跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 07:46 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 08:47 — 2026-11-20 08:47(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 07:46最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

27,982 已收录论文23,249 AI 相关8,559 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 07:44(北京时间)
版本更新 · v4arXiv:2607.18553

循环语言模型中的操作性原初内省:在答案之前读取正确性

Operational Proto-Introspection in Looped Language Models: Reading Correctness Before the Answer

Jan Kirin

AI 速读 基于摘要

作者在循环语言模型 Ouro-RLTT 的隐藏状态上训练探针,发现其能在推理早期部分预测答案正确性,但该信号与问题难度等基线相比优势有限,且无法用于改进生成。

cs.LG · cs.AI

查看原文摘要

Can one tell, while a language model reasons, whether its answer will be right? Looped models are a good place to ask: they run the same layers several times per token, leaving one hidden state per loop for a probe to read. I probe Ouro-RLTT, a 2.6B-parameter looped model, for what these states reveal about how its reasoning will end. I call such information operational proto-introspection: operational because it is defined by what a probe can read, and proto because nothing here shows that the model itself uses it. In part, yes. Reading the first 48 tokens of reasoning, from answers that state no answer yet, a probe on the hidden states reaches an AUROC of 0.758 on a synthetic logic task, against 0.515 for token confidence. Question difficulty is a rival explanation: on 1,164 further questions, token confidence plus simple features of the question predict about as well. It is not only difficulty: between two answers to the same question, the probe scores the correct one higher 74% of the time. A fine-tuned language model reading the same tokens does about as well. On GSM8K and on a second checkpoint this within-question test is unresolved. A probe that ranks finished candidate answers is weak at layer 8 on the first loop, much better on the second, and as accurate as the last layers by the third, on four Ouro checkpoints. The direction it reads is largely shared across loops: a probe trained on the last loop reads the first nearly as well as a probe trained there. The signal helps decide what to do with finished outputs. It improves abstention over surface features and picks correct answers among candidates better than chance, though surface features pick about as well. Once several samples are finished, a baseline that knows their agreement leaves the answer-free probe nothing measurable to add. None of my attempts to use it to make the model generate better answers worked.

版本更新 · v3arXiv:2604.09870

Reading Human Preference from Looped Transformer Internal States

Jan Kirin

原文摘要

Show a frozen language model two replies to the same request, one of which a person preferred. Can a small probe on the model's hidden states tell which? On Ouro-2.6B-Thinking, a model that runs its layers four times per token, and Anthropic's HH-RLHF data, the answer is yes, but only faintly. A linear probe picks the preferred reply 61.5% of the time, a small nonlinear network that scores each reply separately 64.9%, and the evaluator trained for version 1 reaches 64.7% on the test split: clearly better than simple rules such as picking the longer reply, but weak. Whether preference is stored as a comparison between the two replies or as a property of each is still open. A linear probe cannot tell, and a network that reads both replies together has an estimated edge of only 0.7 points (95% CI 0.0 to 1.4) over one that scores each reply separately. These numbers hold under three controls: scoring every pair in both orders, splitting the data by pair, and, for the probes, keeping the end of each conversation, where the two replies differ. Version 1's 95.2% and 84.5% were obtained without the first two and do not hold; version 2's corrected relational-probe accuracy, obtained without the third, was four to five points too low. This version replaces both.

cs.LG · cs.AI