ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses
This addresses the challenge of ensuring accurate and responsible research reporting for NLP conference authors, though it is incremental as it builds on existing RAG and LLM methods.
The authors tackled the problem of inaccurate self-reported conference checklist responses by introducing ConfReady, a RAG-based assistant that helps authors reflect on their work and complete checklists, and curated a dataset of 1,975 ACL checklist responses to benchmark RAG and LLM systems.
The ARR Responsible NLP Research checklist website states that the "checklist is designed to encourage best practices for responsible research, addressing issues of research ethics, societal impact and reproducibility." Answering the questions is an opportunity for authors to reflect on their work and make sure any shared scientific assets follow best practices. Ideally, considering a checklist before submission can favorably impact the writing of a research paper. However, previous research has shown that self-reported checklist responses don't always accurately represent papers. In this work, we introduce ConfReady, a retrieval-augmented generation (RAG) application that can be used to empower authors to reflect on their work and assist authors with conference checklists. To evaluate checklist assistants, we curate a dataset of 1,975 ACL checklist responses, analyze problems in human answers, and benchmark RAG and Large Language Model (LM) based systems on an evaluation subset. Our code is released under the AGPL-3.0 license on GitHub, with documentation covering the user interface and PyPI package.