Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.12255 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914685143482368 |
|---|---|
| author | Martin-Boyle, Anna Tyagi, Aahan Hearst, Marti A. Kang, Dongyeop |
| author_facet | Martin-Boyle, Anna Tyagi, Aahan Hearst, Marti A. Kang, Dongyeop |
| contents | Numerous AI-assisted scholarly applications have been developed to aid different stages of the research process. We present an analysis of AI-assisted scholarly writing generated with ScholaCite, a tool we built that is designed for organizing literature and composing Related Work sections for academic papers. Our evaluation method focuses on the analysis of citation graphs to assess the structural complexity and inter-connectedness of citations in texts and involves a three-way comparison between (1) original human-written texts, (2) purely GPT-generated texts, and (3) human-AI collaborative texts. We find that GPT-4 can generate reasonable coarse-grained citation groupings to support human users in brainstorming, but fails to perform detailed synthesis of related works without human intervention. We suggest that future writing assistant tools should not be used to draft text independently of the human author. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12255 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition Martin-Boyle, Anna Tyagi, Aahan Hearst, Marti A. Kang, Dongyeop Computation and Language Numerous AI-assisted scholarly applications have been developed to aid different stages of the research process. We present an analysis of AI-assisted scholarly writing generated with ScholaCite, a tool we built that is designed for organizing literature and composing Related Work sections for academic papers. Our evaluation method focuses on the analysis of citation graphs to assess the structural complexity and inter-connectedness of citations in texts and involves a three-way comparison between (1) original human-written texts, (2) purely GPT-generated texts, and (3) human-AI collaborative texts. We find that GPT-4 can generate reasonable coarse-grained citation groupings to support human users in brainstorming, but fails to perform detailed synthesis of related works without human intervention. We suggest that future writing assistant tools should not be used to draft text independently of the human author. |
| title | Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.12255 |