Contrastive Learning Reduces Hallucination in Conversations

Understand

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems.

• However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking statements that are irrelevant or factually incorrect.
• To address this problem, we propose a contrastive learning scheme, named MixCL.
• A novel mixed contrastive objective is proposed to explicitly optimize the implicit knowledge elicitation process of LMs, and thus reduce their hallucination in conversations.