1 citations · 1 across the 8 of their papers we have counts for
8 papers
1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation
Huanxin Sheng, Zhiling Ye, Haonan Wang +3
Sparse on-policy distillation (OPD) allocates teacher supervision to a small subset of tokens in student-generated trajectories. However, useful teacher guidance can yield a noisy…
MetaToolAgent: Towards Generalizable Tool Usage in LLMs through Meta-Learning
Zheng Fang, Wolfgang Mayer, Zeyu Zhang +4
Tool learning is increasingly important for large language models (LLMs) to effectively coordinate and utilize a diverse set of tools in order to solve complex real-world tasks. By…
Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts
Xiaoyan Zhao, Ming Yan, Yang Zhang +6
Conversational Recommender Systems (CRSs) aim to provide personalized recommendations through multi-turn natural language interactions with users. Given the strong interaction and…
Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
Zhiling Ye, Yun Yue, Haowen Wang +11
Open-ended evaluation is essential for deploying large language models in real-world settings. In studying HealthBench, we observe that using the model itself as a grader and gener…
Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment
Haowen Wang, Yun Yue, Zhiling Ye +12
Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through d…
R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science
Xu Yang, Xiao Yang, Shikai Fang +13
Recent advances in AI and ML have transformed data science, yet increasing complexity and expertise requirements continue to hinder progress. Although crowd-sourcing platforms alle…
RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment
Xiaohan Wang, Xiaoyan Yang, Yuqi Zhu +7
Large Language Models (LLMs) like GPT-4, MedPaLM-2, and Med-Gemini achieve performance competitively with human experts across various medical benchmarks. However, they still face…
OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy
Haowen Wang, Tao Sun, Kaixiang Ji +3
We advance the field of Parameter-Efficient Fine-Tuning (PEFT) with our novel multi-adapter method, OrchMoE, which capitalizes on modular skill architecture for enhanced forward tr…