Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Learning Models for Actionable Recourse
Authors: Alexis Ross, Himabindu Lakkaraju, Osbert Bastani
NeurIPS 2021 | Venue PDF | LLM Run Details | Input Tokens: 18,601 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,075 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the efficacy of our approach with extensive experiments on real data. |
| Researcher Affiliation | Collaboration | Alexis Ross Harvard University Allen Institute for Artificial Intelligence EMAIL Himabindu Lakkaraju Harvard University EMAIL Osbert Bastani University of Pennsylvania EMAIL |
| Pseudocode | No | The paper describes the algorithm steps using text and mathematical equations but does not include a distinct pseudocode or algorithm block. |
| Open Source Code | Yes | Our code is available at https://github.com/alexisjihyeross/adversarial_recourse. |
| Open Datasets | Yes | The first contains adult income information from the 1994 United States Census Bureau [Dua and Graff, 2017]... The second contains information collected by Propublica about criminal defendants compas recidivism scores [Angwin et al., 2016]... The third dataset represents bail outcomes from two different U.S. state courts from 1990-2009 [Schmidt and Witte, 1988]... The fourth dataset is the german credit dataset [Dua and Graff, 2017] |
| Dataset Splits | Yes | We randomly split each dataset into 80% train and 20% validation sets. |
| Hardware Specification | No | The paper does not specify the hardware used for running the experiments (e.g., CPU, GPU models, or memory). |
| Software Dependencies | No | The paper mentions software like 'alibi implementation' and 'LIME' but does not provide specific version numbers for these or other dependencies. |
| Experiment Setup | Yes | All models are neural networks with 3 100-node hidden layers, dropout probability 0.3, and tanh activations. For evaluation, we choose the epoch achieving the highest validation F1 score. We experimented with λ values between 0.0 to 2.0 in increments of 0.2... we set δmax = 0.75 after standardizing features. |