← Back to all news
arXiv Computation and Language By Yunxiang Mo, Donghao Zhao, Hejia Geng

Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal

Read the original on arXiv Computation and Language →

The paper investigates whether self-consensus—stopping a reasoning model when its partial trajectory’s answers agree—can safely reduce inference cost. A large sweep of 3,520 consensus rules on two models and three benchmarks failed to meet predefined safety criteria, while a boundary‑confidence control (DEER) succeeded. The study shows that agreement signals that an answer persists under a fixed probing procedure, not that reasoning has finished, leading to premature stops and missed corrections even when token savings are significant.

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 Computation and Language.

Related stories

arXiv Machine Learning
Sep 17

One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs

The paper investigates how multi‑agent large language models (LLMs) can correct each other’s mistakes, but also how peer pressure can overturn correct answers. It argues that a safeguard— a ‘brake’ that blocks harmful revisions while allowing beneficial ones— is essentially a correctness probe, and that models’ self‑knowledge (measured by AUROC 0.64–0.89) limits the effectiveness of such a brake. The authors find that even white‑box steering cannot break this ceiling, and that adding information before revision, rather than filtering after, is the more promising approach.

By Yibo Hu
llmsagents
More like this →
arXiv AI
Sep 4

It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories

The paper investigates whether large language models’ reasoning traces truly contain early, informative signals or merely reflect budget and difficulty confounds. Using a restart‑controlled truncation probe, the authors compare continuation success rates against from‑scratch restart curves across 178 problem‑model pairs, finding that only one case shows prefix‑limited success and that continuing a model’s own prefix generally outperforms restarting. A difficulty‑controlled test and two generation‑free analyses reveal that early internal signals do not carry outcome information beyond a problem‑difficulty baseline, underscoring the need for proper counterfactual controls.

By Yigit Utku Bulut
llms
More like this →