Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks

التفاصيل البيبلوغرافية
العنوان: Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks
المؤلفون: Chen, Zizhang, Hong, Pengyu, Madireddy, Sandeep
سنة النشر: 2024
المجموعة: Computer Science
Quantitative Biology
مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Machine Learning, Quantitative Biology - Quantitative Methods
الوصف: 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 on property prediction and reaction prediction for molecular chemistry tasks.
نوع الوثيقة: Working Paper
URL الوصول: http://arxiv.org/abs/2408.03732
رقم الأكسشن: edsarx.2408.03732
قاعدة البيانات: arXiv