In this episode of Neural Search Talks, Andrew Yates (Assistant Prof at the University of Amsterdam) Sergi Castella (Analyst at Zeta Alpha), and Gabriel Bénédict (PhD student at the University of Amsterdam) discuss the prospect of using GPT-like models as a replacement for conventional search engines.
The conversation reflects on the foundations of Information Retrieval, index-centric vs. model-centric, what is Generative Information Retrieval, hallucination, factuality and faithfulness, evaluation of large Language Models, academic research in the times of GPT-4, and more.
Listen to the audio-only version on your preferred platform: https://podcasters.spotify.com/pod/show/neural-ir-talks/episodes/The-Promise-of-Language-Models-for-Search-Generative-Information-Retrieval-e225qek
Generative Information Retrieval (Gen IR) SIGIR Workshop
Workshop organized by Gabriel Bénédict, Ruqing Zhang, and Donald Metzler https://coda.io/@sigir/gen-ir
Resources on Gen IR: https://github.com/gabriben/awesome-generative-information-retrieval
References:
📄 Rethinking Search: https://arxiv.org/abs/2105.02274
📄 Survey on Augmented Language Models: https://arxiv.org/abs/2302.07842
📄 Differentiable Search Index: https://arxiv.org/abs/2202.06991
📄 Recommender Systems with Generative Retrieval: https://shashankrajput.github.io/Generative.pdf
Comments