3 papers
cs.LG2026
AME: A Multi-Type Contributor Attribution Framework in Generative AI Markets
Yang Shi, Songwen Pei, Yang Gao +1
Generative AI enables value creation through multi-stage collaboration among heterogeneous contributors, including training data, base models, fine-tuning behaviors, and prompts. H…
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…