Active Task Disambiguation with LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kobalczyk, Katarzyna, Astorga, Nicolas, Liu, Tennison, van der Schaar, Mihaela
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913682835898368
author Kobalczyk, Katarzyna
Astorga, Nicolas
Liu, Tennison
van der Schaar, Mihaela
author_facet Kobalczyk, Katarzyna
Astorga, Nicolas
Liu, Tennison
van der Schaar, Mihaela
contents Despite the impressive performance of large language models (LLMs) across various benchmarks, their ability to address ambiguously specified problems--frequent in real-world interactions--remains underexplored. To address this gap, we introduce a formal definition of task ambiguity and frame the problem of task disambiguation through the lens of Bayesian Experimental Design. By posing clarifying questions, LLM agents can acquire additional task specifications, progressively narrowing the space of viable solutions and reducing the risk of generating unsatisfactory outputs. Yet, generating effective clarifying questions requires LLM agents to engage in a form of meta-cognitive reasoning, an ability LLMs may presently lack. Our proposed approach of active task disambiguation enables LLM agents to generate targeted questions maximizing the information gain. Effectively, this approach shifts the load from implicit to explicit reasoning about the space of viable solutions. Empirical results demonstrate that this form of question selection leads to more effective task disambiguation in comparison to approaches relying on reasoning solely within the space of questions.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04485
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Active Task Disambiguation with LLMs
Kobalczyk, Katarzyna
Astorga, Nicolas
Liu, Tennison
van der Schaar, Mihaela
Computation and Language
Artificial Intelligence
Machine Learning
Despite the impressive performance of large language models (LLMs) across various benchmarks, their ability to address ambiguously specified problems--frequent in real-world interactions--remains underexplored. To address this gap, we introduce a formal definition of task ambiguity and frame the problem of task disambiguation through the lens of Bayesian Experimental Design. By posing clarifying questions, LLM agents can acquire additional task specifications, progressively narrowing the space of viable solutions and reducing the risk of generating unsatisfactory outputs. Yet, generating effective clarifying questions requires LLM agents to engage in a form of meta-cognitive reasoning, an ability LLMs may presently lack. Our proposed approach of active task disambiguation enables LLM agents to generate targeted questions maximizing the information gain. Effectively, this approach shifts the load from implicit to explicit reasoning about the space of viable solutions. Empirical results demonstrate that this form of question selection leads to more effective task disambiguation in comparison to approaches relying on reasoning solely within the space of questions.
title Active Task Disambiguation with LLMs
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2502.04485