In August of 2024, 495 hackers generated evaluations in an open-ended bug bounty targeting the Open Language Model (OLMo) from The Allen Institute for AI. A vendor panel staffed by representatives of OLMo's safety program adjudicated changes to OLMo's documentation and awarded cash bounties to participants who successfully demonstrated a need for public disclosure clarifying the intent, capacities, and hazards of model deployment. This paper presents a collection of lessons learned, illustrative of flaw reporting best practices intended to reduce the likelihood of incidents and produce safer large language models (LLMs). These include best practices for safety reporting processes, their artifacts, and safety program staffing.
@article{arxiv.2410.12104,
title = {To Err is AI : A Case Study Informing LLM Flaw Reporting Practices},
author = {Sean McGregor and Allyson Ettinger and Nick Judd and Paul Albee and Liwei Jiang and Kavel Rao and Will Smith and Shayne Longpre and Avijit Ghosh and Christopher Fiorelli and Michelle Hoang and Sven Cattell and Nouha Dziri},
journal= {arXiv preprint arXiv:2410.12104},
year = {2024}
}