Temporal Predictors of Outcome in Reasoning Language Models
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
TempoBench: Evaluating Temporal Causal Reasoning in Large Language Models
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
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 KnowledgeDeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining
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 LearningTimeThink: Reasoning with Time for Video LLMs
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 LearningRationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Models
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…