Search Results for author:
Found 10 papers, 7 papers with code
Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning
Despite their high performance on the original publicly available datasets, we find that all models perform poorly on these newly constructed datasets.
Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models
When learnersourcing multiple-choice questions, creating explanations for the solution of a question is a crucial step; it helps other students understand the solution and promotes a deeper understanding of related concepts.
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.
Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning
Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner.
Input-length-shortening and text generation via attention values
Because of the attention mechanism's high computational cost, transformer models usually have an input-length limitation caused by hardware constraints.
Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation
In our model, reasoning is performed using an iterative memory neural network based on RNN with a gated attention mechanism.
AbductionRules: Training Transformers to Explain Unexpected Inputs
Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has been underexplored despite significant applications to scientific discovery, common-sense reasoning, and model interpretability.
Relating Blindsight and AI: A Review
If we assume that artificial networks have no form of visual experience, then deficits caused by blindsight give us insights into the processes occurring within visual experience that we can incorporate into artificial neural networks.
DeepQR: Neural-based Quality Ratings for Learnersourced Multiple-Choice Questions
We propose DeepQR, a novel neural-network model for AQQR that is trained using multiple-choice-question (MCQ) datasets collected from PeerWise, a widely-used learnersourcing platform.
HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention
This paper proposes a chatbot framework that adopts a hybrid model which consists of a knowledge graph and a text similarity model.
