activity
20192026
most citedPrivacy-Preserving In-Context Learning for Large Language Models

6 citations · 13 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice

Jiachen T. Wang, Tong Wu, Kaifeng Lyu +4

Data teams at frontier AI companies routinely train small proxy models to make critical decisions about pretraining data recipes for full-scale training runs. However, the communit…

cs.LG2025

Effectively Controlling Reasoning Models through Thinking Intervention

Tong Wu, Chong Xiang, Jiachen T. Wang +2

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solvi…

cs.LG2024

Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy

Tong Wu, Shujian Zhang, Kaiqiang Song +7

Large Language Models (LLMs) are susceptible to security and safety threats, such as prompt injection, prompt extraction, and harmful requests. One major cause of these vulnerabili…

cs.LG2024★ 5 cited

Certifiably Robust RAG against Retrieval Corruption

Chong Xiang, Tong Wu, Zexuan Zhong +3

Retrieval-augmented generation (RAG) is susceptible to retrieval corruption attacks, where malicious passages injected into retrieval results can lead to inaccurate model responses…

cs.LG2024

Position: Towards Resilience Against Adversarial Examples

Sihui Dai, Chong Xiang, Tong Wu +1

Current research on defending against adversarial examples focuses primarily on achieving robustness against a single attack type such as or -bounded attack…

cs.LG2023★ 6 cited

Privacy-Preserving In-Context Learning for Large Language Models

Tong Wu, Ashwinee Panda, Jiachen T. Wang +1

In-context learning (ICL) is an important capability of Large Language Models (LLMs), enabling these models to dynamically adapt based on specific, in-context exemplars, thereby im…