Towards Faithful Model Explanation in NLP: A Survey
Lyu, Qing, Apidianaki, Marianna, Callison-Burch, Chris
–arXiv.org Artificial Intelligence
End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to understand. This has given rise to numerous efforts towards model explainability in recent years. One desideratum of model explanation is faithfulness, i.e. an explanation should accurately represent the reasoning process behind the model's prediction. In this survey, we review over 110 model explanation methods in NLP through the lens of faithfulness. We first discuss the definition and evaluation of faithfulness, as well as its significance for explainability. We then introduce recent advances in faithful explanation, grouping existing approaches into five categories: similarity-based methods, analysis of model-internal structures, backpropagation-based methods, counterfactual intervention, and self-explanatory models. For each category, we synthesize its representative studies, strengths, and weaknesses. Finally, we summarize their common virtues and remaining challenges, and reflect on future work directions towards faithful explainability in NLP.
arXiv.org Artificial Intelligence
Jan-12-2024
- Country:
- South America > Chile
- Oceania > Australia
- Victoria > Melbourne (0.04)
- New South Wales > Sydney (0.04)
- North America
- Dominican Republic (0.04)
- United States
- Pennsylvania (0.04)
- Maryland > Baltimore (0.04)
- Texas > Travis County
- Austin (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- New York
- New York County > New York City (0.14)
- Richmond County > New York City (0.04)
- Queens County > New York City (0.04)
- Monroe County > Rochester (0.04)
- Kings County > New York City (0.04)
- Bronx County > New York City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Illinois > Cook County
- Chicago (0.04)
- California
- San Diego County > San Diego (0.04)
- Los Angeles County > Long Beach (0.04)
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.14)
- Europe
- Austria (0.04)
- Germany > Berlin (0.04)
- France (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Portugal > Lisbon
- Lisbon (0.04)
- Italy
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- United Kingdom
- Scotland > City of Glasgow
- Glasgow (0.04)
- England > Oxfordshire
- Oxford (0.04)
- Scotland > City of Glasgow
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia
- China > Hong Kong (0.04)
- Middle East
- Jordan (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Genre:
- Overview (1.00)
- Research Report > New Finding (0.67)
- Industry:
- Leisure & Entertainment (1.00)
- Health & Medicine (0.92)
- Education (0.67)
- Media > Film (0.46)
- Technology: