From Queries to Criteria: Understanding How Astronomers Evaluate LLMs

Alina Hyk, Kiera McCormick, Mian Zhong, Ioana Ciucă, Sanjib Sharma, John F Wu, J. E. G. Peek, Kartheik G. Iyer, Ziang Xiao, Anjalie Field

Keywords: Human-centered computing, AI for Science, LM Evaluation, LLM for Astronomy

TL;DR: We analyze and recommend evaluation criteria grounded in real Human-LLM interactions for exploring scientific literature.

Abstract: There is growing interest in leveraging LLMs to aid in astronomy and other scientific research, but benchmarks for LLM evaluation in general have not kept pace with the increasingly diverse ways that real people evaluate and use these models. In this study, we seek to improve evaluation procedures by building an understanding of how users evaluate LLMs. We focus on a particular use case: an LLM-powered retrieval-augmented generation bot for engaging with astronomical literature, which we deployed via Slack. Our inductive coding of 368 queries to the bot over four weeks and our follow-up interviews with 11 astronomers reveal how humans evaluated this system, including the types of questions asked and the criteria for judging responses. We synthesize our findings into concrete recommendations for building better benchmarks, which we then employ in constructing a sample benchmark for evaluating LLMs for astronomy. Overall, our work offers ways to improve LLM evaluation and ultimately usability, particularly for use in scientific research.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 893