The Attribution Contract for Generative Language Models

[2605.23080] The Attribution Contract for Generative Language Models Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2605.23080 (cs) [Submitted on 21 May 2026 ( v1 ), last revised 26 Aug 2026 (this version, v3)] Title: The Attribution Contract for Generative Language Models Authors: Giang Nguyen View PDF HTML (experimental) Abstract: Feature attribution scores each part of an input by how much it explains a model's output. We argue that in generative language models these scores carry no fixed meaning. A classifier has a single output to explain, but a generative model produces its output token by token, and each generated token is both an output and an input, so explaining the output becomes several distinct questions. We support this claim by proposing the Attribution Contract, a framework that names the question a set of attribution scores answers. A contract specifies the model score being explained, what is held fixed, the target output, the generation process, and which features can receive attribution, choices that matter in practice. For example, eligible features decide what a score explains: under a local next-token contract, the model's own generated tokens receive $29\%$ of the attribution mass, comparable to the $25\%$ on the input question, and reading this as a prompt-level explanation is a mistake we name the self-attribution fallacy. The generative process also shapes feature attribution: on a mixture-of-experts model, Integrated Gradients completeness is unreliable, since recomputing expert routing along the attribution path leaves a large residual that holding the routing fixed substantially lowers, while a masked-diffusion model, which fixes its choices at generation, has a residual that instead decreases with more steps. These results show that Attribution Contracts should be carefully specified when proposing and evaluating attribution methods for generative language models, since the meaning and evaluation of an attribution depend on its explanatory setting. Comments: Preprint, 15 pages Subjects: Machine Learning (cs.LG) Cite as: arXiv:2605.23080 [cs.LG] (or arXiv:2605.23080v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2605.23080 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Giang Nguyen [ view email ] [v1] Thu, 21 May 2026 22:27:04 UTC (49 KB) [v2] Mon, 1 Jun 2026 07:17:20 UTC (49 KB) [v3] Wed, 26 Aug 2026 22:05:32 UTC (77 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2026-05 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• The Attribution Contract for Generative Language Models#677608
• Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs#1013597
• Understanding And Enhancing Diversity In Generative Models#354230
• DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation#192398
• h2oGPT: Democratizing Large Language Models#446540