Anshita Gupta


2023

pdf
Editing Common Sense in Transformers
Anshita Gupta | Debanjan Mondal | Akshay Sheshadri | Wenlong Zhao | Xiang Li | Sarah Wiegreffe | Niket Tandon
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Editing model parameters directly in Transformers makes updating open-source transformer-based models possible without re-training. However, these editing methods have only been evaluated on statements about encyclopedic knowledge with a single correct answer. Commonsense knowledge with multiple correct answers, e.g., an apple can be green or red but not transparent, has not been studied but is as essential for enhancing transformers’ reliability and usefulness. In this paper, we investigate whether commonsense judgments are causally associated with localized, editable parameters in Transformers, and we provide an affirmative answer. We find that directly applying the MEMIT editing algorithm results in sub-par performance and improve it for the commonsense domain by varying edit tokens and improving the layer selection strategy, i.e., MEMITCSK. GPT-2 Large and XL models edited using MEMITCSK outperform best-fine-tuned baselines by 10.97% and 10.73% F1 scores on PEP3k and 20Q datasets. In addition, we propose a novel evaluation dataset, PROBE\ SET, that contains unaffected and affected neighborhoods, affected paraphrases, and affected reasoning challenges. MEMITCSK performs well across the metrics while fine-tuning baselines show significant trade-offs between unaffected and affected metrics. These results suggest a compelling future direction for incorporating feedback about common sense into Transformers through direct model editing.