieval and computing Shapley values to quantify token importance, TokenShapley provides a fine-grained data attribution approach. Extensive evaluations on four benchmarks show that TokenShapley outperforms state-of-the-art baselines in token-level attribution, achieving an 11-23% improvement in accuracy.