6 papers
CoVeR: Coverage-Based Routing of Verifier Calls in Agentic Retrieval
Daeyoung Roh, Donghee Han
An agentic retrieval system issues a sequence of search queries and must decide, at each step, whether the evidence collected so far is enough to stop. Delegating that decision to…
HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents
Daeyoung Roh, Donghee Han
Retrieval-augmented search agents answer multi-hop questions by repeatedly issuing search queries and accumulating evidence. This creates a stopping problem: after the necessary ev…
Before Reasoning Can Fail: Pre-Evidence Procedural Failures in Agentic RAG
Daeyoung Roh, Donghee Han
Agentic retrieval-augmented generation (RAG) systems can fail before evidence-conditioned reasoning is tested: an agent may retrieve candidate snippets but finalize without inspect…
Every Error has Its Magnitude: Asymmetric Mistake Severity Training for Multiclass Multiple Instance Learning
Sungrae Hong, Jiwon Jeong, Jisu Shin +4
Multiple Instance Learning (MIL) has emerged as a promising paradigm for Whole Slide Image (WSI) diagnosis, offering effective learning with limited annotations. However, existing…
Closer through commonality: Enhancing hypergraph contrastive learning with shared groups
Daeyoung Roh, Donghee Han, Daehee Kim +2
Hypergraphs provide a superior modeling framework for representing complex multidimensional relationships in the context of real-world interactions that often occur in groups, over…
ProbGate at EHRSQL 2024: Enhancing SQL Query Generation Accuracy through Probabilistic Threshold Filtering and Error Handling
Sangryul Kim, Donghee Han, Sehyun Kim
Recently, deep learning-based language models have significantly enhanced text-to-SQL tasks, with promising applications in retrieving patient records within the medical domain. On…