Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking

no code implementations • 10 Nov 2023 • Lefteris Loukas, Ilias Stogiannidis, Odysseas Diamantopoulos, Prodromos Malakasiotis, Stavros Vassos

Standard Full-Data classifiers in NLP demand thousands of labeled examples, which is impractical in data-limited domains.

Contrastive Learning Data Augmentation +4

Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models

1 code implementation • 20 Oct 2023 • Ilias Stogiannidis, Stavros Vassos, Prodromos Malakasiotis, Ion Androutsopoulos

We propose a framework that allows reducing the calls to LLMs by caching previous LLM responses and using them to train a local inexpensive model on the SME side.

Intent Detection Intent Recognition +1

Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance

no code implementations • 28 Aug 2023 • Lefteris Loukas, Ilias Stogiannidis, Prodromos Malakasiotis, Stavros Vassos

We propose the use of conversational GPT models for easy and quick few-shot text classification in the financial domain using the Banking77 dataset.

Contrastive Learning Few-Shot Text Classification +2

Path planning with Inventory-driven Jump-Point-Search

no code implementations • 4 Jul 2016 • Davide Aversa, Sebastian Sardina, Stavros Vassos

In many navigational domains the traversability of cells is conditioned on the path taken.

Action-based Character AI in Video-games with CogBots Architecture: A Preliminary Report

no code implementations • 11 Jul 2013 • Davide Aversa, Stavros Vassos

In this paper we propose an architecture for specifying the interaction of non-player characters (NPCs) in the game-world in a way that abstracts common tasks in four main conceptual components, namely perception, deliberation, control, action.