arXiv:2203.01769
공식 코드 · Papers with Code
PeerSum: A Peer Review Dataset for Abstractive Multi-document Summarization
원문 초록
We present PeerSum, a new MDS dataset using peer reviews of scientific publications. Our dataset differs from the existing MDS datasets in that our summaries (i.e., the meta-reviews) are highly abstractive and they are real summaries of the source documents (i.e., the reviews) and it also features disagreements among source documents. We found that current state-of-the-art MDS models struggle to generate high-quality summaries for PeerSum, offering new research opportunities.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GenerationPrograms: Fine-grained Attribution with Executable Programs
Improving Fairness of Large Language Models in Multi-document Summarization
Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization
Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization
Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches
Coverage-based Fairness in Multi-document Summarization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.