most citedIterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

1 citations · 1 across the 2 of their papers we have counts for

collaborators

7 papers

cs.CL20241 cited

Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

Jie Liu, Zhanhui Zhou, Jiaheng Liu +4

Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show th…

cs.CL2024

Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models

Zhanhui Zhou, Zhixuan Liu, Jie Liu +3

Large language models are usually fine-tuned to align with human preferences. However, fine-tuning a large language model can be challenging. In this work, we introduce $\textit{we…

cs.CL2024

Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

Zhanhui Zhou, Jie Liu, Zhichen Dong +4

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing sa…

cs.LG2023

A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning

Yinmin Zhang, Jie Liu, Chuming Li +4

Offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online samples. Built on offline RL algorithms, most…

cs.LG2023

Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations

Lu Li, Yuxin Pan, Ruobing Chen +4

Inverse reinforcement learning (IRL) aims to explicitly infer an underlying reward function based on collected expert demonstrations. Considering that obtaining expert demonstratio…

cs.AI2023

MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning

Jie Liu, Yinmin Zhang, Chuming Li +4

Building a single generalist agent with strong zero-shot capability has recently sparked significant advancements. However, extending this capability to multi-agent decision making…