32 papers
CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization
Ziqian Bi, Yinzhi Wang, Tianyang Wang +6
Long Chain-of-Thought (CoT) traces can improve reasoning accuracy, but repeatedly generating them is costly for smaller or latency-constrained language models. This paper studies a…
Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
Benji Peng, Hanxuan Chen, Keyu Chen +12
Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthc…
From In Silico to In Vitro: A Comprehensive Guide to Validating Bioinformatics Findings
Tianyang Wang, Silin Chen, Yunze Wang +18
The integration of bioinformatics predictions and experimental validation plays a pivotal role in advancing biological research, from understanding molecular mechanisms to developi…
47B Mixture-of-Experts Beats 671B Dense Models on Chinese Medical Examinations
Chiung-Yi Tseng, Danyang Zhang, Tianyang Wang +8
The rapid advancement of large language models(LLMs) has prompted significant interest in their potential applications in medical domains. This paper presents a comprehensive bench…
Exploring Efficiency Frontiers of Thinking Budget in Medical Reasoning: Scaling Laws between Computational Resources and Reasoning Quality
Ziqian Bi, Lu Chen, Junhao Song +15
This study presents the first comprehensive evaluation of thinking budget mechanisms in medical reasoning tasks, revealing fundamental scaling laws between computational resources…
Mixture of Experts in Large Language Models
Danyang Zhang, Junhao Song, Ziqian Bi +5
This paper presents a comprehensive review of the Mixture-of-Experts (MoE) architecture in large language models, highlighting its ability to significantly enhance model performanc…