4 citations · 7 across the 10 of their papers we have counts for
13 papers
Tackling prediction tasks in relational databases with LLMs
Marek Wydmuch, Łukasz Borchmann, Filip Graliński
Though large language models (LLMs) have demonstrated exceptional performance across numerous problems, their application to predictive tasks in relational databases remains largel…
Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists
Michał Pietruszka, Łukasz Borchmann, Aleksander Jędrosz +1
We present a benchmark for large language models designed to tackle one of the most knowledge-intensive tasks in data science: writing feature engineering code, which requires doma…
Arctic-TILT. Business Document Understanding at Sub-Billion Scale
Łukasz Borchmann, Michał Pietruszka, Wojciech Jaśkowski +13
The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\…
Document Understanding Dataset and Evaluation (DUDE)
Jordy Van Landeghem, Rubén Tito, Łukasz Borchmann +10
We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding…
STable: Table Generation Framework for Encoder-Decoder Models
Michał Pietruszka, Michał Turski, Łukasz Borchmann +5
The output structure of database-like tables, consisting of values structured in horizontal rows and vertical columns identifiable by name, can cover a wide range of NLP tasks. Fol…
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer
Rafał Powalski, Łukasz Borchmann, Dawid Jurkiewicz +3
We address the challenging problem of Natural Language Comprehension beyond plain-text documents by introducing the TILT neural network architecture which simultaneously learns lay…
From Dataset Recycling to Multi-Property Extraction and Beyond
Tomasz Dwojak, Michał Pietruszka, Łukasz Borchmann +2
This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outper…
Successive Halving Top-k Operator
Michał Pietruszka, Łukasz Borchmann, Filip Graliński
We propose a differentiable successive halving method of relaxing the top-k operator, rendering gradient-based optimization possible. The need to perform softmax iteratively on the…
Dynamic Boundary Time Warping for Sub-sequence Matching with Few Examples
Łukasz Borchmann, Dawid Jurkiewicz, Filip Graliński +1
The paper presents a novel method of finding a fragment in a long temporal sequence similar to the set of shorter sequences. We are the first to propose an algorithm for such a sea…
Sparsifying Transformer Models with Trainable Representation Pooling
Michał Pietruszka, Łukasz Borchmann, Łukasz Garncarek
We propose a novel method to sparsify attention in the Transformer model by learning to select the most-informative token representations during the training process, thus focusing…
On the Multi-Property Extraction and Beyond
Tomasz Dwojak, Michał Pietruszka, Łukasz Borchmann +2
In this paper, we investigate the Dual-source Transformer architecture on the WikiReading information extraction and machine reading comprehension dataset. The proposed model outpe…
ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them
Dawid Jurkiewicz, Łukasz Borchmann, Izabela Kosmala +1
This paper presents the winning system for the propaganda Technique Classification (TC) task and the second-placed system for the propaganda Span Identification (SI) task. The purp…
Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines
Łukasz Borchmann, Dawid Wiśniewski, Andrzej Gretkowski +7
We propose a new shared task of semantic retrieval from legal texts, in which a so-called contract discovery is to be performed, where legal clauses are extracted from documents, g…