arXiv subjects

Thierry Poibeau

Publications and source records attributed to Thierry Poibeau.

At least 19 recordsLinked to original sources

arXiv2026

Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution

We present our submission to the LLM track of the 2026 Computational Models of Reference, Anaphora and Coreference (CRAC 2026) shared task. With an average CoNLL F1 score of 74.32 on the official test set, our system ranked first in the LLM track, and third overall. Our system is based on the Gemma-3-27b model, fine-tuned using a two-stage strategy with a multilingual base adapter followed by dataset-specific adapters. We represent mention spans by their headword using an XML-inspired format with local reindexing and annotate documents iteratively. These design choices proved effective across languages, document lengths, and annotation guidelines.

cs.CL↗

arXiv2026

MajinBook: An open catalogue of digitally mediated world literature

This data paper introduces MajinBook, an open catalogue designed to facilitate the use of shadow libraries-such as Library Genesis and Z-Library-for computational social science and cultural analytics. By linking metadata from these vast, crowd-sourced archives with structured bibliographic data from Goodreads, we create a high-precision corpus of over 539,000 references to digitally mediated English-language books. Spanning three centuries and reflecting a contemporary selection bias, these entries are enriched with first publication dates, genres, and popularity metrics like ratings and reviews. Our methodology prioritises natively digital EPUB files to ensure machine-readable quality, while addressing biases in traditional corpora like HathiTrust, and includes secondary datasets for French, German, and Spanish. We evaluate the linkage strategy for accuracy, release all underlying data openly, and discuss the project's legal permissibility under EU and US frameworks for text and data mining in research.

cs.CL↗

arXiv2026

Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers

Through an analysis of arXiv papers, we report several shifts in word usage that are likely driven by large language models (LLMs) but have not previously received sufficient attention, such as the increased frequency of "beyond" and "via" in titles and the decreased frequency of "the" and "of" in abstracts. Due to the similarities among different LLMs, experiments show that current classifiers struggle to accurately determine which specific model generated a given text in multi-class classification tasks. Meanwhile, variations across LLMs also result in evolving patterns of word usage in academic papers. By adopting a direct and highly interpretable linear approach and accounting for differences between models and prompts, we quantitatively assess these effects and show that real-world LLM usage is heterogeneous and dynamic.

cs.CL↗

arXiv2026

Markovian Generation Chains in Large Language Models

The widespread use of large language models (LLMs) raises an important question: how do texts evolve when they are repeatedly processed by LLMs? In this paper, we define this iterative inference process as Markovian generation chains, where each step takes a specific prompt template and the previous output as input, without including any prior memory. In iterative rephrasing and round-trip translation experiments, the output either converges to a small recurrent set or continues to produce novel sentences over a finite horizon. Through sentence-level Markov chain modeling and analysis of simulated data, we show that iterative process can either increase or reduce sentence diversity depending on factors such as the temperature parameter and the initial input sentence. These results offer valuable insights into the dynamics of iterative LLM inference and their implications for multi-agent LLM systems.

cs.CL↗

arXiv2025

Modeling the Construction of a Literary Archetype: The Case of the Detective Figure in French Literature

This research explores the evolution of the detective archetype in French detective fiction through computational analysis. Using quantitative methods and character-level embeddings, we show that a supervised model is able to capture the unity of the detective archetype across 150 years of literature, from M. Lecoq (1866) to Commissaire Adamsberg (2017). Building on this finding, the study demonstrates how the detective figure evolves from a secondary narrative role to become the central character and the "reasoning machine" of the classical detective story. In the aftermath of the Second World War, with the importation of the hardboiled tradition into France, the archetype becomes more complex, navigating the genre's turn toward social violence and moral ambiguity.

cs.CL↗

arXiv2025

On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?

With the widespread use of large language models (LLMs), many researchers have turned their attention to detecting text generated by them. However, there is no consistent or precise definition of their target, namely "LLM-generated text". Differences in usage scenarios and the diversity of LLMs further increase the difficulty of detection. What is commonly regarded as the detecting target usually represents only a subset of the text that LLMs can potentially produce. Human edits to LLM outputs, together with the subtle influences that LLMs exert on their users, are blurring the line between LLM-generated and human-written text. Existing benchmarks and evaluation approaches do not adequately address the various conditions in real-world detector applications. Hence, the numerical results of detectors are often misunderstood, and their significance is diminishing. Therefore, detectors remain useful under specific conditions, but their results should be interpreted only as references rather than decisive indicators.

