Research map / Large language models / AI and society
ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Train the GCN summarizer on the 1,000-example ScisummNet corpus instead of the 30-example CL-SciSumm corpus | GCN Cited text spans · CL-SciSumm Test | ROUGE-3 F1: 12.77 -> 17.86 | Helped |
| Augment the abstract with salient cited text spans (Hybrid 2) | GCN summarization · CL-SciSumm 2016 test | ROUGE-2 F1: 29.40 -> 30.08 | Helped |
| Augment the abstract with salient cited text spans rather than summarize the union (Hybrid 1) | GCN hybrid summarization · CL-SciSumm 2016 test | ROUGE-2 F1: 27.96 -> 30.08 | Helped |
| Add the authority feature to Hybrid 2 (ablation) | GCN Hybrid 2 · CL-SciSumm 2016 test | ROUGE-2 F1: 30.08 -> 31.54 | Helped |
| Add the authority feature to Hybrid 1 (ablation) | GCN Hybrid 1 · CL-SciSumm 2016 test | ROUGE-2 F1: 27.96 -> 28.05 | Helped |
| Combine abstract content and cited text spans rather than use cited text spans alone | GCN hybrid summarization · CL-SciSumm 2016 test | ROUGE-2 F1: 24.26 -> 30.08 | Helped |
Closest papers by meaning
- HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction (NeurIPS 2024 · similarity 0.88)
- PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models (NeurIPS 2024 · similarity 0.86)
- BooookScore: A systematic exploration of book-length summarization in the era of LLMs (ICLR 2024 · similarity 0.84)
- From Words to Worth: Newborn Article Impact Prediction with LLM (AAAI 2025 · similarity 0.84)
- Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization (AAAI 2025 · similarity 0.83)
- Language Models of Code Are Few-Shot Planners and Reasoners for Multi-Document Summarization with Attribution (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.