AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Xiaotian, Li, Jiyi, Takeuchi, Koh, Kashima, Hisashi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929523906314240
author Lu, Xiaotian
Li, Jiyi
Takeuchi, Koh
Kashima, Hisashi
author_facet Lu, Xiaotian
Li, Jiyi
Takeuchi, Koh
Kashima, Hisashi
contents Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlike close-ended questions with definitive answers. While large language models (LLMs) have demonstrated strong capabilities across various tasks, they exhibit relatively weaker performance in evaluating answers to open-ended questions. In this study, we propose a method that leverages LLMs and the analytic hierarchy process (AHP) to assess answers to open-ended questions. We utilized LLMs to generate multiple evaluation criteria for a question. Subsequently, answers were subjected to pairwise comparisons under each criterion with LLMs, and scores for each answer were calculated in the AHP. We conducted experiments on four datasets using both ChatGPT-3.5-turbo and GPT-4. Our results indicate that our approach more closely aligns with human judgment compared to the four baselines. Additionally, we explored the impact of the number of criteria, variations in models, and differences in datasets on the results.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01246
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses
Lu, Xiaotian
Li, Jiyi
Takeuchi, Koh
Kashima, Hisashi
Computation and Language
Artificial Intelligence
Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlike close-ended questions with definitive answers. While large language models (LLMs) have demonstrated strong capabilities across various tasks, they exhibit relatively weaker performance in evaluating answers to open-ended questions. In this study, we propose a method that leverages LLMs and the analytic hierarchy process (AHP) to assess answers to open-ended questions. We utilized LLMs to generate multiple evaluation criteria for a question. Subsequently, answers were subjected to pairwise comparisons under each criterion with LLMs, and scores for each answer were calculated in the AHP. We conducted experiments on four datasets using both ChatGPT-3.5-turbo and GPT-4. Our results indicate that our approach more closely aligns with human judgment compared to the four baselines. Additionally, we explored the impact of the number of criteria, variations in models, and differences in datasets on the results.
title AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.01246