Preprint Explores How Readily LLMs Serve as Fast Jev-Style Decision Models
An October 2026 arXiv preprint examines whether current LLMs can already output probability distributions over choices without training, matching or exceeding training-free…
More freedom.
More control.
The developments, the evidence, and why they matter.
202 stories
An October 2026 arXiv preprint examines whether current LLMs can already output probability distributions over choices without training, matching or exceeding training-free…
An October 2026 arXiv preprint by Saman Rahbar shows that similarity scores used to claim brain alignment or cross-lingual transfer can remain high even after the underlying…
An arXiv preprint dated 2026-10-03 introduces Weakly Aligned Spatiotemporal Pairs, a framework that treats cross-modal correspondence as an entropic Optimal Transport problem…
arXiv preprint models LLM reasoning as search over a directed acyclic graph and provides a unified analysis of on-policy self-distillation and supervised fine-tuning dynamics…
The October 2026 preprint examines inducing demographic personas from public behavioral data to steer LLMs for group-level survey response simulation, comparing alignment…
arXiv preprint shows that routing statistics across prompt, reasoning and response phases fail to improve mixed-precision quantization of expert FFN tensors over uniform…
arXiv preprint from October 15 2026 finds that how linearly readable a relation is in pretrained representations strongly predicts whether a new relabeled version of that…
arXiv preprint dated October 5 2026 proposes Approximate Pareto Optimality to learn shared aligner initializations that support few-shot adaptation to heterogeneous user…
A preprint submitted October 5 2026 explores if large language models exhibit anosognosia-like failure to recognize quantization-induced impairments in their computational…
arXiv preprint from 2026-10-10 shows that quantizing the recurrent state in linear-attention and state-space models triggers a scale-state feedback loop. Errors compound over…
arXiv preprint from October 12 2026 presents IND-Eval, a public benchmark emphasizing fine-resolution multivariate industrial time series. Evaluation of Chronos-2, TiRex-2 and…
An October 2026 arXiv preprint introduces DANGERLENS to examine whether models with matching refusal behavior can still differ in internal accessibility of dangerous concepts…