Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making
This addresses the issue of untrustworthy explanations in black-box models for NLP users, though it is incremental as it builds on existing rationale generation methods.
The paper tackles the problem of unreliable links between generated rationales and model decisions in explainable AI, proposing a two-stage framework that establishes a more reliable connection and achieves competitive results on five reasoning datasets from the ERASER benchmark.
Explaining black-box model behavior with natural language has achieved impressive results in various NLP tasks. Recent research has explored the utilization of subsequences from the input text as a rationale, providing users with evidence to support the model decision. Although existing frameworks excel in generating high-quality rationales while achieving high task performance, they neglect to account for the unreliable link between the generated rationale and model decision. In simpler terms, a model may make correct decisions while attributing wrong rationales, or make poor decisions while attributing correct rationales. To mitigate this issue, we propose a unified two-stage framework known as Self-Attribution and Decision-Making (SADM). Through extensive experiments on five reasoning datasets from the ERASER benchmark, we demonstrate that our framework not only establishes a more reliable link between the generated rationale and model decision but also achieves competitive results in task performance and the quality of rationale. Furthermore, we explore the potential of our framework in semi-supervised scenarios.