illustration of magnifying glass over top of a search bar and lines of content on a green gradient background

Search and information retrieval

two sets of chat boxes with likes and dislikes

On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots

Result Diversification in Search and Recommendation: A Survey

ICRA 2024 conference recap blog - RASCAL library

RASCAL: Novel robotics for scalable and highly available automated storage and retrieval

Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models

Current selections

Sort by: Most recent

Clear selections

Project

Project GraphRAG

LLM-Derived Knowledge Graphs GraphRAG (Graphs + Retrieval Augmented Generation) is a technique for richly understanding text datasets by combining text extraction, network analysis, and LLM prompting and summarization into a single end-to-end system. GraphRAG and…

Publication

LongEmbed: Extending Embedding Models for Long Context Retrieval

Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li

EMNLP 2024 | April 2024

Microsoft Research Blog

Research Focus: Week of April 1, 2024

April 3, 2024 | Hao Fang, Jason Eisner, Ben Van Durme, Yu Su, Millicent Ochieng, Maxamed Axmed, Kalika Bali, Soham Deshmukh, Benjamin Elizalde, Dimitra Emmanouilidou

In this issue: New research helps COMET embrace African languages; FeatUp improves deep features, a computer vision research cornerstone; LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error; Benchmarking LLMs across languages and…

Publication

Training Audio Captioning Models without Audio

Soham Deshmukh, Benjamin Elizalde, Dimitra Emmanouilidou, Bhiksha Raj, Rita Singh, Huaming Wang

2024 International Conference on Acoustics, Speech, and Signal Processing | April 2024

Publication

A Framework for Exploring the Consequences of AI-Mediated Enterprise Knowledge Access and Identifying Risks to Workers

Anna Gausen, Bhaskar Mitra, Siân Lindley

ACM Conference on Fairness, Accountability, and Transparency | March 2024

Project Project

Microsoft Research Blog

Learning from interaction with Microsoft Copilot (web)

March 27, 2024 | Scott Counts, Jennifer Neville, Mengting Wan, Ryen W. White, Longqi Yang

Microsoft researchers are taking a comprehensive and dynamic approach to help Copilot (web) continuously learn from interaction and feedback, improving the AI system and making it increasingly useful for consumers. Learn more.