Get started
Author

Hoyun Song

Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation
2026 · Association for Computational Linguistics 2026, Ko, Changgeon, et al. · Underline Science Inc.
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
2026 · Association for Computational Linguistics 2026, Hwang, Euijun, et al. · Underline Science Inc.
RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity
2026 · Association for Computational Linguistics 2026, Jung, Chani, et al. · Underline Science Inc.
Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval
2026 · Association for Computational Linguistics 2026, Cho, Sukmin, et al. · Underline Science Inc.
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
2026 · Ko, Changgeon, Shin, Jisu, et al. · arXiv (Cornell University)
PDF
TReX: Tokenizer Regression for Optimal Data Mixture
2026 · Association for Computational Linguistics 2026, Cho, Minkyung, et al. · Underline Science Inc.
TREX: Tokenizer Regression for Optimal Data Mixture
2026 · Won, Inho, Yoo, Hangyeol, et al. · arXiv (Cornell University)
PDF
TReX: Tokenizer Regression for Optimal Data Mixture
2026 · Inho Won, Hangyeol Yoo, et al. · Conference of the European Chapter of the Association for Computational Linguistics
PDF
Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text
2026 · Minkyung Cho, Jihyo Kim, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
KORMo: Korean Open Reasoning Model for Everyone
2025 · Kim, Minjun, Lim, Hyeonseok, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count:
H-index:
I10-index:
Year
Topic
Type