cs.CL↗

arXiv2025

The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works

While coreference resolution is attracting more interest than ever from computational literature researchers, representative datasets of fully annotated long documents remain surprisingly scarce. In this paper, we introduce a new annotated corpus of three full-length French novels, totaling over 285,000 tokens. Unlike previous datasets focused on shorter texts, our corpus addresses the challenges posed by long, complex literary works, enabling evaluation of coreference models in the context of long reference chains. We present a modular coreference resolution pipeline that allows for fine-grained error analysis. We show that our approach is competitive and scales effectively to long documents. Finally, we demonstrate its usefulness to infer the gender of fictional characters, showcasing its relevance for both literary analysis and downstream NLP tasks.

cs.CL↗

arXiv2024

Network Analysis, Plot Theory: Revisiting French Literature through Character Networks

Character recognition is a technique that enables the automated extraction of characters from texts, while coreference resolution establishes connections between various mentions of the same character, collectively facilitating the creation of expansive character networks (Moretti, 2011). Together, these technologies make it possible to navigate and analyze large literary corpora, opening new avenues for in-depth exploration and understanding of literature. We have created a system specifically for the French language, based on BookNLP-fr (the French counterpart of BookNLP) and NetworkX (a Python package for the manipulation and visualization of complex networks). This allows us to establish connections between series of literary works based on structural features (such as typical relationships between characters) or specific subgenres (for instance, adventure novels featuring a group of young heroes). In this paper, as an illustration, we show the networks obtained at different stages of the short novel Boule de Suif from Maupassant (a French 19th century novelist). These figures effectively illustrate how the relationships between the characters develop over the course of the story.

cs.DL↗

arXiv2024

Annotating References to Mythological Entities in French Literature

In this paper, we explore the relevance of large language models (LLMs) for annotating references to Roman and Greek mythological entities in modern and contemporary French literature. We present an annotation scheme and demonstrate that recent LLMs can be directly applied to follow this scheme effectively, although not without occasionally making significant analytical errors. Additionally, we show that LLMs (and, more specifically, ChatGPT) are capable of offering interpretative insights into the use of mythological references by literary authors. However, we also find that LLMs struggle to accurately identify relevant passages in novels (when used as an information retrieval engine), often hallucinating and generating fabricated examples-an issue that raises significant ethical concerns. Nonetheless, when used carefully, LLMs remain valuable tools for performing annotations with high accuracy, especially for tasks that would be difficult to annotate comprehensively on a large scale through manual methods alone.

cs.AI↗

arXiv2024

An Incremental Clustering Baseline for Event Detection on Twitter

Event detection in text streams is a crucial task for the analysis of online media and social networks. One of the current challenges in this field is establishing a performance standard while maintaining an acceptable level of computational complexity. In our study, we use an incremental clustering algorithm combined with recent advancements in sentence embeddings. Our objective is to compare our findings with previous studies, specifically those by Cao et al. (2024) and Mazoyer et al. (2020). Our results demonstrate significant improvements and could serve as a relevant baseline for future research in this area.

cs.CL↗

arXiv2024

Probing for the Usage of Grammatical Number

A central quest of probing is to uncover how pre-trained models encode a linguistic property within their representations. An encoding, however, might be spurious-i.e., the model might not rely on it when making predictions. In this paper, we try to find encodings that the model actually uses, introducing a usage-based probing setup. We first choose a behavioral task which cannot be solved without using the linguistic property. Then, we attempt to remove the property by intervening on the model's representations. We contend that, if an encoding is used by the model, its removal should harm the performance on the chosen behavioral task. As a case study, we focus on how BERT encodes grammatical number, and on how it uses this encoding to solve the number agreement task. Experimentally, we find that BERT relies on a linear encoding of grammatical number to produce the correct behavioral output. We also find that BERT uses a separate encoding of grammatical number for nouns and verbs. Finally, we identify in which layers information about grammatical number is transferred from a noun to its head verb.

cs.CL↗

arXiv2023

How to Evaluate Coreference in Literary Texts?

