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

arXiv: https://arxiv.org/abs/2306.03378 · HTML: https://mlsanity.com/paper/2306.03378/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2023.

## Built on by (most cited first, 6 of 6)

- [Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models](https://mlsanity.com/paper/2310.16570/) (2023)
- [Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs](https://mlsanity.com/paper/2402.10612/) (2024)
- [The Queen of England is not England's Queen: On the Lack of Factual Coherency in PLMs](https://mlsanity.com/paper/2402.01453/) (2024)
- [UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing](https://mlsanity.com/paper/2404.01253/) (2024)
- [Enhancing Fact Retrieval in PLMs through Truthfulness](https://mlsanity.com/paper/2410.13562/) (2024)
- [Single LLM Debate, MoLaCE: Mixture of Latent Concept Experts Against Confirmation Bias](https://mlsanity.com/paper/2512.23518/) (2025)

## Abstract (arXiv)

Many works employed prompt tuning methods to automatically optimize prompt queries and extract the factual knowledge stored in Pretrained Language Models. 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.