SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.03417 · NeurIPS · 2024

Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 Experiment

Nihar Shah, Isabelle Guyon, Zhen Xu, Alexander Goldberg, Ihsan Ullah, Thanh Gia, Hieu Khuong, Kent Rachmat

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ihsaan-ullah/neurips-checklist-assistant canonical 0 of 6
FunctionStatusWhere it lives
clean Not yet run ihsaan-ullah/neurips-checklist-assistant/CheckPaperFormat/check_paper_format.py
code served (permissive licence) · get_code("231eeb3c0401afe1")
clean_paper Not yet run ihsaan-ullah/neurips-checklist-assistant/CheckPaperFormat/check_paper_format.py
code served (permissive licence) · get_code("61725cb61c0b533a")
clean_title Not yet run ihsaan-ullah/neurips-checklist-assistant/CheckPaperFormat/check_paper_format.py
code served (permissive licence) · get_code("6683daa7f5a711d1")
extract_checklist Not yet run ihsaan-ullah/neurips-checklist-assistant/AssistantAnalysis/annotate_responses_public.py
code served (permissive licence) · get_code("4de4b37bc6a31ca7")
extract_paper_parse Not yet run ihsaan-ullah/neurips-checklist-assistant/AssistantAnalysis/annotate_responses_public.py
code served (permissive licence) · get_code("5d35a2c7da58137c")
q_to_file Not yet run ihsaan-ullah/neurips-checklist-assistant/AssistantAnalysis/annotate_responses_public.py
code served (permissive licence) · get_code("d4d0d87078a34d26")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) represent a promising, but controversial, tool in aiding scientific peer review. This study evaluates the usefulness of LLMs in a conference setting as a tool for vetting paper submissions against submission standards. We conduct an experiment at the 2024 Neural Information Processing Systems (NeurIPS) conference, where 234 papers were voluntarily submitted to an "LLMbased Checklist Assistant." This assistant validates whether papers adhere to the author checklist used by NeurIPS, which includes questions to ensure compliance with research and manuscript preparation standards. Evaluation of the assistant by NeurIPS paper authors suggests that the LLM-based assistant was generally helpful in verifying checklist completion. In post-usage surveys, over 70% of authors found the assistant useful, and 70% indicate that they would revise their papers or checklist responses based on its feedback. While causal attribution to the assistant is not definitive, qualitative evidence suggests that the LLM contributed to improving some submissions. Survey responses and analysis of resubmissions indicate that authors made substantive revisions to their submissions in response to specific feedback from the LLM. The experiment also highlights common issues with LLMs-inaccuracy (20/52) and excessive strictness (14/52) were the most frequent issues flagged by authors. We also conduct experiments to understand potential gaming of the system, which reveal that the assistant could be manipulated to enhance scores through fabricated justifications, highlighting potential vulnerabilities of automated review tools.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2411.03417")
get_code_for_paper("2411.03417")
have("2411.03417")

Connect an agent — have() is free.