In this short paper, we examine the main metrics used to evaluate textual coreference and we detail some of their limitations. We show that a unique score cannot represent the full complexity of the problem at stake, and is thus uninformative, or even misleading. We propose a new way of evaluating coreference, taking into account the context (in our case, the analysis of fictions, esp. novels). More specifically, we propose to distinguish long coreference chains (corresponding to main characters), from short ones (corresponding to secondary characters), and singletons (isolated elements). This way, we hope to get more interpretable and thus more informative results through evaluation.

cs.CL↗

arXiv2023

On the Correspondence between Compositionality and Imitation in Emergent Neural Communication

Compositionality is a hallmark of human language that not only enables linguistic generalization, but also potentially facilitates acquisition. When simulating language emergence with neural networks, compositionality has been shown to improve communication performance; however, its impact on imitation learning has yet to be investigated. Our work explores the link between compositionality and imitation in a Lewis game played by deep neural agents. Our contributions are twofold: first, we show that the learning algorithm used to imitate is crucial: supervised learning tends to produce more average languages, while reinforcement learning introduces a selection pressure toward more compositional languages. Second, our study reveals that compositional languages are easier to imitate, which may induce the pressure toward compositional languages in RL imitation settings.

cs.CL↗

arXiv2022

Modern French Poetry Generation with RoBERTa and GPT-2

We present a novel neural model for modern poetry generation in French. The model consists of two pretrained neural models that are fine-tuned for the poem generation task. The encoder of the model is a RoBERTa based one while the decoder is based on GPT-2. This way the model can benefit from the superior natural language understanding performance of RoBERTa and the good natural language generation performance of GPT-2. Our evaluation shows that the model can create French poetry successfully. On a 5 point scale, the lowest score of 3.57 was given by human judges to typicality and emotionality of the output poetry while the best score of 3.79 was given to understandability.

cs.CL↗

arXiv2022

Video Games as a Corpus: Sentiment Analysis using Fallout New Vegas Dialog

We present a method for extracting a multilingual sentiment annotated dialog data set from Fallout New Vegas. The game developers have preannotated every line of dialog in the game in one of the 8 different sentiments: \textit{anger, disgust, fear, happy, neutral, pained, sad } and \textit{surprised}. The game has been translated into English, Spanish, German, French and Italian. We conduct experiments on multilingual, multilabel sentiment analysis on the extracted data set using multilingual BERT, XLMRoBERTa and language specific BERT models. In our experiments, multilingual BERT outperformed XLMRoBERTa for most of the languages, also language specific models were slightly better than multilingual BERT for most of the languages. The best overall accuracy was 54\% and it was achieved by using multilingual BERT on Spanish data. The extracted data set presents a challenging task for sentiment analysis. We have released the data, including the testing and training splits, openly on Zenodo. The data set has been shuffled for copyright reasons.

cs.CL↗

arXiv2022

Automatic Generation of Factual News Headlines in Finnish

We present a novel approach to generating news headlines in Finnish for a given news story. We model this as a summarization task where a model is given a news article, and its task is to produce a concise headline describing the main topic of the article. Because there are no openly available GPT-2 models for Finnish, we will first build such a model using several corpora. The model is then fine-tuned for the headline generation task using a massive news corpus. The system is evaluated by 3 expert journalists working in a Finnish media house. The results showcase the usability of the presented approach as a headline suggestion tool to facilitate the news production process.

cs.CL↗

arXiv2022

Word Order Matters when you Increase Masking

Word order, an essential property of natural languages, is injected in Transformer-based neural language models using position encoding. However, recent experiments have shown that explicit position encoding is not always useful, since some models without such feature managed to achieve state-of-the art performance on some tasks. To understand better this phenomenon, we examine the effect of removing position encodings on the pre-training objective itself (i.e., masked language modelling), to test whether models can reconstruct position information from co-occurrences alone. We do so by controlling the amount of masked tokens in the input sentence, as a proxy to affect the importance of position information for the task. We find that the necessity of position information increases with the amount of masking, and that masked language models without position encodings are not able to reconstruct this information on the task. These findings point towards a direct relationship between the amount of masking and the ability of Transformers to capture order-sensitive aspects of language using position encoding.

cs.CL↗

arXiv2022

Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERT

Both humans and neural language models are able to perform subject-verb number agreement (SVA). In principle, semantics shouldn't interfere with this task, which only requires syntactic knowledge. In this work we test whether meaning interferes with this type of agreement in English in syntactic structures of various complexities. To do so, we generate both semantically well-formed and nonsensical items. We compare the performance of BERT-base to that of humans, obtained with a psycholinguistic online crowdsourcing experiment. We find that BERT and humans are both sensitive to our semantic manipulation: They fail more often when presented with nonsensical items, especially when their syntactic structure features an attractor (a noun phrase between the subject and the verb that has not the same number as the subject). We also find that the effect of meaningfulness on SVA errors is stronger for BERT than for humans, showing higher lexical sensitivity of the former on this task.

cs.CL↗