Search Results for author:
Found 28 papers, 7 papers with code
KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking
This paper introduces KnowHalu, a novel approach for detecting hallucinations in text generated by large language models (LLMs), utilizing step-wise reasoning, multi-formulation query, multi-form knowledge for factual checking, and fusion-based detection mechanism.
REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values
In this paper, we introduce the problem of feature \emph{reselection}, so that features can be selected with respect to secondary model performance characteristics efficiently even after a feature selection process has been done with respect to a primary objective.
Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education
We assess LLMs' zero-shot performance in creating domain-specific concept graphs and introduce TutorQA, a new expert-verified NLP-focused benchmark for scientific graph reasoning and QA.
Knowledge-Aware Neuron Interpretation for Scene Classification
Specifically, for concept completeness, we present core concepts of a scene based on knowledge graph, ConceptNet, to gauge the completeness of concepts.
Better Explain Transformers by Illuminating Important Information
Transformer-based models excel in various natural language processing (NLP) tasks, attracting countless efforts to explain their inner workings.
Privacy-Preserving Algorithmic Recourse
We observe that PrivRecourse can provide paths that are private and realistic.
Fair Coresets via Optimal Transport
In this work, we present fair Wasserstein coresets (FWC), a novel coreset approach which generates fair synthetic representative samples along with sample-level weights to be used in downstream learning tasks.
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Causal Analysis for Robust Interpretability of Neural Networks
The result is task-specific causal explanatory graphs that can audit model behavior and express the actual causes underlying its performance.
Task Adaptive Feature Transformation for One-Shot Learning
We introduce a simple non-linear embedding adaptation layer, which is fine-tuned on top of fixed pre-trained features for one-shot tasks, improving significantly transductive entropy-based inference for low-shot regimes.
Rethinking Log Odds: Linear Probability Modelling and Expert Advice in Interpretable Machine Learning
We introduce a family of interpretable machine learning models, with two broad additions: Linearised Additive Models (LAMs) which replace the ubiquitous logistic link function in General Additive Models (GAMs); and SubscaleHedge, an expert advice algorithm for combining base models trained on subsets of features called subscales.
Empowering the trustworthiness of ML-based critical systems through engineering activities
This paper reviews the entire engineering process of trustworthy Machine Learning (ML) algorithms designed to equip critical systems with advanced analytics and decision functions.
Explainable prediction of Qcodes for NOTAMs using column generation
A NOtice To AirMen (NOTAM) contains important flight route related information.
FisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition
Some methods proposed the adaptation of CNNs to ultra-wide FoV images by learning deformable kernels.
Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions
The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem.
Interventional Black-Box Explanations
Finally, we believe that our method is orthogonal to logic-based explanation methods and can be leveraged to improve their explanations.
Adaptable Deformable Convolutions for Semantic Segmentation of Fisheye Images in Autonomous Driving Systems
Finally, we provide an in-depth analysis of the effect of the deformable convolutions, bringing elements of discussion on the behavior of CNN models.
Towards Knowledge-Augmented Visual Question Answering
We propose a model that captures the interactions between objects in a visual scene and entities in an external knowledge source.
ConceptBert: Concept-Aware Representation for Visual Question Answering
Given an image and a question in natural language, ConceptBert requires visual elements of the image and a Knowledge Graph (KG) to infer the correct answer.
Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach
Convolutional neural networks (CNNs) are commonly used for image classification.
Ontology-guided Semantic Composition for Zero-Shot Learning
Zero-shot learning (ZSL) is a popular research problem that aims at predicting for those classes that have never appeared in the training stage by utilizing the inter-class relationship with some side information.
Background Knowledge Injection for Interpretable Sequence Classification
Sequence classification is the supervised learning task of building models that predict class labels of unseen sequences of symbols.
Local Score Dependent Model Explanation for Time Dependent Covariates
We introduce a novel technique to find global and local explanations for time series data used in binary classification machine learning systems.
Augmenting Transfer Learning with Semantic Reasoning
We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements and what to transfer with semantic embeddings.
Interpretable Credit Application Predictions With Counterfactual Explanations
Our contribution is two-fold: i) we propose positive counterfactuals, i. e. we adapt counterfactual explanations to also explain accepted loan applications, and ii) we propose two weighting strategies to generate more interpretable counterfactuals.
Knowledge-based Transfer Learning Explanation
Machine learning explanation can significantly boost machine learning's application in decision making, but the usability of current methods is limited in human-centric explanation, especially for transfer learning, an important machine learning branch that aims at utilizing knowledge from one learning domain (i. e., a pair of dataset and prediction task) to enhance prediction model training in another learning domain.
Semantic Explanations of Predictions
The main objective of explanations is to transmit knowledge to humans.
Learning from Ontology Streams with Semantic Concept Drift
Data stream learning has been largely studied for extracting knowledge structures from continuous and rapid data records.
