The paper argues that feature attribution scores for generative language models lack a fixed meaning because each generated token is both output and input, leading to multiple distinct explanatory questions. It introduces the Attribution Contract framework, which explicitly defines the model score, fixed variables, target output, generation process, and eligible features, showing how these choices affect attribution outcomes. Experiments demonstrate that different contracts (e.g., local next-token vs. prompt-level) and model architectures (mixture-of-experts vs. masked-diffusion) yield markedly different attribution distributions, highlighting the need for careful contract specification.
By Giang Nguyen
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
By Kieran A. Murphy, Shameen Shrestha
arXiv:2609.34187v2 Announce Type: replace-cross
Abstract: The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they c...
By Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama, Parisa Suchdev, Kathryn Cramer, Elisabeth Kollrack
arXiv:2606. 11552v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation.
By Lexington Whalen, Yuki Ito, Ryo Sakamoto
arXiv:2606. 07537v1 Announce Type: cross Abstract: Large language models hallucinate--producing fluent, confident, factually wrong outputs--with a consistency that persists across generations and scales.
By Md. Rejaul Korim Sadi, Toufiqur Rahman Tasin, Golam Mostofa Naeem
arXiv:2607. 05316v1 Announce Type: cross Abstract: Large language models generate one token at a time, yet their responses show remarkably consistent length structure: step-by-step solutions converge in predictable token counts, retrievals stop after a few sentences, retractions extend responses by measurable amounts.
By Mohamed Amine Merzouk, Dmitri Carpov, Mirko Bronzi, Damiano Fornasiere, Adam Oberman
arXiv:2607. 18961v1 Announce Type: new Abstract: Large language models (LLMs) generate fluent text by incrementally predicting the next token from a prefix.
By Remo Pareschi
arXiv:2608.30315v1 Announce Type: new
Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lang...
By Junjie Yao, Liangkai Hang, Zhi-Qin John Xu
arXiv:2602.00612v3 Announce Type: replace
Abstract: Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages d...
By Yitong Zhang, Yongmin Li, Yuetong Liu, Jia Li, Xiaoran Jia, Zherui Li, Ge Li
arXiv:2608.29034v1 Announce Type: cross
Abstract: A wide range of methods have been proposed for interpreting language models, delivering important insights into their inner workings. However, differ...
By Zhang Enyan, R. Thomas McCoy
arXiv:2603.18908v5 Announce Type: replace
Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...
By Matt Gorbett, Suman Jana
The paper introduces Diffusion Layer Integrated Gradients (DLIG), a token attribution technique for diffusion language models that extends Integrated Gradients to any layer and denoising step. DLIG tracks how a model progressively commits to a self-generated or fixed completion for a prompt, and it satisfies the IG axioms of completeness, implementation invariance, linearity, and symmetry preservation. The method is lightweight and complements interventional analysis, and the authors apply it to tasks such as word-sense disambiguation, multi-hop graph reasoning, and sentence infilling to show how diffusion language models utilize inputs across positions, layers, and denoising steps.
By Darpan Aswal, C\'eline Hudelot