Seminar

Natural Language Processing Seminar

The NLP Seminar is organised by the Linguistic Engineering Group at the Institute of Computer Science, Polish Academy of Sciences (ICS PAS) and has been held since 2000. It is open to everyone and takes place every two weeks on average, usually on Mondays at 10:15.

Many talks are given online – please use the “Join online” link next to the talk. Recordings of most talks are published on the institute’s YouTube channel.

Upcoming talks

  • at 11:00

    Researching local government at scale with AI

    Sabina Tomkins (University of Michigan)

    In English Join online
    Abstract

    Local governments in the United States oversee budgets which amount to trillions of dollars. They are highly consequential sites of political participation and offer a rare opportunity for direct democracy. Yet, due to the vast number of them (roughly 10,000 different units of local government in the US), they have been difficult to study. This is changing as many local governments have begun to post recordings of their meetings online (for example on YouTube). Now, computational methods can be harnessed to study these meetings at scale. This talk will present a large-scale research project for collecting, processing and analyzing these records and discuss the kinds of research opportunities they afford. It will conclude with insights from existing research projects, for example around questions of what kinds of concerns the public bring forward in these meetings and whether these concerns reflect local or national interests.

  • Session

    Persuasion in Parliament and Beyond: Computational Analysis of Political Discourse

    Mini-conference supported by the Polish Academy of Sciences (MOST PAN)

    ParlaMint – Comparable and Interoperable Parliamentary Corpora

    Tomaž Erjavec (Jožef Stefan Institute)

    In English Join online
    Abstract

    The talk presents the ParlaMint corpora of parliamentary debates of 29 European countries and autonomous regions, covering at least the period from 2015 to 2022, and containing over 1 billion words. The corpora are uniformly encoded, contain rich metadata about their 24 thousand speakers, and are linguistically annotated, as well as machine translated to English. We present the compilation of the corpora, including the encoding infrastructure, use of GitHub, the production of individual corpora, the common pipeline for producing their distribution, and use of CLARIN services for dissemination. We also present associated efforts, such corpora of additional countries, and the ParlaSpeech corpora. Finally, the use of the corpora and further work are discussed.

    Beyond the Polish Parliamentary Corpus

    Maciej Ogrodniczuk (Institute of Computer Science, Polish Academy of Sciences)

    In English Join online
    Abstract

    The Polish Parliamentary Corpus, which is also represented in ParlaMint, served as a model for a series of Polish corpora containing similar types of material, which are ideally suited to research into persuasion techniques. The presentation will introduce these datasets: the Round Table Corpus, documenting the opposition’s negotiations with the communist authorities of the Polish People’s Republic in 1989, and the Polish Local Government Debates Corpus – a collection of transcripts from the proceedings of provincial assemblies, city councils, county councils and local councils from 2018 to 2026.

    Multilingual Corpora of Persuasion Techniques in News and Parliamentary Debates

    Jakub Piskorski (Joint Research Centre of the European Commission)

    In English Join online
    Abstract

    This talk provides an overview of recently developed multilingual corpora with text span-level annotation of persuasion techniques in online news, parliamentary debates, and other types of texts. The talk will elaborate on the corpora characteristics, taxonomies, creation process, and annotation complexity aspects. The talk will also reflect on the experience gained from shared tasks revolving around detection and classification of persuasion techniques which exploit these corpora, and covers state-of-the-art performance and cross-corpora comparison.

    Leveraging Persuasion and Intent for Analysis and Reasoning-based Detection of Disinformation with Large Language Models

    Arkadiusz Modzelewski (Uniwersytet Padewski / NASK)

    In English Join online
    Abstract

    This talk introduces novel human-annotated disinformation datasets that enable the analysis of manipulation techniques and malicious intent in Polish and English. It presents reasoning approaches that explicitly incorporate persuasion and intent to improve LLM-based disinformation detection across domains, genres, and languages. Finally, it introduces a multilingual benchmark of human- and AI-generated persuasive content, showing that AI-generated persuasive text exhibits linguistic differences and poses new challenges for detection. Overall, the talk presents new datasets, reasoning frameworks, and empirical insights toward more transparent and generalizable disinformation detection in the era of generative AI.

