arXiv subjects

Tijl De Bie

Publications and source records attributed to Tijl De Bie.

At least 19 recordsLinked to original sources

arXiv2026

Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs

When LLMs judge moral dilemmas, do they reach different conclusions in different languages, and if so, why? Two factors could drive such differences: the language of the dilemma itself, or the language in which the model reasons. Standard evaluation conflates these by testing only matched conditions (e.g., English dilemma with English reasoning). We introduce a methodology that separately manipulates each factor, covering also mismatched conditions (e.g., English dilemma with Chinese reasoning), enabling decomposition of their contributions. To study \emph{what} changes, we propose an approach to interpret the moral judgments in terms of Moral Foundations Theory. As a side result, we identify evidence for splitting the Authority dimension into a family-related and an institutional dimension. Applying this methodology to English-Chinese moral judgment with 13 LLMs, we demonstrate its diagnostic power: (1) the framework isolates reasoning-language effects as contributing twice the variance of input-language effects; (2) it detects context-dependency in nearly half of models that standard evaluation misses; and (3) a diagnostic taxonomy translates these patterns into deployment guidance. We release our code and datasets at https://anonymous.4open.science/r/CrossCulturalMoralJudgement.

cs.CL↗

arXiv2026

People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe

As Large Language Models (LLMs) are increasingly used as a primary source of information and advice, understanding their alignment to humans in terms of values becomes a pressing concern. A growing literature has leveraged large scale surveys to investigate to what extent LLMs' and humans' stated values and opinions align. With limited exceptions, studied populations have been defined country borders or cultural bounds. Yet, this focus neglects the role that socio-demographic divides may play for value alignment disparities. Relying on the European Social Survey, we address this knowledge gap by considering value alignment displayed with respect to 10 prominent commercial LLMs in terms of 15 socio-demographic variables as well as country of residence. Our analyses reveal that LLMs are indeed unequally aligned to the values of different socio-demographic groups, notably those defined by education, income, occupation and religion. When examining alignment at the individual level, a respondent's country, taken as a stand-alone variable, explains a substantial amount of variation that is on par with the full set of considered socio-demographics. Further disentangling the respective role of country-level and socio-demographic factors, we find they are complementary in explaining value alignment patterns, with their relative weights varying across the subset of questions considered.

cs.AI↗

arXiv2026

Grokipedia vs Wikipedia: An LLM-Based Audit of Political Neutrality along Ideologies

Online encyclopedias shape political opinion and, through it, democratic discourse. In late 2025, Grokipedia was released, an encyclopedia written entirely by the LLM Grok. One motivation behind the project was to provide an unbiased alternative to Wikipedia, which has faced accusations of "left-wing" and "liberal" bias. But does an encyclopedia written by an LLM deliver greater neutrality, or does it simply embed a different ideology? We conduct a large-scale political bias study on Grokipedia and Wikipedia, analysing 1,394 article pairs describing members of government for neutrality along nine expert-coded ideology dimensions employing four LLM judges, Grok, Claude, Mistral, and DeepSeek. As the LLMs could themselves be biased, we also investigate patterns in their judgments. We find all LLM-judges, including Grok, to rate Grokipedia less neutral than Wikipedia. Both encyclopedias are rated as portraying politicians favourably overall, but towards different ideological groups. Grokipedia particularly favours economically right-wing politicians and penalises socially liberal ones, while Wikipedia is rated as favourably biased towards the latter.

cs.CL↗

arXiv2026

JobHop v2: A Large-Scale Career Trajectory Dataset from Unstructured Resumes

Large-scale, richly annotated career trajectory data underpins workforce planning, job recommendation, and labour market analysis, yet publicly available datasets are either small, closed to independent use, or built from pre-standardized occupational codes with LLM-synthesized rather than authentic free text. We present JobHop~v2, an improved version of the publicly available JobHop dataset, constructed through end-to-end large language model (LLM) extraction from a corpus of ${\sim}440{,}000$ pseudonymized, multilingual resumes provided by VDAB, the Flemish Public Employment Service. The released dataset comprises $355{,}315$ career trajectories annotated with ESCO occupational codes, quarter-level temporal information, and normalized five-level education attainment, broadening both the coverage and the annotation richness of the original release. Relative to v1, JobHop~v2 introduces a redesigned extraction pipeline based on reasoning-controlled LLM inference with a retry mechanism (achieving a 100% JSON parse rate), a richer extraction schema, and a revised evaluation protocol scored against three complementary annotation baselines. Evaluated against these baselines, our best extractor comes closest to the inter-annotator agreement ceiling among all compared models, trailing it by only 1.1-2.7 percentage points. The dataset and code are publicly released to support reproducible career-trajectory research.

cs.CL↗

arXiv2026

STEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling

Career paths encode decades of skill acquisition, role transitions, and educational investment, and understanding them at scale underpins workforce planning, labor market policy, and job recommendation. Resumes are a rich source of information about career paths: they contain detailed descriptions of work experience, education, and skills. Yet their unstructured, heterogeneous, and multilingual nature has long prevented large-scale systematic analysis. With the advent of large language models (LLMs), it is now possible to source rich career trajectory data containing temporal and educational signals from unstructured resumes, enabling new opportunities for career-path recommendation. Exploiting this opportunity, we present STEP (Sequential Trajectory of Employment Prediction), a novel career-path recommendation system that leverages temporal and educational signals to predict the next job in a career trajectory. STEP integrates a time-decay Gated Recurrent Unit (GRU) cell to model temporal dynamics, Feature-wise Linear Modulation (FiLM) conditioned on educational attainment, and attention-based sequence pooling to select relevant features for next job prediction. To improve internal occupation representation for STEP, we introduce ROUTE, a two-stage contrastive procedure that first adapts a multilingual encoder to the career domain via unsupervised denoising autoencoding, then performs supervised contrastive fine-tuning with guided negative selection. We evaluate STEP on four datasets of career trajectories, including an improved version of our publicly available JobHop dataset, and show that it outperforms state-of-the-art baselines in next job prediction. The dataset and code are publicly released to support reproducible career-trajectory research.

