Cheyon Jin — accepted AI-conference papers

2026

Non-Collaborative User Simulators for Tool Agents

Jeonghoon Shim, Woojung Song, Cheyon Jin, Seungwon KooK, Yohan Jo

ICLR 2026poster

Tool agents interact with users through multi-turn dialogues to accomplish various tasks. Recent studies have adopted user simulation methods to develop these agents in multi-turn settings. However, existing user simulators tend to be agent-friendly, exhibiting only cooperative behaviors, which fail…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval

Jonghyun Song, Cheyon Jin, Wenlong Zhao, Andrew McCallum, Jay-Yoon Lee

EMNLP 2024main

A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encoders (CE) to a limited candidate set. However, relying on this small subset is often susceptible to error propagation fro…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