Explanation-Based Human Debugging of NLP Models: A Survey

By Piyawat Lertvittayakumjorn, Francesca Toni. 2021

90 citations recorded by the source corpus.

Abstract 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.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

Citations in the corpus

Can language models learn from explanations in context? (2022, methodology): “…(e.g. Wei et al., 2022; Reynolds and McDonell, 2021), as well as a huge variety of broader work beyond prompting on topics like training or tuning with explanations (e.g. Camburu et al., 2018; Ling et al., 2017; Hendricks et al., 2016; Narang et al., 2020; Lertvittayakumjorn and Toni, 2021).”
Tell me why! - Explanations support learning of relational and causal structure (2021, background): “Lertvittayakumjorn and Toni (2021) survey works on tuning NLP models using explanatory feedback on features, word-level attention, etc. Schramowski et al. (2020) highlight an in-triguing interactive-learning-from-feedback setting where an expert in the loop gives feedback which can be used for…”
Graph of Thoughts: Solving Elaborate Problems with Large Language Models (2023, background): “more extensive descriptions can be found in dedicated surveys [68, 40, 69, 34].”
Tell me why! Explanations support learning relational and causal structure (2021, background): “Lertvittayakumjorn & Toni (2021) survey works on tuning NLP models using explanatory feedback on features, word-level attention, etc. Schramowski et al. (2020) highlight an intriguing interactive-learning-from-feedback setting where an expert in the loop gives feedback which can be used for similar…”