Adaptive Elicitation of Latent Information Using Natural Language

Jimmy Wang, Thomas P Zollo, Richard Zemel, Hongseok Namkoong

TL;DR: We introduce a novel meta-learning and planning algorithm that can use LLMs to quantify uncertainty over natural language inputs, and ask questions to elicit information that reduces this uncertainty.

Abstract: Eliciting information to reduce uncertainty about a latent entity is a critical task in many application domains, e.g., assessing individual student learning outcomes, diagnosing underlying diseases, or learning user preferences. Though natural language is a powerful medium for this purpose, large language models (LLMs) and existing fine-tuning algorithms lack mechanisms for strategically gathering information to refine their own understanding of the latent entity. To harness the generalization power and world knowledge of LLMs in developing effective information-gathering strategies, we propose an adaptive elicitation framework that actively reduces uncertainty on the latent entity. Since probabilistic modeling of an abstract latent entity is difficult, our framework adopts a predictive view of uncertainty, using a meta-learned language model to simulate future observations and enable scalable uncertainty quantification over complex natural language. Through autoregressive forward simulation, our model quantifies how new questions reduce epistemic uncertainty, enabling the development of sophisticated information-gathering strategies to choose the most informative next queries. In experiments on the 20 questions game, dynamic opinion polling, and adaptive student assessment, our method consistently outperforms baselines in identifying critical unknowns and improving downstream predictions, illustrating the promise of strategic information gathering in natural language settings.

Lay Summary: We propose a framework for using LLMs to ask informative questions about variables and entities that cannot be directly observed. Potentially impactful applications include constructing a dynamic diagnostic questionnaire that maximizes the information gained about a patient’s health or generating a personalized set of test questions that yield the most insight into a student’s learning needs.

Application-Driven Machine Learning: This submission is on Application-Driven Machine Learning.

Link To Code: https://github.com/namkoong-lab/adaptive-elicitation

Primary Area: Applications->Language, Speech and Dialog

Keywords: Uncertainty Quantification, Natural Language, Adaptive Survey Design

Submission Number: 13154