Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer correctness

TL;DR

This paper investigates how prompt-provided knowledge versus the model's inherent knowledge affects ChatGPT's accuracy in health-related answers, revealing that prompt knowledge can sometimes override the model's correct information, impacting answer quality.

Contribution

The study demonstrates that prompt knowledge can overturn the model's encoded knowledge in ChatGPT, affecting answer correctness in health advice scenarios.

Findings

Prompt knowledge can override model knowledge, reducing answer correctness.

ChatGPT's accuracy varies depending on prompt content and source.

Implications for designing more robust and transparent QA systems.

Abstract

Generative pre-trained language models (GPLMs) like ChatGPT encode in the model's parameters knowledge the models observe during the pre-training phase. This knowledge is then used at inference to address the task specified by the user in their prompt. For example, for the question-answering task, the GPLMs leverage the knowledge and linguistic patterns learned at training to produce an answer to a user question. Aside from the knowledge encoded in the model itself, answers produced by GPLMs can also leverage knowledge provided in the prompts. For example, a GPLM can be integrated into a retrieve-then-generate paradigm where a search engine is used to retrieve documents relevant to the question; the content of the documents is then transferred to the GPLM via the prompt. In this paper we study the differences in answer correctness generated by ChatGPT when leveraging the model's knowledge alone vs. in combination with the prompt knowledge. We study this in the context of consumers seeking health advice from the model. Aside from measuring the effectiveness of ChatGPT in this context, we show that the knowledge passed in the prompt can overturn the knowledge encoded in the model and this is, in our experiments, to the detriment of answer correctness. This work has important implications for the development of more robust and transparent question-answering systems based on generative pre-trained language models.