Search Results for author:
Found 14 papers, 5 papers with code
AXCEL: Automated eXplainable Consistency Evaluation using LLMs
We also evaluate the influence of underlying LLMs on prompt based metric performance and recalibrate the SOTA prompt-based metrics with the latest LLMs for fair comparison.
Effective Backdoor Mitigation Depends on the Pre-training Objective
In this work, we demonstrate that the efficacy of CleanCLIP in mitigating backdoors is highly dependent on the particular objective used during model pre-training.
Unveiling the Power of Self-Attention for Shipping Cost Prediction: The Rate Card Transformer
Shipping cost of these packages are used on the day of shipping (day 0) to estimate profitability of sales.
RecRec: Algorithmic Recourse for Recommender Systems
To the best of our knowledge, this work is the first to conceptualize and empirically test a generalized framework for generating recourses for recommender systems.
RecXplainer: Amortized Attribute-based Personalized Explanations for Recommender Systems
We evaluate RecXplainer on five real-world and large-scale recommendation datasets using five different kinds of recommender systems to demonstrate the efficacy of RecXplainer in capturing users' preferences over item attributes and using them to explain recommendations.
BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence
By perturbing the input variables in rank order of importance, the goal is to assess the sensitivity of the model's performance.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Counterfactual Explanations for Machine Learning: Challenges Revisited
Counterfactual explanations (CFEs) are an emerging technique under the umbrella of interpretability of machine learning (ML) models.
Pitfalls of Explainable ML: An Industry Perspective
The goal of explainable ML is to intuitively explain the predictions of a ML system, while adhering to the needs to various stakeholders.
Amortized Generation of Sequential Algorithmic Recourses for Black-box Models
We propose a novel stochastic-control-based approach that generates sequential ARs, that is, ARs that allow x to move stochastically and sequentially across intermediate states to a final state x'.
Removing biased data to improve fairness and accuracy
Machine learning models trained on such debiased data (a subset of the original training data) have low individual discrimination, often 0%.
ShapeFlow: Dynamic Shape Interpreter for TensorFlow
We present ShapeFlow, a dynamic abstract interpreter for TensorFlow which quickly catches tensor shape incompatibility errors, one of the most common bugs in deep learning code.
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders.
Benchmarking Symbolic Execution Using Constraint Problems -- Initial Results
We transform CSP benchmarks into C programs suitable for testing the reasoning capabilities of symbolic execution tools.
Software Engineering Logic in Computer Science I.2.0; I.2.1; I.2.3; I.2.4; I.2.8; I.2.11; D.2
