mlsanityData to 14 Oct 2026

TokenShapley: Token Level Context Attribution with Shapley Value

arXiv 2507.05261 ↗First posted 18 Jun 2025cs.CL cs.LGcited by 15

Not on the map. Why?

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.

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

30 of 43 references.

References · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  7. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  8. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  9. 2022A Survey on In-context Learningcited by 721
  10. 2018QuAC : Question Answering in Contextcited by 381
  11. 2023Studying Large Language Model Generalization with Influence Functionscited by 326
  12. 2023TRAK: Attributing Model Behavior at Scalecited by 283
18 more
  1. 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 281
  2. 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 148
  3. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  4. 2024ContextCite: Attributing Model Generation to Contextcited by 98
  5. 2023A Survey of Large Language Models Attributioncited by 71
  6. 2024Attribute First, then Generate: Locally-attributable Grounded Text Generationcited by 54
  7. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  8. 2023"According to ...": Prompting Language Models Improves Quoting from Pre-Training Datacited by 42
  9. 2024Influence Functions for Scalable Data Attribution in Diffusion Modelscited by 33
  10. 2022Identifying a Training-Set Attack's Target Using Renormalized Influence Estimationcited by 32
  11. 2023Retrieving Supporting Evidence for Generative Question Answeringcited by 31
  12. 2021Data Shapley Valuation for Efficient Batch Active Learningcited by 27
  13. 2024Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answeringcited by 25
  14. 2024Nearest Neighbor Speculative Decoding for LLM Generation and Attributioncited by 25
  15. 2020Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluationcited by 22
  16. 2023SEMQA: Semi-Extractive Multi-Source Question Answeringcited by 19
  17. 2024Efficient Data Shapley for Weighted Nearest Neighbor Algorithmscited by 18
  18. 2021HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversationscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 12.

15 papers.

Sort:

By area:

  1. 2026The Why Behind the Action: Unveiling Internal Drivers via Agentic Attributioncited by 11
  2. 2025MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attributioncited by 3
  3. 2026RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completioncited by 3
  4. 2025Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Modelscited by 2
  5. 2026In-Context Credit Assignment via the Corecited by 2
  6. 2025Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimizationcited by 1
  7. 2026ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Trainingcited by 1
  8. 2026AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Trainingcited by 1
  9. 2026TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoningcited by 0
  10. 2026Computational Challenges in Token Economics: Bridging Economic Theory and AI System Designcited by 0
  11. 2026Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attributioncited by 0
  12. 2026MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systemscited by 0
3 more
  1. 2026Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluationcited by 0
  2. 2026How Context Attribution Handles What the Model Already Knowscited by 0
  3. 2026What the Model Cannot See: Covert and Provable Text Invisibility in LLMscited by 0