Hierarchical Expertise Level Modeling for User Specific Contrastive Explanations

Authors: Sarath Sreedharan, Siddharth Srivastava, Subbarao Kambhampati

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In our evaluation, we wanted to understand how effective our approaches were in terms of the conciseness of the explanations produced, the solution computation time and the usefulness of approximation. All three explanation methods discussed in this paper (blind, heuristic and greedy) were evaluated on five IPC benchmark domains[International Planning Competition, 2011].
Researcher Affiliation Academia Sarath Sreedharan, Siddharth Srivastava and Subbarao Kambhampati School of Computing, Informatics, and Decision Systems Engineering Arizona State University, Tempe, AZ 85281 USA { ssreedh3, siddharths, rao } @ asu.edu
Pseudocode Yes Algorithm 1 Greedy Algorithm for Generating b E
Open Source Code No The paper does not provide an explicit statement or a link to open-source code for the methodology described.
Open Datasets Yes All three explanation methods discussed in this paper (blind, heuristic and greedy) were evaluated on five IPC benchmark domains[International Planning Competition, 2011].
Dataset Splits No The paper mentions selecting problems from 'available test sets' or using 'standard problem generators' but does not provide specific percentages or counts for training, validation, or test data splits.
Hardware Specification No All the experiments detailed in this section were run on an Ubuntu workstation with 64G RAM.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names with specific version numbers) needed to replicate the experiment.
Experiment Setup Yes The lattice for each problem-domain pair was generated by randomly selecting 50% of domain predicates and then generating a fully connected proposition conserving lattice using that set of predicates. ... The foils were generated by selecting random models from the lattice and creating plans from these models that do not hold in the concrete model.