Explanation-based Human Debugging Of NLP Models: A Survey | Awesome LLM Papers Add your paper to Awesome LLM Papers

Awesome LLM Papers

A continuously updated collection of research papers on LLMs.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Explanation-based Human Debugging Of NLP Models: A Survey

Piyawat Lertvittayakumjorn, Francesca Toni . Transactions of the Association for Computational Linguistics 2021 – 42 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
ACL Compositional Generalization Content Enrichment Interdisciplinary Approaches Survey Paper TACL Training Techniques Variational Autoencoders Visual Question Answering

Debugging a machine learning model is hard since the bug usually involves the training data and the learning process. This becomes even harder for an opaque deep learning model if we have no clue about how the model actually works. In this survey, we review papers that exploit explanations to enable humans to give feedback and debug NLP models. We call this problem explanation-based human debugging (EBHD). In particular, we categorize and discuss existing work along three dimensions of EBHD (the bug context, the workflow, and the experimental setting), compile findings on how EBHD components affect the feedback providers, and highlight open problems that could be future research directions.

Similar Work