FAIL: Analyzing Software Failures from the News Using LLMs

TL;DR

FAIL leverages large language models to automate the collection, grouping, and analysis of news-reported software failures, enabling large-scale insights into failure patterns, recurrence, and severity over time.

Contribution

This work introduces FAIL, an automated system that analyzes news reports of software failures using LLMs, filling the gap of manual, small-scale failure analysis methods.

Findings

LLMs can effectively identify and analyze software failure news articles.

High recurrence of similar failures occurs within and across organizations.

Software failure severity has increased over the past decade.

Abstract

Software failures inform engineering work, standards, regulations. For example, the Log4J vulnerability brought government and industry attention to evaluating and securing software supply chains. Accessing private engineering records is difficult, so failure analyses tend to use information reported by the news media. However, prior works in this direction have relied on manual analysis. That has limited the scale of their analyses. The community lacks automated support to enable such analyses to consider a wide range of news sources and incidents. In this paper, we propose the Failure Analysis Investigation with LLMs (FAIL) system to fill this gap. FAIL collects, analyzes, and summarizes software failures as reported in the news. FAIL groups articles that describe the same incidents. It then analyzes incidents using existing taxonomies for postmortems, faults, and system characteristics. To tune and evaluate FAIL, we followed the methods of prior works by manually analyzing 31 software failures. FAIL achieved an F1 score of 90% for collecting news about software failures, a V-measure of 0.98 for merging articles reporting on the same incident, and extracted 90% of the facts about failures. We then applied FAIL to a total of 137,427 news articles from 11 providers published between 2010 and 2022. FAIL identified and analyzed 2457 distinct failures reported across 4,184 articles. Our findings include: (1) current generation of large language models are capable of identifying news articles that describe failures, and analyzing them according to structured taxonomies; (2) high recurrences of similar failures within organizations and across organizations; and (3) severity of the consequences of software failures have increased over the past decade. The full FAIL database is available so that researchers, engineers, and policymakers can learn from a diversity of software failures.