    Open Political Corpora: Structuring, Searching, and Analyzing Political Text Collections with PoliCorp

    Philipp Mayr-Schlegel (GESIS – Leibniz Institute for the Social Sciences)

    In English Join online
    Abstract

    In this work, we present PoliCorp, a web portal designed to facilitate the search and analysis of political text corpora. PoliCorp provides researchers with access to rich textual data, enabling in-depth analysis of parliamentary discourse over time. The platform currently contains a collection of transcripts of debates from the German parliament, spanning 76 years of proceedings. With the advanced search functionality, researchers can apply logical operations to combine or exclude search criteria, making it easier to filter through vast amounts of parliamentary debate data. The search can be customised by combining multiple fields and applying logical operators to uncover complex patterns and insights within the data. Additional data processing steps were performed to enable web-based search and incorporate supplementary features. A key feature that differentiates PoliCorp is its intuitive web-based interface that enables users to query processed political texts without requiring programming skills. The user-friendly platform allows the creation of custom subcorpora via search parameters, which can be freely downloaded in JSON format for further analysis.

    ParlSent-EU: Three Decades of Interpersonal Sentiment in European Parliamentary Debates Since the 1990s

    Kamil Orzechowski (Warsaw University of Technology)

    In English Join online
    Abstract

    Parliamentary corpora offer rich speech texts and speaker metadata but rarely capture interpersonal sentiment between legislators. Research on legislative relationships relies mainly on roll-call votes and co-sponsorship, reflecting behavioural alignment rather than expressed attitudes such as approval, criticism, or hostility. We introduce ParlSent-EU, a cross-national dataset of directed interpersonal sentiment relations from plenary speeches in the Polish Sejm, German Bundestag, and French Assemblée nationale, spanning over three decades from the 1990s. It was developed by Warsaw University of Technology (OMINO project) and GESIS – Leibniz Institute for the Social Sciences (POLLUX project). Each relation records a speaker, a targeted legislator, and the expressed sentiment (positive, neutral, or negative), with temporal, parliamentary, and demographic metadata, enabling the reconstruction of directed, signed, and temporal networks. Relations are identified by a pipeline combining lexical filtering, LLM-based sentiment extraction, and rule-based entity disambiguation, validated against manually annotated gold standards with performance metrics and inter-annotator agreement. ParlSent-EU enables comparative, longitudinal studies of elite affective polarization, cross-party hostility, intra-party cohesion, and gendered political communication in European parliamentary democracies.

    From Detecting Persuasion to Predicting Its Success: Persuasion Strategies as Predictive Signals

    Tiziano Labruna (Fondazione Bruno Kessler)

    In English Join online
    Abstract

    Computational work on persuasion has largely focused on detecting rhetorical techniques in text. This talk would ask a complementary question: do those techniques tell us anything about whether an argument actually changes someone’s mind? Multi-Strategy Persuasion Scoring is a zero-shot framework in which a large language model reasons about each of six persuasion strategies independently and produces a per-strategy score, which can then be aggregated directly or used as input to a lightweight classifier. The strategy has been tested across three datasets, proving that strategy-guided reasoning consistently outperforms both direct pairwise comparison and generic chain-of-thought baselines.

  • Session

    AI without Borders

    Mini-conference supported by the Polish Academy of Sciences (MOST PAN)

    Universalist modelling and processing of idiomaticity in the PARSEME and UniDive framework – recent developments and the state of Polish

    Agata Savary (Paris-Saclay University)

    In English Join online
    Abstract

    Multiword expressions (MWEs), like “biały kruk” (lit. a white crow, ‘a rare person or thing’) or “krew kogoś zalewa” (lit. blood floods someone, ‘someone gets furious’), a “być komuś na rękę (lit. to be on hand to someone, ‘to be convenient’), or “wchodzić w grę” (lit. to enter the play, ‘to come into play’), are combinations of words which exhibit idiosyncratic behavior on the lexical, morphological, syntactic, and semantic levels. Their most outstanding feature is their semantic non-compositionality, i.e. the fact that their meaning cannot be straightforwardly deduced from the meanings of their components.

    MWEs pose severe challenges in semantically-oriented NLP tasks. For instance paraphrasing sentences containing idioms is hindered by their lexical and morpho-syntactic inflexibility. Thus, when applying usual paraphrasing techniques to “krew kogoś zalewa”, we often obtain incorrect paraphrases, in which the idiomatic meaning is lost, e.g. “ktoś jest zalany krwią” (someone is flooded with blood) or “krew kogoś oblewa” (lit. blood poured onto someone). One of the ways to tackle this challenge is to identify MWEs in running text and apply dedicated treatment to them.

