3 papers
cs.CL2026
Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval
Seyeon Jeong, Yeonjun Choi, JongWook Kim +1
Large Language Models (LLMs) suffer from hallucinations and factual inaccuracies, especially in complex reasoning and fact verification tasks. Multi-Agent Debate (MAD) systems aim…
cs.LG2025
Scaling Bidirectional Spans and Span Violations in Attention Mechanism
Jongwook Kim, Sangheon Yun, Sukjin Yoon
The canonical Transformer remains the empirical performance frontier in sequence modeling, and its training can be further optimized by addressing geometric inefficiency.…
cs.LG2025
Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?
Jeongwhan Choi, Woosung Kang, Minseo Kim +2
Foundation models pretrained on large data have demonstrated remarkable zero-shot generalization capabilities across domains. Building on the success of TabPFN for tabular data and…