Summary of Does Faithfulness Conflict with Plausibility? An Empirical Study in Explainable Ai Across Nlp Tasks, by Xiaolei Lu et al.
Does Faithfulness Conflict with Plausibility? An Empirical Study in Explainable AI across NLP Tasks
by Xiaolei Lu, Jianghong Ma
First submitted to arxiv on: 29 Mar 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed explainability algorithms aim to balance faithfulness and plausibility when interpreting AI decision-making processes. By comparing selected methods against expert-level interpretations across three NLP tasks, the study finds that traditional perturbation-based methods like Shapley value and LIME can achieve high levels of both faithfulness and plausibility. This suggests that explainability algorithms should optimize for dual objectives to provide accurate and accessible explanations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The research aims to improve AI decision-making by balancing two important factors: accuracy and user understanding. The study compares different methods used to explain AI decisions with expert opinions on three tasks: sentiment analysis, intent detection, and topic labeling. The results show that some methods are better at providing accurate and easy-to-understand explanations. |
Keywords
» Artificial intelligence » Intent detection » Nlp
