Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues that limit their reliable deployment. In this work, we show that reasoning trace length is a simple and useful confidence estimator in large reasoning models. Through comprehensive experiments across multiple models, datasets, and prompts, we show that trace length performs in comparable but complementary ways to other zero-shot confidence estimators such as verbalized confidence. Our work reveals that reasoning post-training fundamentally alters the relationship between trace… Read More
Trace Length is a Simple Uncertainty Signal in Reasoning Models
Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues that limit their reliable deployment. In this work, we show that reasoning trace length is a simple and useful confidence estimator in large reasoning models. Through comprehensive experiments across multiple models, datasets, and prompts, we show that trace length performs in comparable but complementary ways to other zero-shot confidence estimators such as verbalized confidence. Our work reveals that reasoning post-training fundamentally alters the relationship between trace…
Related Posts
7 Advanced Feature Engineering Tricks for Text Data Using LLM Embeddings
Large language models (LLMs) are not only good at understanding and generating text; they can…
CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching
Conditional generative modeling aims to learn a conditional data distribution from samples containing data-condition pairs.…
10 Python One-Liners for Calling LLMs from Your Code
You don’t always need a heavy wrapper, a big client class, or dozens of lines…