Information Retrieval
Information retrieval (IR) focuses on efficiently finding relevant documents or information within large datasets in response to user queries. Current research emphasizes improving retrieval accuracy and efficiency through advancements in semantic understanding, particularly using multimodal data (text, images, tables) and advanced embedding models within retrieval-augmented generation (RAG) frameworks. These improvements are crucial for various applications, including search engines, question answering systems, and knowledge-based applications across diverse domains like healthcare and legal research, ultimately enhancing access to and understanding of information.
Papers
Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
Kunal Sawarkar, Abhilasha Mangal, Shivam Raj Solanki
FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
Orion Weller, Benjamin Chang, Sean MacAvaney, Kyle Lo, Arman Cohan, Benjamin Van Durme, Dawn Lawrie, Luca Soldaini
From Keywords to Structured Summaries: Streamlining Scholarly Information Access
Mahsa Shamsabadi, Jennifer D'Souza
INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models
Hanseok Oh, Hyunji Lee, Seonghyeon Ye, Haebin Shin, Hansol Jang, Changwook Jun, Minjoon Seo
Assessing generalization capability of text ranking models in Polish
Sławomir Dadas, Małgorzata Grębowiec