Angelos Poulis

Center for Computing & Data Sciences

665 Commonwealth Ave

Boston, MA 02215

Hello I am Angelos, second-year PhD student at Boston University (BU), advised by Professors Evimaria Terzi and Mark Crovella.

I have completed my B.Sc. in Computer Science at the National and Kapodistrian University of Athens (NKUA), Greece, where I did my thesis with Prof. Manolis Koubarakis. Prior joining BU, I did a research internship at the KDD lab, NKUA advised by Prof. Dimitrios Gunopulos.

My research interests broadly lie in machine learning, currently focusing on interpretability of large language models (LLMs). Before that, I did some work on evaluating the logical reasoning capabilities of LLMs.

news

Aug 22, 2025	I’ll be at the 2nd New England Mechanistic Interpretability (NEMI) workshop, and presenting a poster on my current research. Looking forward to connecting with you!
Oct 09, 2024	DELTA paper was accepted to EKAW!
Sep 01, 2024	I started my PhD at Boston University!
Mar 01, 2024	I graduated from the University of Athens!

publications

Transformers in the Service of Description Logic-Based Contexts

Angelos Poulis, Eleni Tsalapati, and Manolis Koubarakis

In Knowledge Engineering and Knowledge Management, 2025

Abs arXiv

Recent advancements in transformer-based models have initiated research interests in investigating their ability to learn to perform reasoning tasks. However, most of the contexts used for this purpose are in practice very simple: generated from short (fragments of) first-order logic sentences with only a few logical operators and quantifiers. In this work, we construct the natural language dataset, DELTA_D, using the description logic language ALCQ. DELTA_D contains 384K examples, and increases in two dimensions: i) reasoning depth, and ii) linguistic complexity. In this way, we systematically investigate the reasoning ability of a supervised fine-tuned DeBERTa-based model and of two large language models (GPT-3.5, GPT-4) with few-shot prompting. Our results demonstrate that the DeBERTa-based model can master the reasoning task and that the performance of GPTs can improve significantly even when a small number of samples is provided (9 shots). We open-source our code and datasets.