2 papers
cs.LG2024
Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
Wei Liu, Zhiying Deng, Zhongyu Niu +4
An important line of research in the field of explainability is to extract a small subset of crucial rationales from the full input. The most widely used criterion for rationale ex…
cs.CL2024
Adversarial Attack for Explanation Robustness of Rationalization Models
Yuankai Zhang, Lingxiao Kong, Haozhao Wang +4
Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area i…