10 papers
OpenThoughts-Agent: Data Recipes for Agentic Models
Negin Raoof, Richard Zhuang, Marianna Nezhurina +47
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts…
MolDeTox: Evaluating Language Model's Stepwise Fragment Editing for Molecular Detoxification
Jueon Park, Wonjune Jang, Jiwoo Lee +2
Large Language Models (LLMs) and Vision Language Models (VLMs) have recently shown promising capabilities in various scientific domain. In particular, these advances have opened ne…
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
Yein Park, Jungwoo Park, Jaewoo Kang
Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstra…
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training
Yein Park, Minbyul Jeong, Jaewoo Kang
The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (…
ToxReason: A Benchmark for Mechanistic Chemical Toxicity Reasoning via Adverse Outcome Pathway
Jueon Park, Wonjune Jang, Chanhwi Kim +2
Recent advances in large language models (LLMs) have enabled molecular reasoning for property prediction. However, toxicity arises from complex biological mechanisms beyond chemica…
CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction
Jueon Park, Yein Park, Minju Song +4
Drug toxicity remains a major challenge in pharmaceutical development. Recent machine learning models have improved in silico toxicity prediction, but their reliance on annotated d…