12 papers
Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
Yingyu Lin, Qiyue Gao, Nikki Lijing Kuang +6
Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the gr…
Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
Hao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu +2
Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input conte…
Training a Large Language Model for Medical Coding Using Privacy-Preserving Synthetic Clinical Data
John Cook, Michael Wyatt, Peng Wei +11
Improving the accuracy and reliability of medical coding reduces clinician burnout and supports revenue cycle processes, freeing providers to focus more on patient care. However, a…
DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science
Fan Shu, Yite Wang, Ruofan Wu +4
The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benchmarking. There are two majo…
STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning
Jaeseong Lee, seung-won hwang, Aurick Qiao +3
Mixture-of-experts (MoEs) have been adopted for reducing inference costs by sparsely activating experts in Large language models (LLMs). Despite this reduction, the massive number…
Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences
Stas Bekman, Samyam Rajbhandari, Michael Wyatt +5
Long sequences are critical for applications like RAG, long document summarization, multi-modality, etc., and modern LLMs, like Llama 4 Scout, support max sequence length of up to…