Beyond Turing Test: Can GPT-4 Sway Experts' Decisions?
This addresses the problem of evaluating LLMs' real-world impact on human decision-making, which is incremental as it builds on existing evaluation methods.
The paper investigates whether GPT-4-generated text can influence decisions of both amateur and expert audiences, finding it persuasive and highlighting a high correlation between real-world audience reactions and standard evaluators.
In the post-Turing era, evaluating large language models (LLMs) involves assessing generated text based on readers' reactions rather than merely its indistinguishability from human-produced content. This paper explores how LLM-generated text impacts readers' decisions, focusing on both amateur and expert audiences. Our findings indicate that GPT-4 can generate persuasive analyses affecting the decisions of both amateurs and professionals. Furthermore, we evaluate the generated text from the aspects of grammar, convincingness, logical coherence, and usefulness. The results highlight a high correlation between real-world evaluation through audience reactions and the current multi-dimensional evaluators commonly used for generative models. Overall, this paper shows the potential and risk of using generated text to sway human decisions and also points out a new direction for evaluating generated text, i.e., leveraging the reactions and decisions of readers. We release our dataset to assist future research.