Researchers from NYU and Meta AI Studies Improving Social Conversational Agents by Learning from Natural Dialogue between Users and a Deployed Model, without Extra Annotations

Human input is a key tactic for improving social dialogue models. In reinforcement learning with human feedback, when many human annotations are required to guarantee a satisfactory reward function, there has been tremendous improvement in learning from feedback. The sources of feedback include numerical scores, rankings, or comments in natural language from users about a […]

The post Researchers from NYU and Meta AI Studies Improving Social Conversational Agents by Learning from Natural Dialogue between Users and a Deployed Model, …

agents ai shorts annotations applications artificial intelligence conversational conversational agents dialogue editors pick extra feedback function human human feedback improvement language model large language model machine learning meta meta ai natural nyu reinforcement reinforcement learning researchers social staff studies tech news technology