arXiv:2305.12473
공식 코드 · Papers with Code
Continually Improving Extractive QA via Human Feedback
원문 초록
We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask questions, receive model-predicted answers, and provide feedback. We conduct experiments involving thousands of user interactions under diverse setups to broaden the understanding of learning from feedback over time. Our experiments show effective improvement from user feedback of extractive QA models over time across different data regimes, including significant potential for domain adaptation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
From Roots to Rewards: Dynamic Tree Reasoning with RL
Describe Anything Model for Visual Question Answering on Text-rich Images
Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation
Warehouse Spatial Question Answering with LLM Agent
UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions
L0: Reinforcement Learning to Become General Agents
토론
이 논문과 연결된 포럼 글이 아직 없습니다.