Boosting Explainability through Selective Rationalization in Pre-trained Language Models

TL;DR

This paper introduces PLMR, a method that improves the explainability of pre-trained language models by splitting them into generator and predictor components, effectively addressing rationalization failures caused by token homogeneity.

Contribution

The paper proposes PLMR, a novel framework that enhances selective rationalization in PLMs by mitigating token homogeneity issues through model splitting and token pruning.

Findings

PLMR significantly improves rationalization quality on multiple datasets.

The method reduces token homogeneity and enhances interpretability.

Experimental results show better trustworthiness of explanations.

Abstract

The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects human-intelligible input subsets as rationales for predictions. Recent studies have shown that applying existing rationalization frameworks to PLMs will result in severe degeneration and failure problems, producing sub-optimal or meaningless rationales. Such failures severely damage trust in rationalization methods and constrain the application of rationalization techniques on PLMs. In this paper, we find that the homogeneity of tokens in the sentences produced by PLMs is the primary contributor to these problems. To address these challenges, we propose a method named Pre-trained Language Model's Rationalization (PLMR), which splits PLMs into a generator and a predictor to deal with NLP tasks while providing interpretable rationales. The generator in PLMR also alleviates homogeneity by pruning irrelevant tokens, while the predictor uses full-text information to standardize predictions. Experiments conducted on two widely used datasets across multiple PLMs demonstrate the effectiveness of the proposed method PLMR in addressing the challenge of applying selective rationalization to PLMs. Codes: https://github.com/ylb777/PLMR.