CLJun 3

SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction

arXiv:2606.0469183.0
Predicted impact top 59% in CL · last 90 daysOriginality Incremental advance
AI Analysis

For zero-shot IE tasks, this work addresses token overhead and cross-type conflicts in multi-agent systems, offering a more efficient and accurate approach.

SMADE-IE introduces a sparse multi-agent framework with evidence-driven debate for zero-shot information extraction, achieving consistent improvements over baselines on 9 benchmark datasets while improving token efficiency.

Zero-shot information extraction (IE) with large language models (LLMs) has attracted increasing attention due to its flexibility in adapting to new schemas and domains without task-specific training. Existing approaches mainly rely on monolithic prompting, each-type prompting, or multi-agent debate. However, monolithic prompting often suffers from boundary and type errors, while each-type prompting and multi-agent debate introduce cross-type conflicts, redundant agent interactions, and substantial token overhead. To address these challenges, we propose SMADE-IE, a sparse and evidence-driven multi-agent framework for zero-shot IE. SMADE-IE first employs an Adaptive Mode Selector to dynamically route inputs into either a lightweight Global Extraction Mode or a Type-Centric Extraction Mode, reducing unnecessary type selection and reasoning noise. For conflicting predictions, we further introduce an Evidence-Driven Debate mechanism that structures arguments into Toulmin-style components and performs confidence aggregation through external evidence scoring and Bayesian updates. Experimental results on 9 benchmark datasets across NER, RE, and JERE tasks show that SMADE-IE consistently outperforms existing zero-shot IE baselines while also improving token efficiency through sparse agent selection and early-stopping debate.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes