利用大语言模型进行自然语言生成评估：进展与挑战
Leveraging Large Language Models for NLG Evaluation: Advances and Challenges
AI总结：
本文综述LLMs在NLG评估中的应用，提出基于LLM评估指标的分类框架，比较各类方法优劣，并指出偏见、鲁棒性、领域适配与统一评估等挑战。
摘要：
在快速发展的自然语言生成（Natural Language Generation, NLG）评估领域，大语言模型（Large Language Models, LLMs）的引入为评估生成内容质量开辟了新途径，例如连贯性、创造性和上下文相关性。本文旨在全面概述利用LLMs进行NLG评估这一尚缺乏系统分析的新兴领域。我们提出了一套连贯的分类体系，用于组织现有基于LLM的评估指标，并提供一个结构化框架以理解和比较这些方法。我们的详细探讨包括批判性地评估各类基于LLM的方法，并比较它们在评估NLG输出时的优势与局限。通过讨论尚未解决的挑战，包括偏见、鲁棒性、领域特定性和统一评估，本文力求为研究人员提供洞见，并倡导更公平、更先进的NLG评估技术。
英文摘要：
In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This paper aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to understand and compare these methods. Our detailed exploration includes critically assessing various LLM-based methodologies, as well as comparing their strengths and limitations in evaluating NLG outputs. By discussing unresolved challenges, including bias, robustness, domain-specificity, and unified evaluation, this paper seeks to offer insights to researchers and advocate for fairer and more advanced NLG evaluation techniques.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
