CDConv: A Benchmark for Contradiction Detection in Chinese Conversations
This addresses the critical issue of dialogue contradiction for developers of Chinese open-domain dialogue systems, though it is incremental as it focuses on benchmarking.
The authors tackled the problem of detecting contradictions in Chinese conversations by creating CDConv, a benchmark with 12K annotated multi-turn dialogues, and found that state-of-the-art chatbots are easily goaded into making contradictions.
Dialogue contradiction is a critical issue in open-domain dialogue systems. The contextualization nature of conversations makes dialogue contradiction detection rather challenging. In this work, we propose a benchmark for Contradiction Detection in Chinese Conversations, namely CDConv. It contains 12K multi-turn conversations annotated with three typical contradiction categories: Intra-sentence Contradiction, Role Confusion, and History Contradiction. To efficiently construct the CDConv conversations, we devise a series of methods for automatic conversation generation, which simulate common user behaviors that trigger chatbots to make contradictions. We conduct careful manual quality screening of the constructed conversations and show that state-of-the-art Chinese chatbots can be easily goaded into making contradictions. Experiments on CDConv show that properly modeling contextual information is critical for dialogue contradiction detection, but there are still unresolved challenges that require future research.