Direct-Inverse Prompting: Analyzing LLMs’ Discriminative Capacity in Self-Improving Generation
Abstract: Mainstream LLM research has primarily focused on enhancing their generative capabilities. However, even the most advanced LLMs experience uncertainty in their outputs, often producing varied results on different runs or when faced with minor changes in input, despite no substantial change in content. Given multiple responses from the same LLM to the same input, we advocate leveraging the LLMs' discriminative capability to reduce this generative uncertainty, aiding in identifying the correct answers. Specifically, we propose and analyze three discriminative prompts: \direct, \inverse, and \hybrid, to explore the potential of both closed-source and open-source LLMs in self-improving their generative performance on two benchmark datasets. Our insights reveal which discriminative prompt is most promising and when to use it. To our knowledge, this is the first work to systematically analyze LLMs' discriminative capacity to address generative uncertainty.
Paper Type: Short
Research Area: Efficient/Low-Resource Methods for NLP
Research Area Keywords: Natural Language Process, Large Language Model, Mathematical Word Problem, discriminative prompts
Contribution Types: NLP engineering experiment
Languages Studied: English
Submission Number: 3303
Loading