Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Davila, Ana, Colan, Jacinto, Hasegawa, Yasuhisa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915393656848384
author Davila, Ana
Colan, Jacinto
Hasegawa, Yasuhisa
author_facet Davila, Ana
Colan, Jacinto
Hasegawa, Yasuhisa
contents Large Language Models (LLMs) have demonstrated significant capabilities in understanding and generating human language, contributing to more natural interactions with complex systems. However, they face challenges such as ambiguity in user requests processed by LLMs. To address these challenges, this paper introduces and evaluates a multi-agent debate framework designed to enhance detection and resolution capabilities beyond single models. The framework consists of three LLM architectures (Llama3-8B, Gemma2-9B, and Mistral-7B variants) and a dataset with diverse ambiguities. The debate framework markedly enhanced the performance of Llama3-8B and Mistral-7B variants over their individual baselines, with Mistral-7B-led debates achieving a notable 76.7% success rate and proving particularly effective for complex ambiguities and efficient consensus. While acknowledging varying model responses to collaborative strategies, these findings underscore the debate framework's value as a targeted method for augmenting LLM capabilities. This work offers important insights for developing more robust and adaptive language understanding systems by showing how structured debates can lead to improved clarity in interactive systems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12370
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
Davila, Ana
Colan, Jacinto
Hasegawa, Yasuhisa
Computation and Language
Human-Computer Interaction
Large Language Models (LLMs) have demonstrated significant capabilities in understanding and generating human language, contributing to more natural interactions with complex systems. However, they face challenges such as ambiguity in user requests processed by LLMs. To address these challenges, this paper introduces and evaluates a multi-agent debate framework designed to enhance detection and resolution capabilities beyond single models. The framework consists of three LLM architectures (Llama3-8B, Gemma2-9B, and Mistral-7B variants) and a dataset with diverse ambiguities. The debate framework markedly enhanced the performance of Llama3-8B and Mistral-7B variants over their individual baselines, with Mistral-7B-led debates achieving a notable 76.7% success rate and proving particularly effective for complex ambiguities and efficient consensus. While acknowledging varying model responses to collaborative strategies, these findings underscore the debate framework's value as a targeted method for augmenting LLM capabilities. This work offers important insights for developing more robust and adaptive language understanding systems by showing how structured debates can lead to improved clarity in interactive systems.
title Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2507.12370