9 papers
NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
Yuan Xie, Jiaqi Song, Guang Qiu +9
Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a mainstream paradigm in recent years. Although existing LLM-based ASR models demonstrat…
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20
Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models…
SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training
Powei Chang, Jinpeng Zhang, Bowen Chen +9
Information-based data selection for instruction tuning is compelling: maximizing the log-determinant of the Fisher information yields a monotone submodular objective, enabling gre…
A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures
Bowen Chen, Namgi Han, Yusuke Miyao
Memorization is a fundamental component of intelligence for both humans and LLMs. However, while LLM performance scales rapidly, our understanding of memorization lags. Due to limi…
OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights
Bowen Chen, Jayesh Gajbhar, Gregory Dusek +6
Artificial intelligence is transforming the sciences, yet general conversational AI systems often generate unverified "hallucinations" undermining scientific rigor. We present Ocea…
Improving Compiler Bug Isolation by Leveraging Large Language Models
Yixian Qi, Jiajun Jiang, Fengjie Li +3
Compilers play a foundational role in building reliable software systems, and bugs within them can lead to catastrophic consequences. The compilation process typically involves hun…