    MWE identification has been the object of many efforts, and is one of the tasks where supervised encoder-based methods still outperform more recent generative LLMs. Paraphrasing of MWEs is an understudied task, especially in multilingual contexts. These two tasks have been the subject of longstanding effort within two European COST networks: PARSEME (2013–2017) and UniDive (2022–2026), which are notably the organizers of 5 multilingual evaluation campaigns on these topics. I will summarize major challenges and findings from these campaigns and highlight future work.

    Detecting AI generated content on surface- and idea-level

    Marzena Karpińska (Simon Fraser University)

    In English Join online
    Abstract

    Modern detectors identify only who wrote the words. However, AI-assisted writing is becoming more common. For instance, a user may use AI tools to polish their writing or produce the text from their supplied content. Hence, it is becoming important to detect who contributed the ideas not only the prose. In this talk, I will first discuss the specificities of AI writing at the prose and content levels. Then I will talk about training Idealens, an AI detector that works based on document content, rather than its prose.

    Can Neural Network Models Learn Logic?

    Jakub Szymanik (University of Trento)

    In English Join online
    Abstract

    Large language models now produce chains of reasoning that look like proofs, but it remains unclear whether they have acquired the rules of inference or merely the patterns that usually accompany them. I will describe a line of joint work with Manuel Vargas Guzmán and Maciej Malicki1 that tries to make this question precise enough to answer. We use syllogistic logic — a small, fully controlled fragment of natural language — as a testbed, and ask models not whether a conclusion holds but which premises are needed to derive it. This lets us separate two things usually conflated under “compositional generalization”: extending a learned pattern to longer chains of reasoning, and recovering the underlying rules from complex cases to apply them to simpler ones. Models turn out to be markedly better at the first than the second, and their success depends systematically on the shape of the inference rather than its difficulty. I will end with two more encouraging results — that training on examples of the task itself substantially helps smaller models, and that even imperfect neural reasoners make effective assistants to a symbolic prover — and with what all this suggests about what “learning logic” could mean for a system that learns from data.

    Footnotes

    1. Vargas Guzmán, M., Szymanik, J., & Malicki, M. (2024). Testing the limits of logical reasoning in neural and hybrid models. Findings of the Association for Computational Linguistics: NAACL 2024, 2267–2279. • Bertolazzi, L., Vargas Guzmán, M., Bernardi, R., Malicki, M., & Szymanik, J. (2026). Teaching small language models to learn logic through meta-learning. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 8049–8080. • Vargas Guzmán, M., Szymanik, J., & Malicki, M. (2026). Hybrid models for natural language reasoning: The case of syllogistic logic. Proceedings of the 23rd International Conference on Principles of Knowledge Representation and Reasoning (KR), 1143–1152. ↩

    Faithful Explanations in the Age of Large Language Models

    Mateusz Lango (Charles University in Prague)

    In English Join online
    Abstract

    The fluency of modern large language models may lead to a perception that natural language generation is close to solved, yet a closer look reveals a recurring pattern of failure whenever a task requires exact, discrete fidelity to some underlying structure rather than fluent pattern completion. Reasoning that is straightforward in a single turn becomes surprisingly brittle across a dialogue; generation under explicit lexical or content constraints remains difficult to guarantee; and explanations produced by LLM-as-judge systems are frequently unfaithful to the actual decision process they claim to justify. I will argue that these three failures share a common shape: each is a case where an LLM must maintain or produce something exact and discrete, but is instead relying on an implicit, continuous representation not well suited to that job. This talk focuses on the third case - faithful explanation - and asks what happens when we make the intermediate representation explicit and symbolic, rather than leaving it to the model to reconstruct implicitly. I will present two lines of work built on this idea. The first constructs faithful explanations for image classifiers via a pipeline that separates the extraction of the (symbolic, verifiable) evidence behind a decision from its realization into fluent natural language, so that plausibility and faithfulness can be optimized somewhat independently. The second uses LLMs not to generate text directly, but to author interpretable, rule-based generation systems from scratch, producing data-to-text generators that are faithful and inspectable by construction rather than by post-hoc checking. Together, these case studies suggest a general recipe for faithful explanation: let neural models handle fluency and search, and let symbolic structure carry the guarantees.

