Exploring Multi-Document Information Consolidation for Scientific Sentiment Summarization

arXiv:2402.18005v1 Announce Type: new
Abstract: Modern natural language generation systems with LLMs exhibit the capability to generate a plausible summary of multiple documents; however, it is uncertain if models truly possess the ability of information consolidation to generate summaries, especially on those source documents with opinionated information. To make scientific sentiment summarization more grounded, we hypothesize that in peer review human meta-reviewers follow a three-layer framework of sentiment consolidation to write meta-reviews and it represents the logic of summarizing scientific …

abstract arxiv capability consolidation cs.ai cs.cl document documents generate information language language generation llms modern multiple natural natural language natural language generation sentiment summarization summary systems type uncertain