用于Meta-Review生成的情感整合框架
A Sentiment Consolidation Framework for Meta-Review Generation
AI总结：
本文针对科学领域meta-review生成任务，提出三层情感整合框架及LLM提示方法，通过实验验证该框架优于简单指令提示。
摘要：
配备大型语言模型（LLMs）的现代自然语言生成系统展现出生成多文档合理摘要的能力；然而，尚不确定它们是否真正具备信息整合能力以生成摘要，尤其是在处理包含主观意见信息的文档时。我们聚焦于meta-review生成，这是科学领域的一种情感摘要形式。为使科学情感摘要更具依据，我们假设人类meta-review作者遵循三层情感整合框架来撰写meta-review。基于该框架，我们提出了用于LLMs生成meta-review的新型提示方法，以及评估生成meta-review质量的评估指标。我们的框架通过实证得到验证：与使用简单指令提示LLMs相比，基于该框架提示LLMs能生成更好的meta-review。
英文摘要：
Modern natural language generation systems with Large Language Models (LLMs) exhibit the capability to generate a plausible summary of multiple documents; however, it is uncertain if they truly possess the capability of information consolidation to generate summaries, especially on documents with opinionated information. We focus on meta-review generation, a form of sentiment summarisation for the scientific domain. To make scientific sentiment summarization more grounded, we hypothesize that human meta-reviewers follow a three-layer framework of sentiment consolidation to write meta-reviews. Based on the framework, we propose novel prompting methods for LLMs to generate meta-reviews and evaluation metrics to assess the quality of generated meta-reviews. Our framework is validated empirically as we find that prompting LLMs based on the framework -- compared with prompting them with simple instructions -- generates better meta-reviews.
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。
