
This repository contains the datasets and source code created for the scientific paper Reasoning-Grounded Natural Language Explanations for Language Models. Included files: decision_trees_v10.zip Synthetic dataset Generated using the included software generator logistic_regressors_v2.zip Synthetic dataset Generated using the included software generator mortgages_decision_tree_v4.zip Partially synthetic, partially anonymized dataset Partially generated using the included software generator Partially uses data from the (anonymized) public domain HMDA National Loan Level Dataset 2022 - Loan Application Records (LAR) dataset by Consumer Financial Protection Bureau (https://ffiec.cfpb.gov/data-publication/snapshot-national-loan-level-dataset/2022) source_code.zip Contains: The code used in the experiments described in the research paper The software generators used for creating the included datasets Instructions on how to install and run the source code are written in the README in the source code ZIP
Machine Learning, Large Language Models, Explainable AI, Reasoning, Natural Language Explanations
Machine Learning, Large Language Models, Explainable AI, Reasoning, Natural Language Explanations
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
