Direct optimization of F-measure for retrieval-based personal question answering
Recent advances in spoken language technologies and the introduction of many customer facing products, have given rise to a wide customer reliance on smart personal assistants for many of their daily tasks. In this paper, we present a system to reduce users' cognitive load by extending personal assistants with long-term personal memory where users can store and retrieve by voice, arbitrary pieces of information. The problem is framed as a neural retrieval based question answering system where answers are selected from previously stored user memories. We propose to directly optimize the end-to-end retrieval performance, measured by the F1-score, using reinforcement learning, leading to better performance on our experimental test set(s).
Code (0)
등록된 구현이 없습니다.
Tasks
Question Answeringreinforcement-learningReinforcement Learning (RL)RetrievalSimilar Papers 제목 키워드 기반
Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering
Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context. Existing state-of-the-art methods primarily rely on retrieval-au…
Reinforcement LearningQuestion AnsweringLSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration
Cloud-device collaboration leverages on-cloud Large Language Models (LLMs) for handling public user queries and on-device Small Language Models (SLMs) for processing private user data, collectively forming a powerful and…
Privacy PreservingRAGRetrievalRetrieval-augmented GenerationA Personalized Dense Retrieval Framework for Unified Information Access
Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the in…
Information RetrievalQuestion AnsweringRetrievalOptimization Methods for Personalizing Large Language Models through Retrieval Augmentation
This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains. We propose the first attempt to optimize …
Knowledge DistillationLanguage ModelingLanguage ModellingRetrievalERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization
Retrieval-augmented generation (RAG) for language models significantly improves language understanding systems. The basic retrieval-then-read pipeline of response generation has evolved into a more extended process due t…
Question AnsweringRAGResponse GenerationRetrieval+1