Saved in:
Bibliographic Details
Main Authors: Li, Ruosen, Li, Ruochen, Wang, Barry, Du, Xinya
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.13545
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909392235921408
author Li, Ruosen
Li, Ruochen
Wang, Barry
Du, Xinya
author_facet Li, Ruosen
Li, Ruochen
Wang, Barry
Du, Xinya
contents To evaluate Large Language Models (LLMs) for question answering (QA), traditional methods typically focus on assessing single-turn responses to given questions. However, this approach doesn't capture the dynamic nature of human-AI interactions, where humans actively seek information through conversation. Recent works in human-computer interaction (HCI) have employed human evaluators to conduct interactions and evaluations, but they are often prohibitively expensive and time-consuming to scale. We introduce an automatic evaluation framework IQA-EVAL to achieve Interactive Question Answering Evaluations, more specifically, we introduce a LLM-based Evaluation Agent (LEA) that can: (1) simulate human behaviors to generate interactions with IQA models; (2) automatically evaluate the generated interactions. Moreover, we propose assigning personas to LEAs to better simulate groups of real human evaluators. We show that: (1) our evaluation framework with GPT-4 (or Claude) as the backbone model achieves a high correlation with human evaluations on the IQA task; (2) assigning personas to LEA to better represent the crowd further significantly improves correlations. Finally, we use our automatic metric to evaluate five recent representative LLMs with over 1000 questions from complex and ambiguous question answering tasks, which comes with a substantial cost of $5k if evaluated by humans.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13545
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering
Li, Ruosen
Li, Ruochen
Wang, Barry
Du, Xinya
Computation and Language
To evaluate Large Language Models (LLMs) for question answering (QA), traditional methods typically focus on assessing single-turn responses to given questions. However, this approach doesn't capture the dynamic nature of human-AI interactions, where humans actively seek information through conversation. Recent works in human-computer interaction (HCI) have employed human evaluators to conduct interactions and evaluations, but they are often prohibitively expensive and time-consuming to scale. We introduce an automatic evaluation framework IQA-EVAL to achieve Interactive Question Answering Evaluations, more specifically, we introduce a LLM-based Evaluation Agent (LEA) that can: (1) simulate human behaviors to generate interactions with IQA models; (2) automatically evaluate the generated interactions. Moreover, we propose assigning personas to LEAs to better simulate groups of real human evaluators. We show that: (1) our evaluation framework with GPT-4 (or Claude) as the backbone model achieves a high correlation with human evaluations on the IQA task; (2) assigning personas to LEA to better represent the crowd further significantly improves correlations. Finally, we use our automatic metric to evaluate five recent representative LLMs with over 1000 questions from complex and ambiguous question answering tasks, which comes with a substantial cost of $5k if evaluated by humans.
title IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering
topic Computation and Language
url https://arxiv.org/abs/2408.13545