4 papers
Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents
Tianyi Zhang, Zhonghao Qi
Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for…
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
Wenbo Yu, Bohua Wang, Hao Fang +10
Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilin…
Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models
Feng Luo, Yu-Neng Chuang, Guanchu Wang +4
On-policy distillation (OPD) trains student models under their own induced distribution while leveraging supervision from stronger teachers. We identify a failure mode of OPD: as t…
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
Tianyi Zhang, Linrong Cai, Jeffrey Li +4
Weak supervision (WS) is a popular approach for label-efficient learning, leveraging diverse sources of noisy but inexpensive weak labels to automatically annotate training data. D…