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

Source: [Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference](<https://www.sota2.com/research/paper/68fa6cd31e209131cea3600e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:18:38.162Z

Authors: Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, Andr\\'e Freitas

Published: 2021-05-07T17:49:19.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2105.03417>)

[PDF](<https://arxiv.org/pdf/2105.03417.pdf>)
