Skip to main navigation Skip to search Skip to main content

Evaluating the Performance of Complex Text Generated by Large Language Models

  • Fenglin Bi
  • , Yantong Wang
  • , Fanyu Han
  • , Zhi Li
  • , Tao Hu
  • , Yanbin Zhang
  • , Wei Wang*
  • *Corresponding author for this work
  • East China Normal University
  • ByteDance Ltd.

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The rapid advancement of Large Language Models (LLMs) has significantly enhanced text generation quality in Natural Language Processing (NLP). However, practical applications impose complex requirements, particularly in fields such as generating analysis reports. This study systematically reviews evaluation methods for LLMs and proposes a general framework for complex text generation, encompassing Generation Content, Prompt Dimension, Retrieval-Augmented Generation (RAG), and LLM Fine-tuning. We first introduce the Complex Text Generation Task Evaluation Paradigm. Based on this paradigm, we identify 15 sub-indicators with corresponding evaluation methods to comprehensively assess and improve LLM performance. Our research fills gaps in existing evaluation systems and provides a scalable framework for future studies, enhancing the applicability and impact of LLMs across various domains.

Original languageEnglish
Title of host publicationIntelligent Computers, Algorithms, and Applications - 4th BenchCouncil International Symposium, IC 2024, Revised Selected Papers
EditorsChunjie Luo, Weiping Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages151-167
Number of pages17
ISBN (Print)9789819663095
DOIs
StatePublished - 2025
Event4th BenchCouncil International Symposium on Intelligent Computers, Algorithms, and Applications, IC 2024 - Guangzhou, China
Duration: 4 Dec 20246 Dec 2024

Publication series

NameCommunications in Computer and Information Science
Volume2517 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference4th BenchCouncil International Symposium on Intelligent Computers, Algorithms, and Applications, IC 2024
Country/TerritoryChina
CityGuangzhou
Period4/12/246/12/24

Keywords

  • Complex Text Generation
  • Controllable Text Generation
  • Large Language Models
  • Natural Language Processing

Fingerprint

Dive into the research topics of 'Evaluating the Performance of Complex Text Generated by Large Language Models'. Together they form a unique fingerprint.

Cite this