Maksym Del

I am a PhD student at the Natural Language Processing group at the University of Tartu, specializing in language model interpretability under the advisement of Mark Fishel.

During my PhD, I taught the Mechanistic Interpretability seminar (Fall 2024) and served as a TA for Natural Language Processing (Spring 2019) and Neural Machine Translation (Fall 2017, 2018). I also gained R&D experience with the Bergamot project.

I hold an MS in Computer Science (AI focus) from the University of Tartu, where I researched neural machine translation, and a BS in Software Engineering from the Kyiv Polytechnic Institute, where I focused on software development and machine learning.

Email  /  Twitter (X)  /  GitHub  /  Google Scholar  /  LinkedIn

Research

I'm interested in mechanistic interpretability and other approaches to AI safety.

To Err Is Human, but Llamas Can Learn It Too

We show how to effectively use large langauge models for artificial error generation and grammatical error correction.

True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4

We show that GPT-4 cannot reliably solve short-form detective puzzles, even when given a chain of thought reasoning trace hinting at the correct answer.

Cross-lingual Similarity of Multilingual Representations Revisited

We demonstrate the universality of the internal cross-lingual structure across multilingual language models.

Similarity of Sentence Representations in Multilingual LMs: Resolving Conflicting Literature and a Case Study of Baltic Languages

We address confsuion in prior work regarding the internal cross-slingual structure in multilingual language models.

Translation Transformers Rediscover Inherent Data Domains

We show that translation transformers keep internal domain representaions apart.

Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translation

We present an approach that does both grammatical error correction and style transfer with a single multilingual translation model out-of-the-box.

Phrase-based Unsupervised Machine Translation with Compositional Phrase Embeddings

We propose compositional phrase embeddings for unsupervised machiene translation.

C-3MA: Tartu-Riga-Zurich Translation Systems for WMT17

We describe the neural machine translation systems of the University of Latvia, University of Zurich and University of Tartu submitted as a part of the WMT17 shared task.

Design and source code from Jon Barron's website