185 citations · 665 across the 58 of their papers we have counts for
69 papers
Do LLMs Make More Mistakes If They Do Not Believe the Input Data?
Peter Kochelka, Aleš Manuel Papáček, Vojtěch Dvořák +1
Large language models (LLMs) are prone to hallucinating or misinterpreting facts, which impairs their usability in retrieval-augmented generation or data-to-text systems. We analys…
VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations
Ivan Kartáč, Jan Tovarys, Mateusz Lango +1
Citation excerpts can be used to increase the reliability of generated outputs and their faithfulness to cited sources, which is especially important in high-stakes domains such as…
Can LLM Coding Agents Reason About Time Series?
Filip Rechtorík, Ondřej Dušek, Zdeněk Kasner
Large language models (LLMs) are increasingly being used for automated decision-making systems in finance, healthcare, or environmental monitoring. Time series data are ubiquitous…
Modular Monolingual Adaptation using Pretrained Language Models
Nalin Kumar, Ondřej Dušek
Building monolingual language models (LMs) for low-resource languages typically relies on adapting pretrained language models (PLMs) by finetuning the whole model on the target lan…
AnimatedLLM: Explaining LLMs with Interactive Visualizations
Zdeněk Kasner, Ondřej Dušek
Large language models (LLMs) are becoming central to natural language processing education, yet materials showing their mechanics are sparse. We present AnimatedLLM, an interactive…
Strategies for Span Labeling with Large Language Models
Danil Semin, Ondřej Dušek, Zdeněk Kasner
Large language models (LLMs) are increasingly used for text analysis tasks, such as named entity recognition or error detection. Unlike encoder-based models, however, generative ar…
LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators
Mateusz Lango, Ondřej Dušek
We present a novel neurosymbolic framework for RDF-to-text generation, in which the model is "trained" through collaborative interactions among multiple LLM agents rather than trad…
FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation
Kristýna Onderková, Ondřej Plátek, Zdeněk Kasner +1
Table-to-text generation (insight generation from tables) is a challenging task that requires precision in analyzing the data. In addition, the evaluation of existing benchmarks is…
When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition
Karen Jia-Hui Li, Simone Balloccu, Ondrej Dusek +1
The increasing trust in large language models (LLMs), especially in the form of chatbots, is often undermined by the lack of their extrinsic evaluation. This holds particularly tru…
Real-World Summarization: When Evaluation Reaches Its Limits
Patrícia Schmidtová, Ondřej Dušek, Saad Mahamood
We examine evaluation of faithfulness to input data in the context of hotel highlights: brief LLM-generated summaries that capture unique features of accommodations. Through human…
Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems
Jędrzej Warczyński, Mateusz Lango, Ondrej Dusek
We introduce a simple approach that uses a large language model (LLM) to automatically implement a fully interpretable rule-based data-to-text system in pure Python. Experimental e…
Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?
Sourabrata Mukherjee, Atul Kr. Ojha, John P. McCrae +1
Text style transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional chall…
Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings
Michelle Elizabeth, Morgan Veyret, Miguel Couceiro +2
Large language models (LLMs) gained immense popularity due to their impressive capabilities in unstructured conversations. Empowering LLMs with advanced prompting strategies such a…
Teaching LLMs at Charles University: Assignments and Activities
Jindřich Helcl, Zdeněk Kasner, Ondřej Dušek +4
This paper presents teaching materials, particularly assignments and ideas for classroom activities, from a new course on large language models (LLMs) taught at Charles University.…
A Survey of Text Style Transfer: Applications and Ethical Implications
Sourabrata Mukherjee, Mateusz Lango, Zdenek Kasner +1
Text style transfer (TST) is an important task in controllable text generation, which aims to control selected attributes of language use, such as politeness, formality, or sentime…
Text Style Transfer: An Introductory Overview
Sourabrata Mukherjee, Ondrej Dušek
Text Style Transfer (TST) is a pivotal task in natural language generation to manipulate text style attributes while preserving style-independent content. The attributes targeted i…
Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
Adam Wojciechowski, Mateusz Lango, Ondrej Dusek
Existing explanation methods for image classification struggle to provide faithful and plausible explanations. This paper addresses this issue by proposing a post-hoc natural langu…
Are Large Language Models Actually Good at Text Style Transfer?
Sourabrata Mukherjee, Atul Kr. Ojha, Ondřej Dušek
We analyze the performance of large language models (LLMs) on Text Style Transfer (TST), specifically focusing on sentiment transfer and text detoxification across three languages:…
Multilingual Text Style Transfer: Datasets & Models for Indian Languages
Sourabrata Mukherjee, Atul Kr. Ojha, Akanksha Bansal +3
Text style transfer (TST) involves altering the linguistic style of a text while preserving its core content. This paper focuses on sentiment transfer, a popular TST subtask, acros…
Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
Simone Balloccu, Patrícia Schmidtová, Mateusz Lango +1
Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially c…
Text Detoxification as Style Transfer in English and Hindi
Sourabrata Mukherjee, Akanksha Bansal, Atul Kr. Ojha +2
This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication an…
Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation
Zdeněk Kasner, Ondřej Dušek
We analyze the behaviors of open large language models (LLMs) on the task of data-to-text (D2T) generation, i.e., generating coherent and relevant text from structured data. To avo…
Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising
Sourabrata Mukherjee, Zdeněk Kasner, Ondřej Dušek
Text sentiment transfer aims to flip the sentiment polarity of a sentence (positive to negative or vice versa) while preserving its sentiment-independent content. Although current…
LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems
Nalin Kumar, Ondřej Dušek
Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been…