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. We ask whether the model carries an internal estimate of how much response remains.
arXiv:2609.38149v1 Announce Type: new
Abstract: Transformer language models (LMs) are feed-forward: deep-layer representations are never fed back to shallower layers, and the only pathway for informa...
By Dor Tirosh, Ido Amos, Mor Geva
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:2609.13154v1 Announce Type: new
Abstract: Recent advances in large language models (LLMs) have made prompts increasingly large and complex. Techniques such as chain-of-thought reasoning (Wei et...
By Shamin Chokshi
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
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. Speculative decoding addresses this bottleneck by employing a lightweight draft model to propose multiple future tokens that are subsequently verified in parallel by a larger target model.