From the 1 of 9 linked papers with an AI index.
9 papers
TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology
Hyunjin Seo, Hyeon Hwang, Gyubok Lee +7
The paper introduces TheBioCollection, a 52.6‑billion‑token unified corpus that aggregates diverse biological resources for pre‑training large language models, and shows that train…
Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering
Rezarta Islamaj, Joey Chan, Robert Leaman +13
Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple sources to answer complex que…
Teaching Language Models to Think in Code
Hyeon Hwang, Jiwoo Lee, Jaewoo Kang
Tool-integrated reasoning (TIR) has emerged as a dominant paradigm for mathematical problem solving in language models, combining natural language (NL) reasoning with code executio…
GraphCliff: Short-Long Range Gating for Modeling Critical Activity Changes Caused by Subtle Molecular Differences
Hajung Kim, Jueon Park, Junseok Choe +4
The quantitative structure-activity relationship assumes a smooth mapping between molecular structure and biological activity. However, activity cliffs, defined as pairs of structu…
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models (LLM) hold significant potential for applications in biomedicine, but they struggle with hallucinations and outdated knowledge.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…