paper-with-me

홈 › Papers

Temporal Predictors of Outcome in Reasoning Language Models

2025-11-03 · Joey David arxiv

The chain-of-thought (CoT) paradigm uses the elicitation of step-by-step rationales as a proxy for reasoning, gradually refining the model's latent representation of a solution. However, it remains unclear just how early a Large Language Model (LLM) internally commits to an eventual outcome. We probe this by training linear classifiers on hidden states after the first t reasoning tokens, showing that eventual correctness is highly predictable after only a few tokens, even when longer outputs are needed to reach a definite answer. We show that, for harder questions, a drop in predictive accuracy highlights a selection artifact: hard items are disproportionately represented in long CoTs. Overall, our results imply that for reasoning models, internal self-assessment of success tends to emerge after only a few tokens, with implications for interpretability and for inference-time control.

📄 PDF Abstract BibTeX arXiv:2511.14773

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

TempoBench: Evaluating Temporal Causal Reasoning in Large Language Models

2025-10-31 · Nikolaus Holzer, William Fishell, Baishakhi Ray, Mark Santolucito arxiv

Temporal reasoning involves understanding how systems evolve over time through input-driven state transitions. A key aspect is temporal causal reasoning, causally reasoning about what prior inputs were necessary in causi…

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

2026-03-23 · Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan 외 arxiv

Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temp…

Trajectory PredictionGeneral Knowledge

DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining

2026-04-24 · Youze Zheng, Jianyou Wang, Yuhan Chen, Matthew Feng 외 arxiv

Predicting the outcomes of prospective clinical trials remains a major challenge for large language models. Prior work has shown that both traditional correlational predictors, such as random forests and logistic regress…

Reinforcement Learning

TimeThink: Reasoning with Time for Video LLMs

2026-07-06 · Handong Li, Longteng Guo, Zikang Liu, Dongze Hao 외 arxiv

Video reasoning requires models to identify and verify temporally localized evidence within long video sequences. Recent Video Large Language Models (Video-LLMs) have shown promising reasoning abilities when aligned with…

Reinforcement Learning

Rationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Models

2026-01-06 · Qingxiang Liu, Zhiqing Cui, Xiaoliang Luo, Yuqian Wu 외 arxiv

The underperformance of existing multimodal large language models for time series reasoning lies in the absence of rationale priors that connect temporal observations to their downstream outcomes, which leads models to r…