Embodied agents need to be able to interact in natural language – understanding task descriptions and asking appropriate follow up questions to obtain necessary information to be effective at successfully accomplishing tasks for a wide range of users.
Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations.
no code implementations • 9 Aug 2023 • Hangjie Shi, Leslie Ball, Govind Thattai, Desheng Zhang, Lucy Hu, Qiaozi Gao, Suhaila Shakiah, Xiaofeng Gao, Aishwarya Padmakumar, Bofei Yang, Cadence Chung, Dinakar Guthy, Gaurav Sukhatme, Karthika Arumugam, Matthew Wen, Osman Ipek, Patrick Lange, Rohan Khanna, Shreyas Pansare, Vasu Sharma, Chao Zhang, Cris Flagg, Daniel Pressel, Lavina Vaz, Luke Dai, Prasoon Goyal, Sattvik Sahai, Shaohua Liu, Yao Lu, Anna Gottardi, Shui Hu, Yang Liu, Dilek Hakkani-Tur, Kate Bland, Heather Rocker, James Jeun, Yadunandana Rao, Michael Johnston, Akshaya Iyengar, Arindam Mandal, Prem Natarajan, Reza Ghanadan
The Alexa Prize program has empowered numerous university students to explore, experiment, and showcase their talents in building conversational agents through challenges like the SocialBot Grand Challenge and the TaskBot Challenge.
Task planning is an important component of traditional robotics systems enabling robots to compose fine grained skills to perform more complex tasks.
Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters.
Embodied agents need to be able to interact in natural language understanding task descriptions and asking appropriate follow up questions to obtain necessary information to be effective at successfully accomplishing tasks for a wide range of users.
Natural language guided embodied task completion is a challenging problem since it requires understanding natural language instructions, aligning them with egocentric visual observations, and choosing appropriate actions to execute in the environment to produce desired changes.
We demonstrate the benefit of our Conv-FEVER dataset by showing that the models trained on this data perform reasonably well to detect factually inconsistent responses with respect to the provided knowledge through evaluation on our human annotated data.
Robots operating in human spaces must be able to engage in natural language interaction with people, both understanding and executing instructions, and using conversation to resolve ambiguity and recover from mistakes.
We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data.
Dialog systems research has primarily been focused around two main types of applications - task-oriented dialog systems that learn to use clarification to aid in understanding a goal, and open-ended dialog systems that are expected to carry out unconstrained "chit chat" conversations.
Intelligent systems need to be able to recover from mistakes, resolve uncertainty, and adapt to novel concepts not seen during training.
Natural language understanding for robotics can require substantial domain- and platform-specific engineering.
Active learning identifies data points to label that are expected to be the most useful in improving a supervised model.
Natural language understanding and dialog management are two integral components of interactive dialog systems.