Filip Gralinski

55 papers A* 1B 3C 5Journal 21Unranked 24

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Adapting LLMs for Minimal-edit Grammatical Error Correction. CoRR Ryszard Staruch, Filip Gralinski, Daniel Dzienisiewicz
2025	—	`conf`	CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation. NAACL (Short Papers) Youngwon Lee, Seung-won Hwang, Daniel F. Campos, Filip Gralinski, Zhewei Yao, Yuxiong He
2025	—	`conf`	Inference Scaling for Bridging Retrieval and Augmented Generation. NAACL (Findings) Youngwon Lee, Seung-won Hwang, Daniel F. Campos, Filip Gralinski, Zhewei Yao, Yuxiong He
2025	J	`jnl`	LLMzSzŁ: a comprehensive LLM benchmark for Polish. CoRR Krzysztof Jassem, Michal Ciesiólka, Filip Gralinski, Piotr Jablonski, Jakub Pokrywka, Marek Kubis, Monika Jablonska, Ryszard Staruch
2025	B	`conf`	Oddballness: universal anomaly detection with language models. COLING Filip Gralinski, Ryszard Staruch, Krzysztof Jurkiewicz
2025	J	`jnl`	Seamlessly Integrating Tree-Based Positional Embeddings into Transformer Models for Source Code Representation. CoRR Patryk Bartkowiak, Filip Gralinski
2025	C	`conf`	reVISION: A Polish Benchmark for Evaluating Vision-Language Models on Multimodal National Exam Data. FedCSIS Michal Ciesiólka, Filip Gralinski
2024	J	`jnl`	CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation. CoRR Youngwon Lee, Seung-won Hwang, Daniel F. Campos, Filip Gralinski, Zhewei Yao, Yuxiong He
2024	J	`jnl`	Inference Scaling for Bridging Retrieval and Augmented Generation. CoRR Youngwon Lee, Seung-won Hwang, Daniel F. Campos, Filip Gralinski, Zhewei Yao, Yuxiong He
2024	J	`jnl`	Oddballness: universal anomaly detection with language models. CoRR Filip Gralinski, Ryszard Staruch, Krzysztof Jurkiewicz
2024	—	`conf`	POLygraph: Polish Fake News Dataset. WASSA Daniel Dzienisiewicz, Filip Gralinski, Piotr Jablonski, Marek Kubis, Pawel Skórzewski, Piotr Wierzchon
2024	J	`jnl`	POLygraph: Polish Fake News Dataset. CoRR Daniel Dzienisiewicz, Filip Gralinski, Piotr Jablonski, Marek Kubis, Pawel Skórzewski, Piotr Wierzchon
2024	J	`jnl`	Tackling prediction tasks in relational databases with LLMs. CoRR Marek Wydmuch, Lukasz Borchmann, Filip Gralinski
2024	J	`jnl`	Two Approaches to Diachronic Normalization of Polish Texts. CoRR Kacper Dudzic, Filip Gralinski, Krzysztof Jassem, Marek Kubis, Piotr Wierzchon
2023	—	`conf`	Arxiv Tables: Document Understanding Challenge Linking Texts and Tables. ICDAR Workshops (2) Karolina Konopka, Michal Turski, Filip Gralinski
2023	—	`conf`	CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data. ICDAR (3) Michal Turski, Tomasz Stanislawek, Karol Kaczmarek, Pawel Dyda, Filip Gralinski
2023	J	`jnl`	CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data. CoRR Michal Turski, Tomasz Stanislawek, Karol Kaczmarek, Pawel Dyda, Filip Gralinski
2023	—	`conf`	Modeling Spaced Repetition with LSTMs. CSEDU (2) Jakub Pokrywka, Marcin Biedalak, Filip Gralinski, Krzysztof Biedalak
2022	—	`conf`	Challenging America: Modeling language in longer time scales. NAACL-HLT (Findings) Jakub Pokrywka, Filip Gralinski, Krzysztof Jassem, Karol Kaczmarek, Krzysztof Jurkiewicz, Piotr Wierzchon
2022	C	`conf`	Temporal Language Modeling for Short Text Document Classification with Transformers. FedCSIS Jakub Pokrywka, Filip Gralinski
2022	C	`conf`	Using Transformer models for gender attribution in Polish. FedCSIS Karol Kaczmarek, Jakub Pokrywka, Filip Gralinski
2021	—	`conf`	DUE: End-to-End Document Understanding Benchmark. NeurIPS Datasets and Benchmarks Lukasz Borchmann, Michal Pietruszka, Tomasz Stanislawek, Dawid Jurkiewicz, Michal Turski, Karolina Szyndler, Filip Gralinski
2021	J	`jnl`	Dynamic Boundary Time Warping for sub-sequence matching with few examples. Expert Syst. Appl. Lukasz Borchmann, Dawid Jurkiewicz, Filip Gralinski, Tomasz Górecki
2021	—	`conf`	Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts. ICDAR (1) Tomasz Stanislawek, Filip Gralinski, Anna Wróblewska, Dawid Lipinski, Agnieszka Kaliska, Paulina Rosalska, Bartosz Topolski, Przemyslaw Biecek
2021	J	`jnl`	Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts. CoRR Tomasz Stanislawek, Filip Gralinski, Anna Wróblewska, Dawid Lipinski, Agnieszka Kaliska, Paulina Rosalska, Bartosz Topolski, Przemyslaw Biecek
2021	—	`conf`	LAMBERT: Layout-Aware Language Modeling for Information Extraction. ICDAR (1) Lukasz Garncarek, Rafal Powalski, Tomasz Stanislawek, Bartosz Topolski, Piotr Halama, Michal Turski, Filip Gralinski
