paper-with-me

홈 › Papers

A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference

2024-04-03 · Mokanarangan Thayaparan, Marco Valentino, André Freitas

Integer Linear Programming (ILP) has been proposed as a formalism for encoding precise structural and semantic constraints for Natural Language Inference (NLI). However, traditional ILP frameworks are non-differentiable, posing critical challenges for the integration of continuous language representations based on deep learning. In this paper, we introduce a novel approach, named Diff-Comb Explainer, a neuro-symbolic architecture for explanation-based NLI based on Differentiable BlackBox Combinatorial Solvers (DBCS). Differently from existing neuro-symbolic solvers, Diff-Comb Explainer does not necessitate a continuous relaxation of the semantic constraints, enabling a direct, more precise, and efficient incorporation of neural representations into the ILP formulation. Our experiments demonstrate that Diff-Comb Explainer achieves superior performance when compared to conventional ILP solvers, neuro-symbolic black-box solvers, and Transformer-based encoders. Moreover, a deeper analysis reveals that Diff-Comb Explainer can significantly improve the precision, consistency, and faithfulness of the constructed explanations, opening new opportunities for research on neuro-symbolic architectures for explainable and transparent NLI in complex domains.

📄 PDF Abstract BibTeX arXiv:2404.02625

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Inference

Similar Papers 제목 키워드 기반

Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers

2022-08-05 · Mokanarangan Thayaparan, Marco Valentino, André Freitas

Integer Linear Programming (ILP) provides a viable mechanism to encode explicit and controllable assumptions about explainable multi-hop inference with natural language. However, an ILP formulation is non-differentiable …

Efficient Search for Diverse Coherent Explanations

2019-01-02 · Chris Russell

This paper proposes new search algorithms for counterfactual explanations based upon mixed integer programming. We are concerned with complex data in which variables may take any value from a contiguous range or an addit…

counterfactual

Differentiable Integer Linear Programming is not Differentiable & it's not a mere technical problem

2026-01-25 · Thanawat Sornwanee arxiv

We show how the differentiability method employed in the paper ``Differentiable Integer Linear Programming'', Geng, et al., 2025 as shown in its theorem 5 is incorrect. Moreover, there already exists some downstream work…

Differentiable Initialization-Accelerated CPU-GPU Hybrid Combinatorial Scheduling

2026-03-30 · Mingju Liu, Jiaqi Yin, Alvaro Velasquez, Cunxi Yu arxiv

This paper presents a hybrid CPU-GPU framework for solving combinatorial scheduling problems formulated as Integer Linear Programming (ILP). While scheduling underpins many optimization tasks in computing systems, solvin…

Lossy compression of matrices by black-box optimisation of mixed integer nonlinear programming

2022-04-22 · Tadashi Kadowaki, Mitsuru Ambai

In edge computing, suppressing data size is a challenge for machine learning models that perform complex tasks such as autonomous driving, in which computational resources (speed, memory size and power) are limited. Effi…

Autonomous DrivingEdge-computing