文本生成:关于任务、评估与挑战的系统文献综述
Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges
AI总结:
该系统综述梳理2017-2025年257篇论文,划分文本生成五大任务,评估三类方法,指出任务特有与共有的9项挑战,为NLP领域不同阶段研究者提供领域概览与研究方向参考。
摘要:
文本生成已变得比以往任何时候都更容易获取,对这些系统(尤其是使用大型语言模型的系统)日益增长的兴趣,推动了相关出版物的激增。我们提供了一篇涵盖257篇论文的系统文献综述,覆盖2017年1月至2025年12月这一时期。本综述将文本生成的研究贡献分为五大任务:开放式文本生成、摘要生成、翻译、 paraphrasing( paraphrasing 即复述)以及问答。对于我们分类体系中的每个任务,我们都回顾了相关特征与关键子任务。我们评估了当前用于评估文本生成系统的方法,涵盖无模型评估、基于模型的评估以及人工评估。我们的研究揭示了若干特定于任务的挑战(例如,多文档摘要生成缺少数据集、故事生成缺乏连贯性,以及问答中复杂推理的困难)。我们进一步讨论了近期文本生成论文中所有任务及子任务共有的9项挑战:偏差、推理、幻觉、滥用、隐私、可解释性、透明度、数据集与计算。本系统文献综述面向两类主要受众:寻求该领域概述与有前景研究方向的自然语言处理领域早期研究人员,以及需要了解主要任务、评估、挑战及缓解策略最新概述的资深研究人员。
英文摘要:
Text generation has become more accessible than ever, and the growing interest in these systems, especially those using large language models, has spurred a surge in related publications. We provide a systematic literature review comprising 257 papers, covering the period from January 2017 to December 2025. This review categorizes text generation contributions into five main tasks: open-ended text generation, summarization, translation, paraphrasing, and question answering. For each task in our taxonomy, we review relevant characteristics and key subtasks. We assess current approaches for evaluating text generation systems, covering model-free, model-based, and human evaluation. Our investigation shows several task-specific challenges (e.g., missing datasets for multi-document summarization, lack of coherence in story generation, and difficulties in complex reasoning for question answering). We further discuss nine challenges common to all tasks and sub-tasks in recent text generation papers: bias, reasoning, hallucinations, misuse, privacy, interpretability, transparency, datasets, and computing. This systematic literature review targets two main audiences: early-career researchers in natural language processing seeking an overview of the field and promising research directions, and senior researchers who need a recent overview of the main tasks, evaluation, challenges, and mitigation strategies.
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。