COKE: A Cognitive Knowledge Graph for Machine Theory of Mind

Theory of mind (ToM) refers to humans' ability to understand and infer the desires, beliefs, and intentions of others. The acquisition of ToM plays a key role in humans' social cognition and interpersonal relations. Though indispensable for social intelligence, ToM is still lacking for modern AI and NLP systems since they cannot access the human mental state and cognitive process beneath the training corpus. To empower AI systems with the ToM ability and narrow the gap between them and humans, in this paper, we propose COKE: the first cognitive knowledge graph for machine theory of mind. Specifically, COKE formalizes ToM as a collection of 45k+ manually verified cognitive chains that characterize human mental activities and subsequent behavioral/affective responses when facing specific social circumstances. In addition, we further generalize COKE using LLMs and build a powerful generation model COLM tailored for cognitive reasoning. Experimental results in both automatic and human evaluation demonstrate the high quality of COKE, the superior ToM ability of COLM , and its potential to significantly enhance social applications. 042 will deliver an impressive speech (a mental activ-043 ity), feels joyful (an affective response), and has a 044 restful sleep tonight (a behavioral response). Here 045 ToM is instantiated as a chained cognitive process 046 that derives from our knowledge, experiences, and 047 memories (Harris et al., 1989). ToM is indispens-048 able to humans since it allows us to leverage our 049 own minds to simulate others', so as to achieve 050 efficient communication (Rabinowitz et al., 2018).