SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactuals
Not on the map. Why?
Abstract (arXiv)
We introduce SparcAssist, a general-purpose risk assessment tool for the machine learning models trained for language tasks. It evaluates models' risk by inspecting their behavior on counterfactuals, namely out-of-distribution instances generated based on the given data instance. The counterfactuals are generated by replacing tokens in rational subsequences identified by ExPred, while the replacements are retrieved using HotFlip or Masked-Language-Model-based algorithms. The main purpose of our system is to help the human annotators to assess the model's risk on deployment. The counterfactual instances generated during the assessment are the by-product and can be used to train more robust NLP models in the future.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 39 references that are in the map. First posted on arXiv 3 May 2022.
Builds on
24 of 39 references.
References · 24
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
- 2021GPT Understands, Toocited by 716
- 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
- 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
- 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 249
- 2019Explainable Machine Learning in Deploymentcited by 211
- 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 106
12 more
- 2020Imitation Attacks and Defenses for Black-box Machine Translation Systemscited by 81
- 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
- 2020When is invariance useful in an Out-of-Distribution Generalization problem ?cited by 52
- 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 35
- 2021Explain and Predict, and then Predict Againcited by 29
- 2018EXS: Explainable Search Using Local Model Agnostic Interpretabilitycited by 18
- 2021The Irrationality of Neural Rationale Modelscited by 16
- 2018Posthoc Interpretability of Learning to Rank Models using Secondary Training Datacited by 10
- 2021Towards Benchmarking the Utility of Explanations for Model Debuggingcited by 10
- 2017Tempas: Temporal Archive Search Based on Tagscited by 5
- 2018Discovering Entities with Just a Little Help from Youcited by 4
- 2021FaxPlainAC: A Fact-Checking Tool Based on EXPLAINable Models with HumAn Correction in the Loopcited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.