Facets, Taxonomies, and Syntheses: Navigating Structured Representations in LLM-Assisted Literature Review
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908337758535680 |
|---|---|
| author | Fok, Raymond Chang, Joseph Chee Radensky, Marissa Siangliulue, Pao Bragg, Jonathan Zhang, Amy X. Weld, Daniel S. |
| author_facet | Fok, Raymond Chang, Joseph Chee Radensky, Marissa Siangliulue, Pao Bragg, Jonathan Zhang, Amy X. Weld, Daniel S. |
| contents | Comprehensive literature review requires synthesizing vast amounts of research -- a labor intensive and cognitively demanding process. Most prior work focuses either on helping researchers deeply understand a few papers (e.g., for triaging or reading), or retrieving from and visualizing a vast corpus. Deep analysis and synthesis of large paper collections (e.g., to produce a survey paper) is largely conducted manually with little support. We present DimInd, an interactive system that scaffolds literature review across large paper collections through LLM-generated structured representations. DimInd scaffolds literature understanding with multiple levels of compression, from papers, to faceted literature comparison tables with information extracted from individual papers, to taxonomies of concepts, to narrative syntheses. Users are guided through these successive information transformations while maintaining provenance to source text. In an evaluation with 23 researchers, DimInd supported participants in extracting information and conceptually organizing papers with less effort compared to a ChatGPT-assisted baseline workflow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18496 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Facets, Taxonomies, and Syntheses: Navigating Structured Representations in LLM-Assisted Literature Review Fok, Raymond Chang, Joseph Chee Radensky, Marissa Siangliulue, Pao Bragg, Jonathan Zhang, Amy X. Weld, Daniel S. Human-Computer Interaction Comprehensive literature review requires synthesizing vast amounts of research -- a labor intensive and cognitively demanding process. Most prior work focuses either on helping researchers deeply understand a few papers (e.g., for triaging or reading), or retrieving from and visualizing a vast corpus. Deep analysis and synthesis of large paper collections (e.g., to produce a survey paper) is largely conducted manually with little support. We present DimInd, an interactive system that scaffolds literature review across large paper collections through LLM-generated structured representations. DimInd scaffolds literature understanding with multiple levels of compression, from papers, to faceted literature comparison tables with information extracted from individual papers, to taxonomies of concepts, to narrative syntheses. Users are guided through these successive information transformations while maintaining provenance to source text. In an evaluation with 23 researchers, DimInd supported participants in extracting information and conceptually organizing papers with less effort compared to a ChatGPT-assisted baseline workflow. |
| title | Facets, Taxonomies, and Syntheses: Navigating Structured Representations in LLM-Assisted Literature Review |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2504.18496 |