266 citations · 298 across the 14 of their papers we have counts for
16 papers
Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives
Qiwei Di, Xuheng Li, Kaixuan Ji +3
On-policy distillation (OPD) learns from teacher feedback on student-generated responses and has shown promise in reducing forgetting relative to supervised fine-tuning (SFT). Howe…
Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity
Kaixuan Ji, Qiwei Di, Qingyue Zhao +2
We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers. For -armed band…
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
Qingyue Zhao, Kaixuan Ji, Heyang Zhao +1
\emph{Kullback-Leibler} (KL) regularization is ubiquitous in reinforcement learning algorithms in the form of \emph{reverse} or \emph{forward} KL. Recent studies have demonstrated…
On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
Kaixuan Ji, Qiwei Di, Heyang Zhao +2
Kullback-Leibler (KL) regularization is widely used in offline decision-making and offers several benefits, motivating recent work on the sample complexity of offline learning with…
Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
Kaixuan Ji, Qingyue Zhao, Heyang Zhao +2
Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqr…
Best-of-Majority: Minimax-Optimal Strategy for Pass@ Inference Scaling
Qiwei Di, Kaixuan Ji, Xuheng Li +2
LLM inference often generates a batch of candidates for a prompt and selects one via strategies like majority voting or Best-of- N (BoN). For difficult tasks, this single-shot sele…
Towards a Sharp Analysis of Offline Policy Learning for -Divergence-Regularized Contextual Bandits
Qingyue Zhao, Kaixuan Ji, Heyang Zhao +2
Many offline reinforcement learning algorithms are underpinned by -divergence regularization, but their sample complexity *defined with respect to regularized objectives* still…
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
Kaixuan Ji, Guanlin Liu, Ning Dai +6
Reinforcement Learning (RL) plays a crucial role in aligning large language models (LLMs) with human preferences and improving their ability to perform complex tasks. However, curr…
Self-Play Preference Optimization for Language Model Alignment
Yue Wu, Zhiqing Sun, Huizhuo Yuan +3
Standard reinforcement learning from human feedback (RLHF) approaches relying on parametric models like the Bradley-Terry model fall short in capturing the intransitivity and irrat…
Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation
Huizhuo Yuan, Zixiang Chen, Kaixuan Ji +1
Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI), especially when compared with the remarkable progress made in fine-tun…
Reinforcement Learning from Human Feedback with Active Queries
Kaixuan Ji, Jiafan He, Quanquan Gu
Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (…
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Zixiang Chen, Yihe Deng, Huizhuo Yuan +2
Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Language Models (LLMs). In this paper, we delve into the prospect o…
Mastering the Task of Open Information Extraction with Large Language Models and Consistent Reasoning Environment
Ji Qi, Kaixuan Ji, Xiaozhi Wang +5
Open Information Extraction (OIE) aims to extract objective structured knowledge from natural texts, which has attracted growing attention to build dedicated models with human expe…
Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
Kaixuan Ji, Qingyue Zhao, Jiafan He +2
Recent studies have shown that episodic reinforcement learning (RL) is no harder than bandits when the total reward is bounded by , and proved regret bounds that have a polyloga…
Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers
Weng Lam Tam, Xiao Liu, Kaixuan Ji +6
Prompt tuning attempts to update few task-specific parameters in pre-trained models. It has achieved comparable performance to fine-tuning of the full parameter set on both languag…
P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
Xiao Liu, Kaixuan Ji, Yicheng Fu +4
Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU…