Large Language Models are biased to overestimate profoundness

Eugenio Herrera-Berg, Tomás Vergara Browne, Pablo León-Villagrá, Marc-Lluís Vives, Cristian Buc Calderon

Submission Type: Regular Short Paper

Submission Track: Resources and Evaluation

Submission Track 2: Language Modeling and Analysis of Language Models

Keywords: Large language models, reasoning, bias, nonsensical statements

Abstract: Recent advancements in natural language processing by large language models (LLMs), such as GPT-4, have been suggested to approach Artificial General Intelligence. And yet, it is still under dispute whether LLMs possess similar reasoning abilities to humans. This study evaluates GPT-4 and various other LLMs in judging the profoundness of mundane, motivational, and pseudo-profound statements. We found a significant statement-to-statement correlation between the LLMs and humans, irrespective of the type of statements and the prompting technique used. However, LLMs systematically overestimate the profoundness of nonsensical statements, with the exception of Tk-instruct, which uniquely underestimates the profoundness of statements. Only few-shot learning prompts, as opposed to chain-of-thought prompting, draw LLMs ratings closer to humans. Furthermore, this work provides insights into the potential biases induced by Reinforcement Learning from Human Feedback (RLHF), inducing an increase in the bias to overestimate the profoundness of statements.

Submission Number: 3827