3 papers
cs.CR2026
A Watermark for Black-Box Language Models
Dara Bahri, John Wieting
Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's…
cs.CL2024
Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data
Tim Baumgärtner, Yang Gao, Dana Alon +1
Reinforcement Learning from Human Feedback (RLHF) is a popular method for aligning Language Models (LM) with human values and preferences. RLHF requires a large number of preferenc…
cs.CL2024
Impact of Preference Noise on the Alignment Performance of Generative Language Models
Yang Gao, Dana Alon, Donald Metzler
A key requirement in developing Generative Language Models (GLMs) is to have their values aligned with human values. Preference-based alignment is a widely used paradigm for this p…