mlsanityData to 7 Oct 2026

Interlocking-free Selective Rationalization Through Genetic-based Learning

arXiv 2412.10312 ↗First posted 13 Dec 2024cs.LG cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

A popular end-to-end architecture for selective rationalization is the select-then-predict pipeline, comprising a generator to extract highlights fed to a predictor. Such a cooperative system suffers from suboptimal equilibrium minima due to the dominance of one of the two modules, a phenomenon known as interlocking. While several contributions aimed at addressing interlocking, they only mitigate its effect, often by introducing feature-based heuristics, sampling, and ad-hoc regularizations. We present GenSPP, the first interlocking-free architecture for selective rationalization that does not require any learning overhead, as the above-mentioned. GenSPP avoids interlocking by performing disjoint training of the generator and predictor via genetic global search. Experiments on a synthetic and a real-world benchmark show that our model outperforms several state-of-the-art competitors.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 54 references that are in the map. First posted on arXiv 13 Dec 2024.

Builds on

27 of 54 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Layer Normalizationcited by 5,579
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  6. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  7. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 521
  8. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 403
  9. 2016Rationalizing Neural Predictionscited by 281
  10. 2021Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detectioncited by 258
  11. 2020Invariant Rationalizationcited by 131
  12. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
15 more
  1. 2017Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agentscited by 107
  2. 2020An Information Bottleneck Approach for Controlling Conciseness in Rationale Extractioncited by 69
  3. 2018Deriving Machine Attention from Human Rationalescited by 54
  4. 2022CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checkingcited by 37
  5. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  6. 2020Neuroevolution in Deep Neural Networks: Current Trends and Future Challengescited by 33
  7. 2019A Game Theoretic Approach to Class-wise Selective Rationalizationcited by 32
  8. 2023D-Separation for Causal Self-Explanationcited by 21
  9. 2023Enhancing the Rationale-Input Alignment for Self-explaining Rationalizationcited by 15
  10. 2021Distribution Matching for Rationalizationcited by 14
  11. 2023Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraintcited by 14
  12. 2020Correspondence between neuroevolution and gradient descentcited by 11
  13. 2024Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalizationcited by 11
  14. 2023Rationalizing Predictions by Adversarial Information Calibrationcited by 4
  15. 2022Interlock-Free Multi-Aspect Rationalization for Text Classificationcited by 1

Built on by

Not cited yet.