2021	A*	`conf`	Successive Halving Top-k Operator. AAAI Michal Pietruszka, Lukasz Borchmann, Filip Gralinski
2020	—	`conf`	ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them. SemEval@COLING Dawid Jurkiewicz, Lukasz Borchmann, Izabela Kosmala, Filip Gralinski
2020	J	`jnl`	ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them. CoRR Dawid Jurkiewicz, Lukasz Borchmann, Izabela Kosmala, Filip Gralinski
2020	—	`conf`	Contract Discovery: Dataset and a Few-shot Semantic Retrieval Challenge with Competitive Baselines. EMNLP (Findings) Lukasz Borchmann, Dawid Wisniewski, Andrzej Gretkowski, Izabela Kosmala, Dawid Jurkiewicz, Lukasz Szalkiewicz, Gabriela Palka, Karol Kaczmarek, Agnieszka Kaliska, Filip Gralinski
2020	J	`jnl`	Dynamic Boundary Time Warping for Sub-sequence Matching with Few Examples. CoRR Lukasz Borchmann, Dawid Jurkiewicz, Filip Gralinski, Tomasz Górecki
2020	B	`conf`	From Dataset Recycling to Multi-Property Extraction and Beyond. CoNLL Tomasz Dwojak, Michal Pietruszka, Lukasz Borchmann, Jakub Chledowski, Filip Gralinski
2020	J	`jnl`	From Dataset Recycling to Multi-Property Extraction and Beyond. CoRR Tomasz Dwojak, Michal Pietruszka, Lukasz Borchmann, Jakub Chledowski, Filip Gralinski
2020	J	`jnl`	Kleister: A novel task for Information Extraction involving Long Documents with Complex Layout. CoRR Filip Gralinski, Tomasz Stanislawek, Anna Wróblewska, Dawid Lipinski, Agnieszka Kaliska, Paulina Rosalska, Bartosz Topolski, Przemyslaw Biecek
2020	J	`jnl`	LAMBERT: Layout-Aware language Modeling using BERT for information extraction. CoRR Lukasz Garncarek, Rafal Powalski, Tomasz Stanislawek, Bartosz Topolski, Piotr Halama, Filip Gralinski
2020	J	`jnl`	On the Multi-Property Extraction and Beyond. CoRR Tomasz Dwojak, Michal Pietruszka, Lukasz Borchmann, Filip Gralinski, Jakub Chledowski
2020	J	`jnl`	Sparsifying Transformer Models with Differentiable Representation Pooling. CoRR Michal Pietruszka, Lukasz Borchmann, Filip Gralinski
2020	J	`jnl`	Successive Halving Top-k Operator. CoRR Michal Pietruszka, Lukasz Borchmann, Filip Gralinski
2019	—	`conf`	GEval: Tool for Debugging NLP Datasets and Models. BlackboxNLP@ACL Filip Gralinski, Anna Wróblewska, Tomasz Stanislawek, Kamil Grabowski, Tomasz Górecki
2019	J	`jnl`	Searching for Legal Clauses by Analogy. Few-shot Semantic Retrieval Shared Task. CoRR Lukasz Borchmann, Dawid Wisniewski, Andrzej Gretkowski, Izabela Kosmala, Dawid Jurkiewicz, Lukasz Szalkiewicz, Gabriela Palka, Karol Kaczmarek, Agnieszka Kaliska, Filip Gralinski
2017	—	`conf`	Automated Normalization and Analysis of Historical Texts. LCT Pawel Skórzewski, Krzysztof Jassem, Filip Gralinski
2017	—	`conf`	The RetroC challenge: how to guess the publication year of a text? DATeCH Filip Gralinski, Rafal Jaworski, Lukasz Borchmann, Piotr Wierzchon
2016	B	`conf`	"He Said She Said" ― a Male/Female Corpus of Polish. LREC Filip Gralinski, Lukasz Borchmann, Piotr Wierzchon
2016	—	`conf`	Vive la Petite Différence! - Exploiting Small Differences for Gender Attribution of Short Texts. TSD Filip Gralinski, Rafal Jaworski, Lukasz Borchmann, Piotr Wierzchon
2015	—	`conf`	RetroC - A Corpus for Evaluating Temporal Classifiers. LTC Filip Gralinski, Piotr Wierzchon
2013	—	`ch.`	PSI-Toolkit: A Natural Language Processing Pipeline. Computational Linguistics - Applications Filip Gralinski, Krzysztof Jassem, Marcin Junczys-Dowmunt
2012	—	`conf`	Mining the Web for Idiomatic Expressions Using Metalinguistic Markers. TSD Filip Gralinski
2010	—	`conf`	Computational Lexicography of Multi-Word Units. How Efficient Can It Be? MWE@COLING Filip Gralinski, Agata Savary, Monika Czerepowicka, Filip Makowiecki
2010	—	`conf`	Matura Evaluation Experiment Based on Human Evaluation of Machine Translation. IMCSIT Aleksandra Wojak, Filip Gralinski
2010	C	`conf`	Mining Parenthetical Translations for Polish-English Lexica. CICLing Filip Gralinski
2009	—	`conf`	Acquiring Bilingual Lexica from Keyword Listings. LTC Filip Gralinski, Krzysztof Jassem, Roman Kurc
2009	C	`conf`	An Environment for Named Entity Recognition and Translation. EAMT Filip Gralinski, Krzysztof Jassem, Michal Marcinczuk
2009	—	`conf`	Looking for new words out there. IMCSIT Filip Gralinski, Marcin Walas
2006	—	`conf`	Some Methods of Describing Discontinuity in Polish and Their Cost-Effectiveness. TSD Filip Gralinski
2003	—	`conf`	Applying Transition Networks in Translating Polish E-Mails. IIS Krzysztof Jassem, Filip Gralinski, Tomasz Kowalski