Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2305.14647 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916287845761024 |
|---|---|
| author | Zeng, Qi Sidhu, Mankeerat Blume, Ansel Chan, Hou Pong Wang, Lu Ji, Heng |
| author_facet | Zeng, Qi Sidhu, Mankeerat Blume, Ansel Chan, Hou Pong Wang, Lu Ji, Heng |
| contents | Opinions in scientific research papers can be divergent, leading to controversies among reviewers. However, most existing datasets for opinion summarization are centered around product reviews and assume that the analyzed opinions are non-controversial, failing to account for the variability seen in other contexts such as academic papers, political debates, or social media discussions. To address this gap, we propose the task of scientific opinion summarization, where research paper reviews are synthesized into meta-reviews. To facilitate this task, we introduce the ORSUM dataset covering 15,062 paper meta-reviews and 57,536 paper reviews from 47 conferences. Furthermore, we propose the Checklist-guided Iterative Introspection approach, which breaks down scientific opinion summarization into several stages, iteratively refining the summary under the guidance of questions from a checklist. Our experiments show that (1) human-written summaries do not always satisfy all necessary criteria such as depth of discussion, and identifying consensus and controversy for the specific domain, and (2) the combination of task decomposition and iterative self-refinement shows strong potential for enhancing the opinions and can be applied to other complex text generation using black-box LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_14647 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation Zeng, Qi Sidhu, Mankeerat Blume, Ansel Chan, Hou Pong Wang, Lu Ji, Heng Computation and Language Opinions in scientific research papers can be divergent, leading to controversies among reviewers. However, most existing datasets for opinion summarization are centered around product reviews and assume that the analyzed opinions are non-controversial, failing to account for the variability seen in other contexts such as academic papers, political debates, or social media discussions. To address this gap, we propose the task of scientific opinion summarization, where research paper reviews are synthesized into meta-reviews. To facilitate this task, we introduce the ORSUM dataset covering 15,062 paper meta-reviews and 57,536 paper reviews from 47 conferences. Furthermore, we propose the Checklist-guided Iterative Introspection approach, which breaks down scientific opinion summarization into several stages, iteratively refining the summary under the guidance of questions from a checklist. Our experiments show that (1) human-written summaries do not always satisfy all necessary criteria such as depth of discussion, and identifying consensus and controversy for the specific domain, and (2) the combination of task decomposition and iterative self-refinement shows strong potential for enhancing the opinions and can be applied to other complex text generation using black-box LLMs. |
| title | Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2305.14647 |