Overview of the NTCIR-18 Automatic Evaluation of LLMs (AEOLLM) Task
This addresses the problem of limited and costly evaluation methods for LLMs in academia and industry, but it is incremental as it builds on existing automatic evaluation efforts.
The paper tackles the challenge of effectively evaluating large language models (LLMs) by proposing the NTCIR-18 AEOLLM task, which focuses on generative tasks and reference-free methods, resulting in 48 runs from 4 teams.
In this paper, we provide an overview of the NTCIR-18 Automatic Evaluation of LLMs (AEOLLM) task. As large language models (LLMs) grow popular in both academia and industry, how to effectively evaluate the capacity of LLMs becomes an increasingly critical but still challenging issue. Existing methods can be divided into two types: manual evaluation, which is expensive, and automatic evaluation, which faces many limitations including task format (the majority belong to multiple-choice questions) and evaluation criteria (occupied by reference-based metrics). To advance the innovation of automatic evaluation, we propose the AEOLLM task which focuses on generative tasks and encourages reference-free methods. Besides, we set up diverse subtasks such as dialogue generation, text expansion, summary generation and non-factoid question answering to comprehensively test different methods. This year, we received 48 runs from 4 teams in total. This paper will describe the background of the task, the data set, the evaluation measures and the evaluation results, respectively.