7 papers
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
Haruka Kiyohara, Mihaela Curmei, Ariel Evnine +7
Large-scale search, recommendation, and retrieval-augmented generation (RAG) systems typically employ a two-stage architecture: an early-stage ranker (ESR) generates a candidate se…
: Better Prompt Optimization with Fewer Prompts
Zhaolin Gao, Yu, Wang +4
Prompt optimization improves language models without updating their weights by searching for a better system prompt, but its effectiveness varies widely across tasks. We study what…
SteerEval: A Framework for Evaluating Steerability with Natural Language Profiles for Recommendation
Joyce Zhou, Weijie Zhou, Doug Turnbull +1
Natural-language user profiles have recently attracted attention not only for improved interpretability, but also for their potential to make recommender systems more steerable. By…
Prompt Curriculum Learning for Efficient LLM Post-Training
Zhaolin Gao, Joongwon Kim, Wen Sun +4
We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-…
End-to-end Training for Recommendation with Language-based User Profiles
Zhaolin Gao, Joyce Zhou, Yijia Dai +1
There is a growing interest in natural language-based user profiles for recommender systems, which aims to enhance transparency and scrutability compared with embedding-based metho…
REBEL: Reinforcement Learning via Regressing Relative Rewards
Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan +7
While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) application…