ŁB
Łukasz Borchmann
cs.CLcs.LGcs.AIcs.IRcs.CVcs.DBcs.DLcs.DS
On Valency
published · living versionsW_5txyfx4z·v1 · currentpublished
Preprints & journals
21 papers in the corpus · 2019–2026Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews2603.22327v2 · Shreyansh Padarha, Ryan Othniel Kearns, Tristan Naidoo et al.2026 · 0 citationsarXiv
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections2603.12180v2 · \Lukasz Borchmann, Jordy Van Landeghem, MichałTurski et al.2026 · 0 citationsarXiv
Language Models Model Language2510.12766v1 · \Lukasz Borchmann2025 · 0 citationsarXiv
Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL2505.20315v2 · Zhewei Yao, Guoheng Sun, Lukasz Borchmann et al.2025 · 4 citationsarXiv
Unchecked and Overlooked: Addressing the Checkbox Blind Spot in Large Language Models with CheckboxQA2504.10419v2 · MichałTurski, Mateusz Chili'nski, \Lukasz Borchmann2025 · 0 citationsarXiv
Query and Conquer: Execution-Guided SQL Generation2503.24364v1 · \Lukasz Borchmann, Marek Wydmuch2025 · 1 citationarXiv
In Case You Missed It: ARC 'Challenge' Is Not That Challenging2412.17758v1 · \Lukasz Borchmann2024 · 0 citationsarXiv
Tackling prediction tasks in relational databases with LLMs2411.11829v1 · Marek Wydmuch, \Lukasz Borchmann, Filip Grali'nski2024 · 0 citationsarXiv
Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists2410.23331v1 · MichałPietruszka, \Lukasz Borchmann, Aleksander Jedrosz et al.2024 · 0 citationsarXiv
Arctic-TILT. Business Document Understanding at Sub-Billion Scale2408.04632v1 · \Lukasz Borchmann, MichałPietruszka, Wojciech Ja'skowski et al.2024 · 1 citationarXiv
Notes on Applicability of GPT-4 to Document Understanding2405.18433v1 · \Lukasz Borchmann2024 · 1 citationarXiv
Document Understanding Dataset and Evaluation (DUDE)2305.08455v3 · Jordy Van Landeghem, Rub'en Tito, \Lukasz Borchmann et al.2023 · 57 citationsarXiv
STable: Table Generation Framework for Encoder-Decoder Models2206.04045v2 · MichałPietruszka, MichałTurski, \Lukasz Borchmann et al.2022 · 6 citationsarXiv
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer2102.09550v3 · RafałPowalski, \Lukasz Borchmann, Dawid Jurkiewicz et al.2021 · 150 citationsarXiv
From Dataset Recycling to Multi-Property Extraction and Beyond2011.03228v1 · Tomasz Dwojak, MichałPietruszka, \Lukasz Borchmann et al.2020 · 5 citationsarXiv
Dynamic Boundary Time Warping for Sub-sequence Matching with Few Examples2010.14464v2 · \Lukasz Borchmann, Dawid Jurkiewicz, Filip Grali'nski et al.2020 · 6 citationsarXiv
Successive Halving Top-k Operator2010.15552v1 · MichałPietruszka, \Lukasz Borchmann, Filip Grali'nski2020 · 5 citationsarXiv
Sparsifying Transformer Models with Trainable Representation Pooling2009.05169v4 · MichałPietruszka, \Lukasz Borchmann, \Lukasz Garncarek2020 · 9 citationsarXiv
On the Multi-Property Extraction and Beyond2006.08281v1 · Tomasz Dwojak, MichałPietruszka, \Lukasz Borchmann et al.2020 · 0 citationsarXiv
ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them2005.07934v2 · Dawid Jurkiewicz, \Lukasz Borchmann, Izabela Kosmala et al.2020 · 44 citationsarXiv
Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines1911.03911v2 · \Lukasz Borchmann, Dawid Wi'sniewski, Andrzej Gretkowski et al.2019 · 17 citationsarXiv
Career total: 39 works. 21 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.