Amazon conducted the test earlier this year for Australia's corporate regulator the Securities and Investments Commission (ASIC) using submissions made to an inquiry.
The test involved testing generative AI models before selecting one to ingest five submissions from a parliamentary inquiry into audit and consultancy firms. The most promising model, Meta's open source model Llama2-70B, was prompted to summarise the submissions with a focus on ASIC mentions, recommendations, references to more regulation, and to include the page references and context.
Ten ASIC staff, of varying levels of seniority, were also given the same task with similar prompts. Then, a group of reviewers blindly assessed the summaries produced by both humans and AI for coherency, length, ASIC references, regulation references and for identifying recommendations. They were unaware that this exercise involved AI at all.
These reviewers overwhelmingly found that the human summaries beat out their AI competitors on every criteria and on every submission, scoring an 81% on an internal rubric compared with the machine's 47%.
Reviewers told the report's authors that AI summaries often missed emphasis, nuance and context; included incorrect information or missed relevant information; and sometimes focused on auxiliary points or introduced irrelevant information. Three of the five reviewers said they guessed that they were reviewing AI content.
The reviewers' overall feedback was that they felt AI summaries may be counterproductive and create further work because of the need to fact-check and refer to original submissions which communicated the message better and more concisely.
