Papers by Piotr Przybyła
Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models can be used to attack content filtering algorithms in social media platforms. |
| Approach: | They propose to generate adversarial examples to test the robustness of social media content filtering algorithms. |
| Outcome: | The proposed model outperforms existing models in the case of propaganda, false claims, rumours and hyperpartisan news. |
Investigating Text Simplification Evaluation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that parallel TS corpora contain inaccurate simplifications and incorrect alignments. |
| Approach: | They propose to improve the distribution of parallel text simplification corpora to build more robust TS models. |
| Outcome: | The proposed models can be improved by improving the distribution of TS datasets. |
Using NLP to quantify the environmental cost and diversity benefits of in-person NLP conferences (2022.findings-acl)
Copied to clipboard
| Challenge: | Figure 1 shows the increase in travel to the ACL annual meeting over the past 40 years . |
| Approach: | They analyse the carbon cost associated with journeys made by researchers attending in-person NLP conferences by text-mining publications from the ACL anthology . |
| Outcome: | The proposed model compares the carbon cost associated with travel to in-person conferences to previously known values for training large models. |
PolQA: Polish Question Answering Dataset (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent proposed systems for open-domain question answering (OpenQA) require large amounts of training data to achieve state-of-the-art performance. |
| Approach: | They propose an efficient annotation strategy that increases passage retrieval accuracy@10 by 10.55 p.p. while reducing the annotation cost by 82%. |
| Outcome: | The proposed approach increases passage retrieval accuracy @10 by 10.55 p.p. while reducing the annotation cost by 82%. |
Exploring Supervised Approaches to the Detection of Anthropomorphic Language in the Reporting of NLP Venues (2025.findings-acl)
Copied to clipboard
| Challenge: | anthropomorphisms are used to describe technical contributions to AI . however, they also give potential for incorrect assumptions about LLMs' capacities. |
| Approach: | They undertake a corpus annotation of one year of ACL abstracts and news articles from the same period and train a regression classifier based on BERT to identify anthropomorphic language. |
| Outcome: | The proposed method can automatically label abstracts for their degree of anthropomorphism based on their corpus and reporting on diachronic and inter-venue findings. |
Multi-Word Lexical Simplification (2020.coling-main)
Copied to clipboard
| Challenge: | In text simplification, individual words are replaced with their simpler equivalents, but single word substitutions do not cover the full complexity of techniques humans use to approach text simulating. |
| Approach: | They propose a task of multi-word lexical simplification in which a sentence is made easier to understand by replacing its fragment with a simpler alternative. |
| Outcome: | The proposed method is based on a purpose-trained neural language model and evaluates against human and resource-based baselines. |
Exploring morphology-aware tokenization: A case study on Spanish language modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that subword tokenization improves performance of neural language models. |
| Approach: | They propose a linguistically grounded approach to train a tokenizer on morphologically segmented data. |
| Outcome: | The proposed tokenizer improves on a Spanish language model with morphological information. |