Invariant Rationalization
Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction. A typical rationalization criterion, i.e. maximum mutual information (MMI), finds the rationale that maximizes the prediction performance based only on the rationale. However, MMI can be problematic because it picks up spurious correlations between the input features and the output. Instead, we introduce a game-theoretic invariant rationalization criterion where the rationales are constrained to enable the same predictor to be optimal across different environments. We show both theoretically and empirically that the proposed rationales can rule out spurious correlations, generalize better to different test scenarios, and align better with human judgments. Our data and code are available.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Fine-grained Graph Rationalization
Rationale discovery is defined as finding a subset of the input data that maximally supports the prediction of downstream tasks. In the context of graph machine learning, graph rationale is defined to locate the critical…
PredictionMitigating Biases in Toxic Language Detection through Invariant Rationalization
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, …
Natural Language UnderstandingCooperative Classification and Rationalization for Graph Generalization
Graph Neural Networks (GNNs) have achieved impressive results in graph classification tasks, but they struggle to generalize effectively when faced with out-of-distribution (OOD) data. Several approaches have been propos…
ClassificationGraph ClassificationKnowledge DistillationFaithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges
Large language models (LLMs) are increasingly used as automatic judges for summarization and dialogue evaluation. Prior work has documented biases such as position, verbosity, and style preferences, but largely focuses o…
Dialogue EvaluationRationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations
We introduce AI rationalization, an approach for generating explanations of autonomous system behavior as if a human had performed the behavior. We describe a rationalization technique that uses neural machine translatio…
Explanation GenerationMachine TranslationTranslation