activity
20232026
most citedJailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

22 citations · 32 across the 27 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning

Lizhe Fang, Weizhou Shen, Tianyi Tang +1

Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings has emerged as an i…

cs.CL2026

Autoregressive Models Rival Diffusion Models at ANY-ORDER Generation

Tianqi Du, Lizhe Fang, Weijie Yang +4

Diffusion language models enable any-order generation and bidirectional conditioning, offering appealing flexibility for tasks such as infilling, rewriting, and self-correction. Ho…

cs.CL2025

Long-Short Alignment for Effective Long-Context Modeling in LLMs

Tianqi Du, Haotian Huang, Yifei Wang +1

Large language models (LLMs) have exhibited impressive performance and surprising emergent properties. However, their effectiveness remains limited by the fixed context window of t…

cs.CL2025

Rethinking Invariance in In-context Learning

Lizhe Fang, Yifei Wang, Khashayar Gatmiry +2

In-Context Learning (ICL) has emerged as a pivotal capability of auto-regressive large language models, yet it is hindered by a notable sensitivity to the ordering of context examp…

cs.CL2024

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

Zijun Wang, Haoqin Tu, Jieru Mei +3

This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate…

cs.CL2024★ 2 cited

What is Wrong with Perplexity for Long-context Language Modeling?

Lizhe Fang, Yifei Wang, Zhaoyang Liu +5

Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While r…