LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Eunsu, Suk, Juyoung, Kim, Seungone, Muennighoff, Niklas, Kim, Dongkwan, Oh, Alice
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908388742397952
author Kim, Eunsu
Suk, Juyoung
Kim, Seungone
Muennighoff, Niklas
Kim, Dongkwan
Oh, Alice
author_facet Kim, Eunsu
Suk, Juyoung
Kim, Seungone
Muennighoff, Niklas
Kim, Dongkwan
Oh, Alice
contents We introduce LLM-as-an-Interviewer, a novel paradigm for evaluating large language models (LLMs). This approach leverages multi-turn interactions where the LLM interviewer actively provides feedback on responses and poses follow-up questions to the evaluated LLM. At the start of the interview, the LLM interviewer dynamically modifies datasets to generate initial questions, mitigating data contamination. We apply the LLM-as-an-Interviewer framework to evaluate six models on the MATH and DepthQA tasks. Our results show that the framework effectively provides insights into LLM performance, including the quality of initial responses, adaptability to feedback, and ability to address follow-up queries like clarification or additional knowledge requests. The framework also addresses key limitations of conventional methods like LLM-as-a-Judge, including verbosity bias and inconsistency across runs. Finally, we propose the Interview Report, which aggregates insights from the interview process, providing examples and a comprehensive analysis of the LLM's strengths and weaknesses. This report offers a detailed snapshot of the model's real-world applicability. The code for our framework is publicly available at https://github.com/interview-eval/.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10424
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation
Kim, Eunsu
Suk, Juyoung
Kim, Seungone
Muennighoff, Niklas
Kim, Dongkwan
Oh, Alice
Computation and Language
Artificial Intelligence
We introduce LLM-as-an-Interviewer, a novel paradigm for evaluating large language models (LLMs). This approach leverages multi-turn interactions where the LLM interviewer actively provides feedback on responses and poses follow-up questions to the evaluated LLM. At the start of the interview, the LLM interviewer dynamically modifies datasets to generate initial questions, mitigating data contamination. We apply the LLM-as-an-Interviewer framework to evaluate six models on the MATH and DepthQA tasks. Our results show that the framework effectively provides insights into LLM performance, including the quality of initial responses, adaptability to feedback, and ability to address follow-up queries like clarification or additional knowledge requests. The framework also addresses key limitations of conventional methods like LLM-as-a-Judge, including verbosity bias and inconsistency across runs. Finally, we propose the Interview Report, which aggregates insights from the interview process, providing examples and a comprehensive analysis of the LLM's strengths and weaknesses. This report offers a detailed snapshot of the model's real-world applicability. The code for our framework is publicly available at https://github.com/interview-eval/.
title LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.10424