To Err is AI : A Case Study Informing LLM Flaw Reporting Practices

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 bountie...

Full description

Saved in:

Bibliographic Details
Main Authors:	McGregor, Sean, Ettinger, Allyson, Judd, Nick, Albee, Paul, Jiang, Liwei, Rao, Kavel, Smith, Will, Longpre, Shayne, Ghosh, Avijit, Fiorelli, Christopher, Hoang, Michelle, Cattell, Sven, Dziri, Nouha
Format:	Journal Article
Language:	English
Published:	15-10-2024
Subjects:	Computer Science - Computers and Society Computer Science - Learning Computer Science - Software Engineering
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
DOI:	10.48550/arxiv.2410.12104