5 papers
Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
Xisen Jin, Michael Duan, Qin Lin +4
As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces a threat where safety measures…
Reference-Based Distillation Detection in LLMs
Rajat Rawat, Sizhe Chen, Akshay Anand +3
Model distillation -- training on outputs from stronger third-party models -- is widely used to boost performance, but raises concerns about unfair advantages and policy violations…
A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
Rui Xin, Niloofar Mireshghallah, Shuyue Stella Li +6
Sanitizing sensitive text data typically involves removing personally identifiable information (PII) or generating synthetic data under the assumption that these methods adequately…
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
Hyunwoo Kim, Niloofar Mireshghallah, Michael Duan +11
Research involving privacy-sensitive data has always been constrained by data scarcity, standing in sharp contrast to other areas that have benefited from data scaling. This challe…
Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks
Xinxi Lyu, Michael Duan, Rulin Shao +2
Retrieval-augmented Generation (RAG) has primarily been studied in limited settings, such as factoid question answering; more challenging, reasoning-intensive benchmarks have seen…