Analogy Generation By Prompting Large Language Models: A Case Study Of Instructgpt

Bhavya Bhavya, Jinjun Xiong, ChengXiang Zhai

Oral Session 3 - Thursday 07/21 14:40 EST
Abstract: We propose a novel application of prompting Pre-trained Language Models (PLMs) to generate analogies and study how to design effective prompts for two task settings: generating a source concept analogous to a given target concept (aka Analogous Concept Generation ACG), and generating an explanation of the similarity between a given pair of target concept and source concept (aka Analogous Concept Explanation or ACE). We found that it is feasible to prompt InstructGPT to generate meaningful analogies and the best prompts tend to be precise imperative statements especially with low temperature setting. We also systematically analyzed the sensitivity of the InstructGPT model to prompt design and temperature and found that the model is particularly sensitive to certain variations (e.g., questions vs. imperative statements). Further, we conducted human evaluation on 1.3k of the generated analogies and found that the quality of generations varies substantially by model size. The largest InstructGPT model can achieve human-level performance at generating meaningful analogies for a given target while there is still room for improvement on the ACE task.