会员服务
LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI
Arxiv
0+阅读 · 6月16日
HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate
Arxiv
0+阅读 · 6月13日
DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation
Arxiv
0+阅读 · 6月15日
The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment
Arxiv
0+阅读 · 6月7日
When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning
Arxiv
0+阅读 · 6月1日
MADRAG: Multi-Agent Debate with Retrieval-Augmented Generation for Training-Free Analytic Essay Scoring
Arxiv
0+阅读 · 6月4日
Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verification
Arxiv
0+阅读 · 5月14日
ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning
Arxiv
0+阅读 · 6月11日
Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines
Arxiv
0+阅读 · 5月26日
SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate
Arxiv
0+阅读 · 5月21日
BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection
Arxiv
0+阅读 · 6月11日
MARS: toward more efficient multi-agent collaboration for LLM reasoning
Arxiv
0+阅读 · 3月24日
Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate
Arxiv
0+阅读 · 4月15日
Efficient LLM Safety Evaluation through Multi-Agent Debate
Efficient LLM Safety Evaluation through Multi-Agent Debate
Arxiv
0+阅读 · 3月18日
Efficient LLM Safety Evaluation through Multi-Agent Debate
Arxiv
0+阅读 · 3月17日
参考链接
微信扫码咨询专知VIP会员
Top