Tailoring self-rationalizers with multi-reward distillation
Large language models (LMs) are capable of generating free-text rationales to aid question
answering. However, prior work 1) suggests that useful self-rationalization is emergent only …
answering. However, prior work 1) suggests that useful self-rationalization is emergent only …
D-separation for causal self-explanation
Rationalization aims to strengthen the interpretability of NLP models by extracting a subset
of human-intelligible pieces of their inputting texts. Conventional works generally employ the …
of human-intelligible pieces of their inputting texts. Conventional works generally employ the …
MGR: multi-generator based rationalization
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP
model in which the generator selects a subset of human-intelligible pieces of the input text to …
model in which the generator selects a subset of human-intelligible pieces of the input text to …
CAVE: Controllable Authorship Verification Explanations
Authorship Verification (AV)(do two documents have the same author?) is essential in many
sensitive real-life applications. AV is often used in proprietary domains that require a private …
sensitive real-life applications. AV is often used in proprietary domains that require a private …
AGR: Reinforced causal agent-guided self-explaining rationalization
Y Zhao, Z Wang, X Li, J Liang, R Li - Proceedings of the 62nd …, 2024 - aclanthology.org
Most existing rationalization approaches are susceptible to degeneration accumulation due
to a lack of effective control over the learning direction of the model during training. To …
to a lack of effective control over the learning direction of the model during training. To …
Mare: Multi-aspect rationale extractor on unsupervised rationale extraction
Unsupervised rationale extraction aims to extract text snippets to support model predictions
without explicit rationale annotation. Researchers have made many efforts to solve this task …
without explicit rationale annotation. Researchers have made many efforts to solve this task …
Pde+: Enhancing generalization via pde with adaptive distributional diffusion
The generalization of neural networks is a central challenge in machine learning, especially
concerning the performance under distributions that differ from training ones. Current …
concerning the performance under distributions that differ from training ones. Current …
Interventional rationalization
Selective rationalizations improve the explainability of neural networks by selecting a
subsequence of the input (ie, rationales) to explain the prediction results. Although existing …
subsequence of the input (ie, rationales) to explain the prediction results. Although existing …
Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
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 extraction is the …
rationales from the full input. The most widely used criterion for rationale extraction is the …
Interlocking-free Selective Rationalization Through Genetic-based Learning
F Ruggeri, G Signorelli - arXiv preprint arXiv:2412.10312, 2024 - arxiv.org
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 …
pipeline, comprising a generator to extract highlights fed to a predictor. Such a cooperative …