    Towards Temporal Intelligence in Language Technologies: Modeling, Retrieval, and Reasoning

    Adam Jatowt (University of Innsbruck)

    In English Join online
    Abstract

    Time is central to how we understand the world. It shapes how we interpret events, construct narratives, and reason about change, causality, and evidence. In this talk, I will first examine how well large language models handle temporal information and temporal reasoning, an essential but still less explored dimension of language intelligence. I will then discuss recent advances in incorporating temporal awareness into language technologies, including time-aware representation learning, retrieval from evolving document collections, and the development of new resources for training and evaluation. I will also introduce temporal reasoning-oriented question answering and retrieval benchmarks that highlight the challenges of retrieving time-sensitive information, answering complex temporal questions, and reasoning over changing evidence. The talk will conclude with open challenges for building language technologies that can better understand, retrieve, and reason over information across time.

    In Search for Universal Language Similarity Metric with Application in Multilingual AI

    Michał Ptaszyński (Kitami Institute of Technology)

    In English Join online
    Abstract

    How similar must two languages be for an AI model trained on one to work on the other, and can we know before training? Multilingual AI models are usually trained on a few high-resource languages and then applied to many others. This lecture presents qWALS, an open-source metric of structural distance between more than 2,600 languages, built on nearly 200 features from the World Atlas of Language Structures (WALS), including word order, morphology, phonology, negation and grammatical gender. Unlike vector-based measures, every qWALS feature can be inspected and re-weighted for a given task.

    I show that cross-lingual transfer works better the more similar the source and target languages are. Once the features relevant to a task are selected, qWALS predicts transfer performance in syntactic parsing almost perfectly (up to r = −0.99). For Polish, a model trained on other Slavic languages clearly outperforms one trained on English. To additionally validate qWALS, three professional linguists judged 769 language-pair similarity questions, and their answers agreed with qWALS at least as closely as with each other.

    Finally, I discuss what this means for multilingual models and LLMs, namely, choosing source languages for transfer, estimating performance before training, and deciding which languages to include in training data. This matters most for low-resource and endangered languages, where data is scarce and the choice of source language matters most.

    Persuasion, Politeness, and the Social Meaning of Machine-Generated Language

    Agnieszka Faleńska (University of Stuttgart)

    In English Join online
    Abstract

    Large language models are becoming remarkably good at producing language that sounds convincing, respectful, and socially appropriate. But does this mean they are becoming better communicators?

    In this talk, I explore this question through a series of studies examining how language models differ from human writers, construct persuasive arguments, and adapt to their conversational partners. We will see that AI-generated language exhibits distinctive linguistic patterns, while often appearing more agreeable and persuasive than human writing. Beyond the quality of their arguments, models also reproduce subtle communicative strategies, such as expressing trust, acknowledging different perspectives, and establishing common ground. Yet the very linguistic choices that make communication seem natural and engaging can also carry unintended social meanings, signalling familiarity, hierarchy, or social expectations that may be inappropriate in a given context.

    Together, these findings highlight a fundamental challenge for human–AI interaction: producing human-like language is not the same as navigating its social meaning. Understanding AI communication requires looking beyond fluency and correctness to the social functions of language and how people interpret them.

    Safety Vulnerabilities in Spoken Language Models and Web Agents

    Karolina Stańczak (ETH Zurich)

    In English Join online
    Abstract

    LLM-based AI systems are rapidly expanding beyond single-modality text generation. Spoken language models combine speech and text to enable natural voice-based interaction, while web agents now act autonomously on real websites, completing complex tasks on a user’s behalf. Both introduce new attack opportunities that existing safety evaluations were not designed to capture. This presentation will explore these two topics. First, I will present JAMA (Joint Audio-text Multimodal Attack), which shows that jailbreaking spoken language models by perturbing a single modality is insufficient. Jointly optimizing adversarial perturbations across both text and audio increases jailbreak success by up to 20x over unimodal attacks, while a sequential approximation keeps this attack computationally efficient. Second, I will introduce SafeArena, the first benchmark designed to evaluate the deliberate misuse of web agents across categories such as misinformation, illegal activity, and cybercrime. Our Agent Risk Assessment framework reveals that leading agents, including GPT-4o and Claude-3.5 Sonnet, complete an alarming number of harmful tasks. I will conclude this talk by discussing why safety evaluation must keep pace with how LLM-based systems are deployed, accounting for both their expanding modalities and growing agentic capabilities.

Archive 2026–27

Older talks (425 since 2000)