52 citations · 61 across the 15 of their papers we have counts for
10 papers · 1 filter
dLLM: Simple Diffusion Language Modeling
Zhanhui Zhou, Lingjie Chen, Hanghang Tong +1
Although diffusion language models (DLMs) are evolving quickly, many recent models converge on a set of shared components. These components, however, are distributed across ad-hoc…
RePO: Replay-Enhanced Policy Optimization
Siheng Li, Zhanhui Zhou, Wai Lam +2
Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy out…
Emergent Response Planning in LLMs
Zhichen Dong, Zhanhui Zhou, Zhixuan Liu +2
In this work, we argue that large language models (LLMs), though trained to predict only the next token, exhibit emergent planning behaviors: $\textbf{their hidden representations…
Inference-Time Language Model Alignment via Integrated Value Guidance
Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang +2
Large language models are typically fine-tuned to align with human preferences, but tuning large models is computationally intensive and complex. In this work, we introduce $\texti…
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…
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…
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
Zhichen Dong, Zhanhui Zhou, Chao Yang +2
Large Language Models (LLMs) are now commonplace in conversation applications. However, their risks of misuse for generating harmful responses have raised serious societal concerns…
ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models
Yanan Wu, Jie Liu, Xingyuan Bu +10
This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs). Unl…
MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues
Ge Bai, Jie Liu, Xingyuan Bu +8
The advent of Large Language Models (LLMs) has drastically enhanced dialogue systems. However, comprehensively evaluating the dialogue abilities of LLMs remains a challenge. Previo…
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…