arXiv:2607. 20791v1 Announce Type: new Abstract: High-temperature sampling is one of the primary mechanisms for increasing diversity in LLMs.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
FLEET is a new method for text generation that adds a memory mechanism to large language models. It represents each generation as a sparse trajectory of high‑entropy states and uses these trajectories to compute per‑token utility scores that adjust the logits. Benchmarks show that FLEET matches the accuracy of repeated sampling while being three times faster and improving accuracy on complex coding tasks, all with minimal changes to existing pipelines.
The paper introduces Variance‑Calibrated Modulation (VCM), a training‑free pre‑decoding technique that reshapes language model probability distributions before truncation. VCM uses two dynamic mechanisms: a Contextual Searchlight via PMI to suppress stopwords and highlight context‑relevant tokens, and an Adaptive Self‑Debiasing that applies scale‑invariant penalization based on real‑time logit standard deviation. Experiments on open‑ended generation, factual QA, and mathematical reasoning show that VCM consistently reduces the likelihood trap, improving diversity, coherence, and reasoning accuracy with minimal computational cost.
arXiv:2609.24150v1 Announce Type: new Abstract: Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to generate multiple candidate tokens that are...
arXiv:2609.16450v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a promising parallel decoding paradigm as an alternative to autoregressive generation through iterative...
arXiv:2610.01687v1 Announce Type: cross Abstract: Test-time scaling often seeks better answers by sampling multiple responses from a frozen model, yet conventional temperature sampling generates ever...
arXiv:2609.39560v1 Announce Type: new Abstract: Sampling several responses and voting over their answers can improve a language model's accuracy, but repeated answers limit the benefit of additional...