Sumit's Diary

This final post of the Adaptive RAG series explores methods that treat adaptive retrieval as a learned skill and explicitly teach models when to retrieve.

This post introduces techniques that probe the LLM’s internal confidence and knowledge boundaries.

Building on part 1’s exploration of naive RAG’s limitations, this post introduces adaptive retrieval frameworks and pre-generation retrieval decision-making methods that determine if retrieval is truly necessary.

Retrieval-Augmented Generation (RAG) isn’t a silver bullet.

Learned embeddings often suffer from ’embedding collapse’, where they occupy only a small subspace of the available dimensions.

This article provides an introduction to online advertising systems and explores research work that incorporates ads into the LLM responses to user queries of commercial nature.

This article continues the discussion on the evolution of multi-task learning-based large-scale recommender systems.

This article introduces the multi-task learning paradigm adopted by various large-scale video recommender systems.

This article provides an introduction and literature review for multi-task learning based recommender systems.

Modeling users’ past historical interactions or behavior sequences is an essential task for domains like recommender systems, click-through rate prediction, targeted advertisement, and more.