# In-Context Credit Assignment via the Core

arXiv: https://arxiv.org/abs/2605.06920 · HTML: https://mlsanity.com/paper/2605.06920/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 24 of 24)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Towards Efficient Data Valuation Based on the Shapley Value](https://mlsanity.com/paper/1902.10275/) (2019)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [Data Shapley in One Training Run](https://mlsanity.com/paper/2406.11011/) (2024)
- [Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.13663/) (2024)
- [AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution](https://mlsanity.com/paper/2411.15102/) (2024)
- [TokenShapley: Token Level Context Attribution with Shapley Value](https://mlsanity.com/paper/2507.05261/) (2025)
- [LAQuer: Localized Attribution Queries in Content-grounded Generation](https://mlsanity.com/paper/2506.01187/) (2025)
- [TracLLM: A Generic Framework for Attributing Long Context LLMs](https://mlsanity.com/paper/2506.04202/) (2025)
- [Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.16415/) (2025)
- [Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.13772/) (2025)
- [Statistical Cost Sharing](https://mlsanity.com/paper/1703.03111/) (2017)
- [Source Attribution in Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.04480/) (2025)
- [Learning Cooperative Games](https://mlsanity.com/paper/1505.00039/) (2015)
- [JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution](https://mlsanity.com/paper/2405.20404/) (2024)
- [Making AI-Enhanced Videos: Analyzing Generative AI Use Cases in YouTube Content Creation](https://mlsanity.com/paper/2503.03134/) (2025)
- [Approximating the Core via Iterative Coalition Sampling](https://mlsanity.com/paper/2402.03928/) (2024)
- [Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation](https://mlsanity.com/paper/2504.14856/) (2025)
- [Weakest Bidder Types and New Core-Selecting Combinatorial Auctions](https://mlsanity.com/paper/2505.13680/) (2025)
- [MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution](https://mlsanity.com/paper/2512.05958/) (2025)
- [Context Attribution with Multi-Armed Bandit Optimization](https://mlsanity.com/paper/2506.19977/) (2025)

## Built on by (most cited first, 2 of 2)

- [Inference Auctions](https://mlsanity.com/paper/2609.40070/) (2026)
- [Rethinking Least-Core Computation in Contextual-Distractor Games](https://mlsanity.com/paper/2610.06087/) (2026)

## Abstract (arXiv)

We propose incentive-aligned mechanisms for in-context credit assignment: the task of assigning credit for AI-generated content among creators whose intellectual property appears in the context window. Our approach is based on the least core solution concept from cooperative game theory, which distributes value in a way that is as stable as possible by ensuring that no subset of creators is significantly under-compensated relative to the value they could generate on their own. We develop algorithms for approximating the least core, which leverage novel routines for constraint seeding and constraint separation. On a web retrieval credit assignment task, we find that our approaches approximate the least core using an order of magnitude fewer LLM calls compared to alternative methods.