Search Results for author:
Found 2 papers, 0 papers with code
Provably Robust DPO: Aligning Language Models with Noisy Feedback
Our experiments on IMDb sentiment generation and Anthropic's helpful-harmless dataset show that rDPO is robust to noise in preference labels compared to vanilla DPO and other heuristics proposed by practitioners.
GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval
Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
