Papers by Anastasia Voznyuk

3 papers
DeepPavlov 1.0: Your Gateway to Advanced NLP Models Backed by Transformers and Transfer Learning (2024.emnlp-demo)

Copied to clipboard

Challenge: Open-source framework for using NLP models is released for non-experts . complexity of building, fine-tuning and deploying state-of-the-art models remains a barrier .
Approach: They present DeepPavlov 1.0, an open-source framework for using NLP models . the framework is based on PyTorch and supports HuggingFace transformers .
Outcome: The DeepPavlov 1.0 framework is designed for practitioners with limited knowledge of NLP/ML.
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders (2025.findings-acl)

Copied to clipboard

Challenge: Existing algorithms for AI text detection lack interpretability, limiting their reliability in highstakes applications.
Approach: They extend existing ATD frameworks by using Sparse Autoencoders to extract features from Gemma-2-2b residual stream.
Outcome: The proposed algorithms can extract human-interpretable features from Gemma-2-2b model.
Quantifying Logical Consistency in Transformers via Query-Key Alignment (2025.emnlp-main)

Copied to clipboard

Challenge: Existing solutions for multi-step logical reasoning are unreliable . Existing methods generate intermediate steps but provide no internal check of coherence .
Approach: They propose a method that uses internal Query-Key interactions within transformer attention heads as a proxy for logical consistency.
Outcome: The proposed method reveals latent reasoning structure in large language models and provides a mechanistic alternative to ablation-based analysis.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations