Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Statistical Frontiers in LLMs and Foundation Models

Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks

Zizhang Chen · Pengyu Hong · Sandeep Madireddy

Keywords: [ LLM ] [ Uncertainty Quantifficationm AI4Chemistry ]

[ ] [ Project Page ]
Sat 14 Dec 3:45 p.m. PST — 4:30 p.m. PST

Abstract:

Uncertainty quantification enables users to assess the reliability of responses generated by large language models (LLMs). We present a novel Question Rephrasing technique to evaluate the input uncertainty of LLMs, which refers to the uncertainty arising from equivalent variations of the inputs provided to LLMs. This technique is integrated with sampling methods that measure the output uncertainty of LLMs, thereby offering a more comprehensive uncertainty assessment. We validated our approach to property prediction and reaction prediction for molecular chemistry tasks.

Chat is not available.