#multiturn

[moneymasteryhubonline]

Multi-turn conversations with Action-Based Contrastive Self-Training

Are action-based preferences necessary? One of the key factors of ACT is that the contrastive pairs highlight differences between conversational actions. In “ACT w/ Random Actions”, we additionally examine the importance of action selection by randomly sampling both the winning and losing action when constructing the preference pair, and observe this underperforms normal ACT. Do we need on-policy…