Publication Type

Journal Article

Version

publishedVersion

Publication Date

2-2026

Abstract

Rationalization, a data-centric framework, aims to build self-explanatory models to explain the prediction outcome by generating a subset of human-intelligible pieces of the input data. It involves a cooperative game model where a generator generates the most human-intelligible parts of the input (i.e., rationales), followed by a predictor that makes predictions based on these generated rationales. Conventional rationalization methods typically impose constraints via regularization terms to calibrate or penalize undesired generation. However, these methods are suffering from a problem called mode collapse, in which the predictor produces correct predictions yet the generator consistently outputs rationales with collapsed patterns. Moreover, existing studies are typically designed separately for specific collapsed patterns, lacking a unified consideration. In this paper, we systematically revisit cooperative rationalization from a novel game-theoretic perspective and identify the fundamental cause of this problem: the generator no longer tends to explore new strategies to uncover informative rationales, ultimately leading the system to converge to a suboptimal game equilibrium (correct predictions versus collapsed rationales). To solve this problem, we then propose a novel approach, Game-theoretic Policy Optimization oriented RATionalization (PoRat), which progressively introduces policy interventions to address the game equilibrium in the cooperative game process, thereby guiding the model toward a more optimal solution state. We theoretically analyse the cause of such a suboptimal equilibrium and prove the feasibility of the proposed method. Furthermore, we validate our method on nine widely used real-world datasets and two synthetic settings, where PoRat achieves up to 8.1% performance improvements over existing state-of-the-art methods.

Keywords

Data-centric Explainability, Self-explanation, Rationale Mining, Game-theoretic Policy Optimization

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Publication

IEEE Transactions on Knowledge and Data Engineering

Volume

38

Issue

2

First Page

1159

Last Page

1173

ISSN

1041-4347

Identifier

10.1109/TKDE.2025.3638864

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TKDE.2025.3638864

Download

Share

COinS