Year: 2025
Type: conference-paper
Abstract: Implicit premise is central to argumentative coherence and faithfulness, yet remain elusive in traditional single-pass computational models.We introduce a multi-agent framework that casts implicit premise recovery as a dialogic reasoning task between two LLM agents.Through structured rounds of debate, agents critically evaluate competing premises and converge on the most contextually appropriate interpretation.Evaluated on a controlled binary classification benchmark for premise selection, our approach achieves state-of-the-art accuracy, outperforming both neural baselines and singleagent LLMs.We find that accuracy gains stem not from repeated generation, but from agents refining their predictions in response to opposing views.Moreover, we show that forcing models to defend assigned stances degrades performance-engendering rhetorical rigidity to flawed reasoning.These results underscore the value of interactive debate in revealing pragmatic components of argument structure.
Authors: Harvey Bonmu Ku, Jeongyeol Shin, Hyoun Jun Lee, Seonok Na, Insu Jeon
Institution: Ministry of National Defense
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412889364