mlsanityData to 7 Oct 2026

Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery

arXiv 2403.07955 ↗First posted 12 Mar 2024cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

The remarkable success in neural networks provokes the selective rationalization. It explains the prediction results by identifying a small subset of the inputs sufficient to support them. Since existing methods still suffer from adopting the shortcuts in data to compose rationales and limited large-scale annotated rationales by human, in this paper, we propose a Shortcuts-fused Selective Rationalization (SSR) method, which boosts the rationalization by discovering and exploiting potential shortcuts. Specifically, SSR first designs a shortcuts discovery approach to detect several potential shortcuts. Then, by introducing the identified shortcuts, we propose two strategies to mitigate the problem of utilizing shortcuts to compose rationales. Finally, we develop two data augmentations methods to close the gap in the number of annotated rationales. Extensive experimental results on real-world datasets clearly validate the effectiveness of our proposed method.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 12 Mar 2024.

Builds on

31 of 44 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2017Billion-scale similarity search with GPUscited by 2,477
  5. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,140
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  7. 2016Deep Variational Information Bottleneckcited by 915
  8. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  9. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 293
  10. 2016Rationalizing Neural Predictionscited by 281
  11. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  12. 2020Invariant Rationalizationcited by 131
19 more
  1. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  2. 2019Rethinking Cooperative Rationalization: Introspective Extraction and Complement Controlcited by 96
  3. 2020An Information Bottleneck Approach for Controlling Conciseness in Rationale Extractioncited by 69
  4. 2019Inferring Which Medical Treatments Work from Reports of Clinical Trialscited by 63
  5. 2018Deriving Machine Attention from Human Rationalescited by 54
  6. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  7. 2020Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifierscited by 35
  8. 2019A Game Theoretic Approach to Class-wise Selective Rationalizationcited by 32
  9. 2021UNIREX: A Unified Learning Framework for Language Model Rationale Extractioncited by 32
  10. 2020Learning from the Best: Rationalizing Prediction by Adversarial Information Calibrationcited by 25
  11. 2021What to Learn, and How: Toward Effective Learning from Rationalescited by 25
  12. 2020FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generationcited by 21
  13. 2023D-Separation for Causal Self-Explanationcited by 21
  14. 2021Rationalization through Conceptscited by 19
  15. 2020Weakly- and Semi-supervised Evidence Extractioncited by 16
  16. 2021Distribution Matching for Rationalizationcited by 14
  17. 2021Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLUcited by 13
  18. 2021Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extractioncited by 11
  19. 2024Cooperative Classification and Rationalization for Graph Generalizationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 2.

8 papers.

  1. 2025Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associationscited by 14
  2. 2024Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalizationcited by 11
  3. 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Modelscited by 5
  4. 2026GNN Explanations that do not Explain and How to find Themcited by 3
  5. 2025Boosting Explainability through Selective Rationalization in Pre-trained Language Modelscited by 2
  6. 2025Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalizationcited by 1
  7. 2024The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Mattercited by 0
  8. 2026Learn from A Rationalist: Distilling Intermediate Interpretable Rationalescited by 0