13 papers
Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages
Chanwoong Yoon, Jungsoo Park, Alan Ritter
Safety alignment helps models adhere to human values, but it often reduces response utility. We ask a critical but understudied question: Does safety alignment impose the cost equa…
AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale
Minbyul Jeong, Chanwoong Yoon
Agents learn to act through interaction with environments, yet the environments used for training are often manually constructed or synthesized around predefined tasks and benchmar…
Solar Open 2 Technical Report
Sungrae Park, Sanghoon Kim, Gyoungjin Gim +50
We present Solar Open 2, a 250B-A15B Mixture-of-Experts language model built for long-horizon agentic tasks, scaled up from Solar Open 1 (Solar Open 100B). To hold entire agent tra…
The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
Taewhoo Lee, Minju Song, Chanwoong Yoon +2
Analogical reasoning is at the core of human cognition, serving as an important foundation for a variety of intellectual activities. While prior work has shown that LLMs can repres…
Assessing LLM Reasoning Steps via Principal Knowledge Grounding
Hyeon Hwang, Yewon Cho, Chanwoong Yoon +5
Step-by-step reasoning has become a standard approach for large language models (LLMs) to tackle complex tasks. While this paradigm has proven effective, it raises a fundamental qu…
Rationale-Guided Retrieval Augmented Generation for Medical Question Answering
Jiwoong Sohn, Yein Park, Chanwoong Yoon +5
Large language models (LLM) hold significant potential for applications in biomedicine, but they struggle with hallucinations and outdated knowledge. While retrieval-augmented gene…