Ghazal Afroozi Milani

Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks. However, their ability to perform tasks requiring formal representation and reasoning remains limited. This paper explores the integration of Meta Inverse Entailment (MIE) with LLMs to enhance their reasoning capabilities. In our experiments, we examine a hybrid GPT-MIE model on a simplified natural language grammar. The results suggest that the accuracy of GPT is significantly improved when it incorporates the grammar learned using MIE. This hybrid approach demonstrates the potential of combining LLMs’ linguistic proficiency with MIE’s rigorous formalism, leading to better performance in tasks demanding logical representation and reasoning.

With the ever-increasing potential of AI to perform personalised tasks, it is becoming essential to develop new machine learning techniques which are data-efficient and do not require hundreds or thousands of training data. In this paper, we explore an Inductive Logic Programming approach for one-shot text classification. In particular, we explore the framework of Meta-Interpretive Learning (MIL), along with using common-sense background knowledge extracted from ConceptNet. Results indicate that MIL can learn text classification rules from a small number of training examples, even one example. Moreover, the higher complexity of chosen example for one-shot learning, the higher accuracy of the outcome. Finally, we utilise two approaches, Background Knowledge Splitting and Average One-Shot Learning, to evaluate our model on a public News Category dataset. The outcomes validate MIL's superior performance to the Siamese net for one-shot learning from text.