Papers by Mateusz Lango
Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Hallucination of text lacking grounding in input data is a problem in neural data-to-text generation. |
| Approach: | They propose to combine probabilistic output of a generator language model with the output of an “text critic” classifier which guides the generation by assessing the match between the input data and the generated text. |
| Outcome: | The proposed method improves on the WebNLG and OpenDialKG benchmarks. |
SRS-Stories: Vocabulary-constrained multilingual story generation for language learning (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for learning foreign languages are to use a spaced repetition system to learn new vocabulary. |
| Approach: | They use large language models to generate personalized stories using only the vocabulary they know. |
| Outcome: | The generated stories are more grammatical, coherent, and provide better examples of word usage than the standard beam search approach. |
Reasoning Gets Harder for LLMs Inside A Dialogue (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) achieve strong performance on many reasoning benchmarks, yet these evaluations typically focus on isolated tasks that differ from real-world usage in task-oriented dialogue (TOD). |
| Approach: | They propose to use a dynamic benchmark to examine how framing reasoning tasks within task-oriented dialogue (TOD) affect LLM performance. |
| Outcome: | The proposed model performs well on isolated tasks and in task-oriented dialogues, but performance is inconsistent between them. |
A Closer Look on Unsupervised Cross-lingual Word Embeddings Mapping (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for word embeddings are limited to a single, unannotated corpus, which means that word representations with similar meaning in distinct languages can be very different. |
| Approach: | They propose an unsupervised method for cross-lingual word embedding mapping that uses stochastic initialization and isometric initialization to verify the method's robustness. |
| Outcome: | The proposed method is robust on different embedding representations and new language pairs, particularly those involving Slavic languages like Polish or Czech. |
Polish-ASTE: Aspect-Sentiment Triplet Extraction Datasets for Polish (2024.lrec-main)
Copied to clipboard
| Challenge: | Aspect-Sentiment Triplet Extraction (ASTE) is one of the most challenging and complex tasks in sentiment analysis. |
| Approach: | They propose to use customer opinions of hotels and purchased products in Polish to extract ASTE triplets that contain an aspect, its associated sentiment polarity, and an opinion phrase that serves as a rationale for the assigned polarities. |
| Outcome: | The proposed datasets contain customer opinions about hotels and purchased products expressed in Polish and are available under a permissive licence and have the same file format as the English datasets. |
One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models (2026.acl-short)
Copied to clipboard
| Challenge: | Recent diffusion-based approaches to text generation are inefficient due to the need for multiple denoising steps. |
| Approach: | They propose a shortcut flow-matching model that learns to directly predict multi-step denoising outcomes in a single step. |
| Outcome: | The proposed model improves on three datasets and can predict multi-step denoising outcomes in a single step. |
Semi-Automatic Construction of Word-Formation Networks (for Polish and Spanish) (L18-1)
Copied to clipboard
| Challenge: | a semi-automatic method for the construction of derivational networks is proposed . the proposed method is general enough to be adopted for other languages . |
| Approach: | They propose a semi-automatic method for the construction of derivational networks using a sequential pattern mining technique. |
| Outcome: | The proposed method is general enough to be adopted for other languages. |
Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs (2024.eacl-long)
Copied to clipboard
| Challenge: | Lack of access to model details has raised concerns about data contamination among researchers. |
| Approach: | They conduct the first systematic analysis of work using OpenAI’s GPT-3.5 and GPT-4, the most prominently used LLMs today, in the context of data contamination. |
| Outcome: | The proposed models have been exposed to 4.7M samples from 263 benchmarks during the first year after their release. |
Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing explanation methods for image classification struggle to provide faithful and plausible explanations for predictions. |
| Approach: | They propose a natural language explanation method that can be applied to any CNN-based classifier without altering its training process or affecting predictive performance. |
| Outcome: | The proposed method can be applied to any CNN-based classifier without altering its training process or affecting predictive performance. |
LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing neural approaches to generate RDF-to-text are limited in their implementation. |
| Approach: | They propose a framework where the model is “trained” through collaborative interactions among multiple LLM agents rather than traditional backpropagation. |
| Outcome: | The proposed framework reduces hallucinations and fluency penalties on the WebNLG and OpenDialKG datasets. |
ASTE-Transformer: Modelling Dependencies in Aspect-Sentiment Triplet Extraction (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Aspect-Sentiment Triplet Extraction (ASTE) is a recent task in aspect-based sentiment analysis. |
| Approach: | They propose a task of aspect-based sentiment analysis that extracts triples from sentences . they propose three transformer-inspired layers to enable modelling of dependencies . |
| Outcome: | The proposed method achieves higher performance in terms of F1 measure than other methods studied on popular benchmarks. |