Preference Inference for Language Models Debiased by Fisher Random Walk Models
Harvard TH Chan School of Public Health 677 Huntington Ave, Boston, MAHSPH Biostatistics & DFCI Data Science Colloquium Series September 11 at 4:00PM Harvard TH Chan School of Public Health, FXB-301 Junwei Lu, PhD Associate Professor of Biostatistics, Harvard TH Chan School of Public Health Human preference alignment has been shown to be effective in training the large language models (LMs). It allows the LLM to […]
