activity
20242026
most citedGenerative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates

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

collaborators
Showing cs.CLShow all

18 papers · 1 filter

cs.CL2025

Weak-to-Strong Jailbreaking on Large Language Models

Xuandong Zhao, Xianjun Yang, Tianyu Pang +4

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computati…

cs.CL2025

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

Xuandong Zhao, Lei Li, Yu-Xiang Wang

In this paper, we propose a new decoding method called Permute-and-Flip (PF) decoder. It enjoys stability properties similar to the standard sampling decoder, but is provably up to…

cs.CL2024

Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions

Kexun Zhang, Yee Man Choi, Zhenqiao Song +3

How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform we…

cs.CL2024

LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback

Wenda Xu, Daniel Deutsch, Mara Finkelstein +6

Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In t…

cs.CL2024

CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation

Xi Xu, Wenda Xu, Siqi Ouyang +1

Simultaneous speech translation (SimulST) systems must balance translation quality with response time, making latency measurement crucial for evaluating their real-world performanc…

cs.CL2024

Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems

Chinmay Dandekar, Wenda Xu, Xi Xu +2

With the rapid advancement of machine translation research, evaluation toolkits have become essential for benchmarking system progress. Tools like COMET and SacreBLEU offer single…