Automated Focused Feedback Generation for Scientific Writing Assistance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chamoun, Eric, Schlichktrull, Michael, Vlachos, Andreas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917684306771968
author Chamoun, Eric
Schlichktrull, Michael
Vlachos, Andreas
author_facet Chamoun, Eric
Schlichktrull, Michael
Vlachos, Andreas
contents Scientific writing is a challenging task, particularly for novice researchers who often rely on feedback from experienced peers. Recent work has primarily focused on improving surface form and style rather than manuscript content. In this paper, we propose a novel task: automated focused feedback generation for scientific writing assistance. We present SWIF$^{2}$T: a Scientific WrIting Focused Feedback Tool. It is designed to generate specific, actionable and coherent comments, which identify weaknesses in a scientific paper and/or propose revisions to it. Our approach consists of four components - planner, investigator, reviewer and controller - leveraging multiple Large Language Models (LLMs) to implement them. We compile a dataset of 300 peer reviews citing weaknesses in scientific papers and conduct human evaluation. The results demonstrate the superiority in specificity, reading comprehension, and overall helpfulness of SWIF$^{2}$T's feedback compared to other approaches. In our analysis, we also identified cases where automatically generated reviews were judged better than human ones, suggesting opportunities for integration of AI-generated feedback in scientific writing.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20477
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automated Focused Feedback Generation for Scientific Writing Assistance
Chamoun, Eric
Schlichktrull, Michael
Vlachos, Andreas
Computation and Language
Scientific writing is a challenging task, particularly for novice researchers who often rely on feedback from experienced peers. Recent work has primarily focused on improving surface form and style rather than manuscript content. In this paper, we propose a novel task: automated focused feedback generation for scientific writing assistance. We present SWIF$^{2}$T: a Scientific WrIting Focused Feedback Tool. It is designed to generate specific, actionable and coherent comments, which identify weaknesses in a scientific paper and/or propose revisions to it. Our approach consists of four components - planner, investigator, reviewer and controller - leveraging multiple Large Language Models (LLMs) to implement them. We compile a dataset of 300 peer reviews citing weaknesses in scientific papers and conduct human evaluation. The results demonstrate the superiority in specificity, reading comprehension, and overall helpfulness of SWIF$^{2}$T's feedback compared to other approaches. In our analysis, we also identified cases where automatically generated reviews were judged better than human ones, suggesting opportunities for integration of AI-generated feedback in scientific writing.
title Automated Focused Feedback Generation for Scientific Writing Assistance
topic Computation and Language
url https://arxiv.org/abs/2405.20477