Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge

An example of the probing tasks studied in this paper.


Large language models (LLMs) have been widely studied for their ability to store and utilize positive knowledge. However, negative knowledge, such as “lions don’t live in the ocean”, is also ubiquitous in the world but rarely mentioned explicitly in the text. What do LLMs know about negative knowledge? This work examines the ability of LLMs to negative commonsense knowledge. We design a constrained keywords-to-sentence generation task (CG) and a Boolean question-answering task (QA) to probe LLMs. Our experiments reveal that LLMs frequently fail to generate valid sentences grounded in negative commonsense knowledge, yet they can correctly answer polar yes-or-no questions. We term this phenomenon the belief conflict of LLMs. Our further analysis shows that statistical shortcuts and negation reporting bias from language modeling pre-training cause this conflict.

In The 61th Annual Meeting of the Association for Computational Linguistics (ACL 2023)
Jiangjie Chen
Jiangjie Chen
Ph.D. Candidate (on the job market!)

His research interests mainly include natural language reasoning and large language models.