The Attribution Contract: Feature Attribution for Generative Language Models

• URL: http://arxiv.org/abs/2605.23080v1
• Date: Thu, 21 May 2026 22:27:04 GMT
• Title: The Attribution Contract: Feature Attribution for Generative Language Models
• Abstract summary: Feature attribution methods promise to identify which input features matter for a model output.<n>It is often unclear what should count as a feature in the first place in generative language models.<n>We introduce the Attribution Contract, a specification for feature-attribution claims.
• Score: 1.6001421987996292
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often unclear what should count as a feature in the first place. In autoregressive language models, earlier generated tokens are both outputs of the model and inputs to later predictions. In diffusion language models, generation proceeds through iterative denoising or unmasking rather than fixed left-to-right prediction, so local explanation may target a state of diffusion rather than a next token. We argue that this ambiguity is not merely an implementation detail, but a conceptual limitation of carrying classifier-era feature attribution directly into generative language modeling. We introduce the Attribution Contract, a specification for feature-attribution claims that names what output is being explained, which features are eligible to receive attribution, what generative process is assumed, what is held fixed, and what model score is being attributed. The contract clarifies why the same attribution method can answer different questions depending on how it is instantiated. We argue that many disagreements about feature attribution in generative language models are not disagreements about attribution algorithms, but about unstated explanatory contracts. Using autoregressive and diffusion language models as case studies, we show when attribution to earlier generated tokens, intermediate states, or denoising stages is informative, when it is misleading, and why feature-attribution methods in generative language models should be evaluated as method-contract pairs.

Related papers

• A Variational Framework for Improving Naturalness in Generative Spoken Language Models [52.673912922590866]
  We propose an end-to-end variational approach that automatically learns to encode continuous speech attributes to enhance semantic tokens.<n>Our approach eliminates the need for manual extraction and selection of paralinguistic features.<n>It produces preferred speech continuations according to human raters.
  arXiv  Detail & Related papers  (2025-06-17T17:58:17Z)
• Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning [29.745218855471787]
  Tokenization is a necessary component within the current architecture of many language mod-els.<n>We argue that tokenization is necessary for reasonably human-like language performance.<n>We discuss implications for architectural choices, meaning construction, the primacy of language for thought.
  arXiv  Detail & Related papers  (2024-12-14T18:18:52Z)
• Gumbel Counterfactual Generation From Language Models [64.55296662926919]
  We show that counterfactual reasoning is conceptually distinct from interventions.<n>We propose a framework for generating true string counterfactuals.<n>We show that the approach produces meaningful counterfactuals while at the same time showing that commonly used intervention techniques have considerable undesired side effects.
  arXiv  Detail & Related papers  (2024-11-11T17:57:30Z)
• Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models [6.394084132117747]
  We propose a technique that leverages counterfactual generation to evaluate the faithfulness of attribution methods for autoregressive language models.<n>Our technique generates fluent, in-distribution counterfactuals, making the evaluation protocol more reliable.
  arXiv  Detail & Related papers  (2024-08-21T00:17:59Z)
• Unifying Corroborative and Contributive Attributions in Large Language Models [11.376900121298517]
  We argue for and present a unified framework of large language model attributions. We show how existing methods of different types of attribution fall under the unified framework. We believe that this unified framework will guide the use case driven development of systems that leverage both types of attribution, as well as the standardization of their evaluation.
  arXiv  Detail & Related papers  (2023-11-20T23:17:20Z)
• PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model [37.2192243883707]
  We propose PLANNER, a model that combines latent semantic diffusion with autoregressive generation to generate fluent text. Results on semantic generation, text completion and summarization show its effectiveness in generating high-quality long-form text.
  arXiv  Detail & Related papers  (2023-06-05T01:36:39Z)
• Quark: Controllable Text Generation with Reinforced Unlearning [68.07749519374089]
  Large-scale language models often learn behaviors that are misaligned with user expectations. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property. For unlearning toxicity, negative sentiment, and repetition, our experiments show that Quark outperforms both strong baselines and state-of-the-art reinforcement learning methods.
  arXiv  Detail & Related papers  (2022-05-26T21:11:51Z)
• Interpreting Language Models with Contrastive Explanations [99.7035899290924]
  Language models must consider various features to predict a token, such as its part of speech, number, tense, or semantics. Existing explanation methods conflate evidence for all these features into a single explanation, which is less interpretable for human understanding. We show that contrastive explanations are quantifiably better than non-contrastive explanations in verifying major grammatical phenomena.
  arXiv  Detail & Related papers  (2022-02-21T18:32:24Z)
• Contrastive Explanations for Model Interpretability [77.92370750072831]
  We propose a methodology to produce contrastive explanations for classification models. Our method is based on projecting model representation to a latent space. Our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.
  arXiv  Detail & Related papers  (2021-03-02T00:36:45Z)
• Unnatural Language Inference [48.45003475966808]
  We find that state-of-the-art NLI models, such as RoBERTa and BART, are invariant to, and sometimes even perform better on, examples with randomly reordered words. Our findings call into question the idea that our natural language understanding models, and the tasks used for measuring their progress, genuinely require a human-like understanding of syntax.
  arXiv  Detail & Related papers  (2020-12-30T20:40:48Z)
• Limits of Detecting Text Generated by Large-Scale Language Models [65.46403462928319]
  Some consider large-scale language models that can generate long and coherent pieces of text as dangerous, since they may be used in misinformation campaigns. Here we formulate large-scale language model output detection as a hypothesis testing problem to classify text as genuine or generated.
  arXiv  Detail & Related papers  (2020-02-09T19:53:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.