Detailed Information

Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational Systems

Cited 0 time in Web of Science Cited 0 time in Scopus

Ahuja, Sarthak; Kachuee, Mohammad; Sheikholeslami, Fateme; Liu, Weiqing; Do, Jae Young

Issue Date
Association for Computational Linguistics (ACL)
Association for Computational Linguistics (ACL). Annual Meeting Conference Proceedings, Vol.5, pp.361-367
Off-Policy reinforcement learning has been a driving force for the state-of-the-art conversational AIs leading to more natural human-agent interactions and improving the user satisfaction for goal-oriented agents. However, in large-scale commercial settings, it is often challenging to balance between policy improvements and experience continuity on the broad spectrum of applications handled by such system. In the literature, off-policy evaluation and guard-railing on aggregate statistics has been commonly used to address this problem. In this paper, we propose a method for curating and leveraging high-precision samples sourced from historical regression incident reports to validate, safe-guard, and improve policies prior to the online deployment. We conducted extensive experiments using data from a real-world conversational system and actual regression incidents. The proposed method is currently deployed in our production system to protect customers against broken experiences and enable long-term policy improvements.
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Related Researcher

  • College of Engineering
  • Department of Electrical and Computer Engineering
Research Area AI 애플리케이션을 위한 알고리즘-시스템 공동 설계, AI-powered Big Data Management, Generative AI, Large Language Model, ML, 고성능 대규모 AI 데이터 분석 및 처리, 모달 AI


Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.