Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning
This addresses the need for reliable and budget-friendly AI agents in applications like home automation, though it is incremental as it builds on existing uncertainty estimation methods.
The paper tackles the problem of hallucination in large language models during decision planning by introducing a non-parametric uncertainty quantification method that efficiently estimates point-wise dependencies with a single inference, enabling cost-effective use of black-box LLMs.
Step-by-step decision planning with large language models (LLMs) is gaining attention in AI agent development. This paper focuses on decision planning with uncertainty estimation to address the hallucination problem in language models. Existing approaches are either white-box or computationally demanding, limiting use of black-box proprietary LLMs within budgets. The paper's first contribution is a non-parametric uncertainty quantification method for LLMs, efficiently estimating point-wise dependencies between input-decision on the fly with a single inference, without access to token logits. This estimator informs the statistical interpretation of decision trustworthiness. The second contribution outlines a systematic design for a decision-making agent, generating actions like ``turn on the bathroom light'' based on user prompts such as ``take a bath''. Users will be asked to provide preferences when more than one action has high estimated point-wise dependencies. In conclusion, our uncertainty estimation and decision-making agent design offer a cost-efficient approach for AI agent development.