Towards Alleviating the Object Bias in Prompt Tuning-based Factual Knowledge Extraction

Abstract: Many works employed prompt tuning methods to automatically optimize prompt queries and extract the factual knowledge stored in Pretrained LLMs. In this paper, we observe that the optimized prompts, including discrete prompts and continuous prompts, exhibit undesirable object bias. To handle this problem, we propose a novel prompt tuning method called MeCoD. consisting of three modules: Prompt Encoder, Object Equalization and Biased Object Obstruction. Experimental results show that MeCoD can significantly reduce the object bias and at the same time improve accuracy of factual knowledge extraction.