Search Results for author:
Found 14 papers, 6 papers with code
Can Large Language Models Learn Independent Causal Mechanisms?
We show that such causal constraints can improve out-of-distribution performance on abstract and causal reasoning tasks.
Behaviour Modelling of Social Animals via Causal Structure Discovery and Graph Neural Networks
Better understanding the natural world is a crucial task with a wide range of applications.
Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies
The importance and novelty of this survey are that it explores the perspective of under-represented societies.
Poison is Not Traceless: Fully-Agnostic Detection of Poisoning Attacks
This paper presents a novel fully-agnostic framework, DIVA (Detecting InVisible Attacks), that detects attacks solely relying on analyzing the potentially poisoned data set.
Fast Adversarial Label-Flipping Attack on Tabular Data
To demonstrate this risk is inherited in the adversary's objective, we propose FALFA (Fast Adversarial Label-Flipping Attack), a novel efficient attack for crafting adversarial labels.
Challenges in Annotating Datasets to Quantify Bias in Under-represented Society
Recent advances in artificial intelligence, including the development of highly sophisticated large language models (LLM), have proven beneficial in many real-world applications.
Large Language Models Are Not Strong Abstract Reasoners
We perform extensive evaluations of state-of-the-art LLMs, showing that they currently achieve very limited performance in contrast with other natural language tasks, even when applying techniques that have been shown to improve performance on other NLP tasks.
Neuromodulation Gated Transformer
We introduce a novel architecture, the Neuromodulation Gated Transformer (NGT), which is a simple implementation of neuromodulation in transformers via a multiplicative effect.
Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis
An indigenous perspective on the effectiveness of debiasing techniques for pre-trained language models (PLMs) is presented in this paper.
Disentanglement of Latent Representations via Causal Interventions
Following this assumption, we introduce a new method for disentanglement inspired by causal dynamics that combines causality theory with vector-quantized variational autoencoders.
A Survey of Methods, Challenges and Perspectives in Causality
Deep Learning models have shown success in a large variety of tasks by extracting correlation patterns from high-dimensional data but still struggle when generalizing out of their initial distribution.
Source Inference Attacks in Federated Learning
However, existing MIAs ignore the source of a training member, i. e., the information of which client owns the training member, while it is essential to explore source privacy in FL beyond membership privacy of examples from all clients.
Membership Inference Attacks on Machine Learning: A Survey
In recent years, MIAs have been shown to be effective on various ML models, e. g., classification models and generative models.
Recurring Concept Meta-learning for Evolving Data Streams
The novelty of ECPF is in how it uses similarity of classifications on new data, between a new classifier and existing classifiers, to quickly identify the best classifier to reuse.
