This is a github project holding PAIR's explorations with using natural language as the boundary object between recommenders and people.
Our papers on this topic:
- Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences RecSys 2023 -- Scott Sanner, Krisztian Balog, Filip Radlinski, Ben Wedin, Lucas Dixon
- Large Language Models for User Interest Journeys arxiv 2023 -- Konstantina Christakopoulou, Alberto Lalama, Cj Adams, Iris Qu, Yifat Amir, Samer Chucri, Pierce Vollucci, Fabio Soldo, Dina Bseiso, Sarah Scodel, Lucas Dixon, Ed H. Chi, Minmin Chen
- KNNs of Semantic Encodings for Rating Prediction arxiv 2023 -- Léo Laugier, Raghuram Vadapalli, Thomas Bonald, Lucas Dixon. See the See the https://github.com/PAIR-code/recommendation-rudders/tree/master/multi-sentence-rep-rs subdirectory for associated code.
- On Natural Language User Profiles for Transparent and Scrutable Recommendation ACM SIGIR 2022 -- Filip Radlinski, Krisztian Balog, Fernando Diaz, Lucas Dixon, Ben Wedin
- Augmenting the User-Item Graph with Textual Similarity Models arxiv 2021 -- Federico López, Martin Scholz, Jessica Yung, Marie Pellat, Michael Strube, Lucas Dixon. See the https://github.com/PAIR-code/recommendation-rudders/tree/master/hyperbolic-rs subdirectory for associated code.