arXiv:2607. 16451v1 Announce Type: cross Abstract: Chat models sometimes commit to an answer and then produce reasoning that justifies it rather than deriving it -- even when the answer contradicts a task premise.
arXiv:2606. 30128v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting improves LLM reasoning, but the source is contested: do the intermediate steps help because they carry useful semantic content, or because conditioning on more tokens buys extra computation before the model commits to an answer?
arXiv:2606. 29490v1 Announce Type: cross Abstract: Confidence is an estimate of the probability that a chosen answer is correct.
arXiv:2606. 25013v1 Announce Type: new Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts.
arXiv:2606. 26502v1 Announce Type: new Abstract: Large reasoning models (LRMs) take longer on harder problems, just as humans do.
arXiv:2607. 08059v1 Announce Type: cross Abstract: Uncertainty quantification for visual language models (VLMs) conventionally targets the answer token distribution.
arXiv:2603. 29025v3 Announce Type: replace-cross Abstract: Large language models fail when a salient surface cue conflicts with an unstated feasibility constraint.
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items.
arXiv:2608. 15022v1 Announce Type: new Abstract: Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly.
arXiv:2607. 28814v1 Announce Type: cross Abstract: In Motivational Interviewing (MI), a client's sustain talk (arguments for the status quo) calls for the counselor to roll with resistance, a move that can fail in two opposite ways: capitulation (abandoning the change agenda to preserve rapport) or confrontation (arguing or directing, overriding the client's autonomy).
arXiv:2608. 05687v1 Announce Type: cross Abstract: Masked diffusion language models (dLLMs) can commit tokens in any order -- a freedom marketed as their core advantage over autoregressive decoding.
arXiv:2607. 09786v1 Announce Type: new Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer.