5 papers
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?
Xuanfei Ren, Tengyang Xie
Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets record only trajectory-level outcomes. We develop…
POLCA: Stochastic Generative Optimization with LLM
Xuanfei Ren, Allen Nie, Tengyang Xie +1
Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic gene…
I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses
Xuan Ren, Biao Wu, Lingqiao Liu
This paper explores an intriguing observation: fine-tuning a large language model (LLM) with responses generated by a LLM often yields better results than using responses generated…
Efficient Response Generation Strategy Selection for Fine-Tuning Large Language Models Through Self-Aligned Perplexity
Xuan Ren, Qi Chen, Lingqiao Liu
Fine-tuning large language models (LLMs) typically relies on producing large sets of input-output pairs. Yet for a given question, there can be many valid outputs. In practice, the…
You Can Generate It Again: Data-to-Text Generation with Verification and Correction Prompting
Xuan Ren, Zeyu Zhang, Lingqiao Liu
Small language models like T5 excel in generating high-quality text for data-to-text tasks, offering adaptability and cost-efficiency compared to Large Language Models (LLMs). Howe…