Semih Yavuz
author title Research DirectorSemih Yavuz is a Research Director at Salesforce AI Research, leading a team focused on improving the factuality, groundedness, and reasoning capabilities of large language models in knowledge-intensive applications. His work involves developing state-of-the-art embedding and re-ranker models for knowledge retrieval across diverse domains, including code, multi-modal, and multilingual contexts, while refining retrieval-augmented generation (RAG) by enhancing how LLMs consume and integrate knowledge in complex reasoning. His team is focused on pushing the boundaries of the research to develop accurate, scalable, and reliable AI systems and driving product impact with them in the CRM domain.
Lead Author: Xi Ye TL;DR: We propose RnG-KBQA, a Rank-and-Generate Approach for Question Answering over Knowledge Bases, which enables answering natural language questions over large-scale knowledge bases. Our approach is capable of answering…
TL;DR: We propose controllable counterfactuals (CoCo) to evaluate dialogue state tracking (DST) models on novel scenarios, which results in significant performance drop of up to 30.8% for state-of-the-art DST models. Using CoCo for…

