Retrieval-Enhanced Machine Learning

Abstract

Although information access systems have long supported people in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models. In this way, the core principles of indexing, representation, retrieval, and ranking can be applied and extended to substantially improve model generalization, scalability, robustness, and interpretability. We describe a generic retrieval-enhanced machine learning (REML) framework, which includes a number of existing models as special cases. REML challenges information retrieval conventions, presenting opportunities for novel advances in core areas, including optimization. The REML research agenda lays a foundation for a new style of information access research and paves a path towards advancing machine learning and artificial intelligence.

arXiv commentTo appear in proceedings of ACM SIGIR 2022

References in corpus (4)

• Learning Transferable Visual Models From Natural Language Supervision
• Deeper Text Understanding for IR with Contextual Neural Language Modeling
• Controllable Semantic Parsing via Retrieval Augmentation
• Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking

Cited by in corpus (8)

• Exploring the State of the Art in Legal QA Systems
• Exploring ChatGPT for Next-generation Information Retrieval: Opportunities and Challenges
• AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• An Approximate Algorithm for Maximum Inner Product Search over Streaming Sparse Vectors
• RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation
• A Canary in the AI Coal Mine: American Jews May Be Disproportionately Harmed by Intellectual Property Dispossession in Large Language Model Training
• ROMO: Retrieval-enhanced Offline Model-based Optimization