Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference

TL;DR

Diff-Explainer introduces a hybrid framework combining differentiable convex optimization with neural models to enhance explainable multi-hop question answering, improving performance and interpretability.

Contribution

It is the first to integrate explicit constraints with neural architectures via differentiable convex optimization for explainable multi-hop inference.

Findings

Significant performance improvements over non-differentiable ILP solvers (8.91%-13.3%).

Achieves strong results compared to standalone Transformers.

Provides structured explanations alongside predictions.

Abstract

This paper presents Diff-Explainer, the first hybrid framework for explainable multi-hop inference that integrates explicit constraints with neural architectures through differentiable convex optimization. Specifically, Diff-Explainer allows for the fine-tuning of neural representations within a constrained optimization framework to answer and explain multi-hop questions in natural language. To demonstrate the efficacy of the hybrid framework, we combine existing ILP-based solvers for multi-hop Question Answering (QA) with Transformer-based representations. An extensive empirical evaluation on scientific and commonsense QA tasks demonstrates that the integration of explicit constraints in an end-to-end differentiable framework can significantly improve the performance of non-differentiable ILP solvers (8.91% - 13.3%). Moreover, additional analysis reveals that Diff-Explainer is able to achieve strong performance when compared to standalone Transformers and previous multi-hop approaches while still providing structured explanations in support of its predictions.