cs.CL↗

arXiv2026

Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications

The rapid rise of Large Language Models (LLMs) has created new disruptive possibilities for persuasive communication, enabling fully-automated, personalized, and interactive content generation at an unprecedented scale. In this paper, we survey the emerging field of LLM-based persuasion, reviewing empirical studies that measure the influence of LLM Systems on human attitudes and behaviors. We categorize applications across domains such as politics, marketing, public health, e-commerce, and charitable giving, finding that such systems have frequently achieved human-level or even superhuman persuasiveness. Synthesizing recent evidence, we identify key factors influencing this effectiveness, including the interaction approach, model scale and capability, prompt design, personalization, and AI source disclosure. Furthermore, we critically examine the experimental designs and success metrics used to evaluate these Systems, distinguishing between direct behavioral outcomes and proxy indicators. Our survey suggests that the current capabilities of LLM-based persuasion pose profound ethical and societal risks, including to information integrity, fairness and inclusion, privacy, and individual autonomy. These risks underscore the urgent need for ethical guidelines and updated regulatory frameworks to avoid the widespread deployment of irresponsible and harmful LLM Systems.

cs.CL↗

arXiv2026

VIGIL: An Extensible System for Real-Time Detection and Mitigation of Cognitive Bias Triggers

The rise of generative AI is posing increasing risks to online information integrity and civic discourse. Most concretely, such risks can materialise in the form of mis- and disinformation. As a mitigation, media-literacy and transparency tools have been developed to address factuality of information and the reliability and ideological leaning of information sources. However, a subtler but possibly no less harmful threat to civic discourse is to use of persuasion or manipulation by exploiting human cognitive biases and related cognitive limitations. To the best of our knowledge, no tools exist to directly detect and mitigate the presence of triggers of such cognitive biases in online information. We present VIGIL (VIrtual GuardIan angeL), the first browser extension for real-time cognitive bias trigger detection and mitigation, providing in-situ scroll-synced detection, LLM-powered reformulation with full reversibility, and privacy-tiered inference from fully offline to cloud. VIGIL is built to be extensible with third-party plugins, with several plugins that are rigorously validated against NLP benchmarks are already included. It is open-sourced at https://github.com/aida-ugent/vigil.

cs.CL↗

arXiv2026

Cards Against LLMs: Benchmarking Humor Alignment in Large Language Models

Humor is one of the most culturally embedded and socially significant dimensions of human communication, yet it remains largely unexplored as a dimension of Large Language Model (LLM) alignment. In this study, five frontier language models play the same Cards Against Humanity games (CAH) as human players. The models select the funniest response from a slate of ten candidate cards across 9,894 rounds. While all models exceed the random baseline, alignment with human preference remains modest. More striking is that models agree with each other substantially more often than they agree with humans. We show that this preference is partly explained by systematic position biases and content preferences, raising the question whether LLM humor judgment reflects genuine preference or structural artifacts of inference and alignment.

cs.CL↗

arXiv2026

WorkRB: A Community-Driven Evaluation Framework for AI in the Work Domain

Today's evolving labor markets rely increasingly on recommender systems for hiring, talent management, and workforce analytics, with natural language processing (NLP) capabilities at the core. Yet, research in this area remains highly fragmented. Studies employ divergent ontologies (ESCO, O*NET, national taxonomies), heterogeneous task formulations, and diverse model families, making cross-study comparison and reproducibility exceedingly difficult. General-purpose benchmarks lack coverage of work-specific tasks, and the inherent sensitivity of employment data further limits open evaluation. We present \textbf{WorkRB} (Work Research Benchmark), the first open-source, community-driven benchmark tailored to work-domain AI. WorkRB organizes 13 diverse tasks from 7 task groups as unified recommendation and NLP tasks, including job/skill recommendation, candidate recommendation, similar item recommendation, and skill extraction and normalization. WorkRB enables both monolingual and cross-lingual evaluation settings through dynamic loading of multilingual ontologies. Developed within a multi-stakeholder ecosystem of academia, industry, and public institutions, WorkRB has a modular design for seamless contributions and enables integration of proprietary tasks without disclosing sensitive data. WorkRB is available under the Apache 2.0 license at https://github.com/techwolf-ai/WorkRB.

cs.CL↗

arXiv2026

Multiresolution Analysis and Statistical Thresholding on Dynamic Networks

Detecting structural change in dynamic network data has wide-ranging applications. Existing approaches typically divide the data into time bins, extract network features within each bin, and then compare these features over time. This introduces an inherent tradeoff between temporal resolution and the statistical stability of the extracted features. Despite this tradeoff, reminiscent of time-frequency tradeoffs in signal processing, most methods rely on a fixed temporal resolution. Choosing an appropriate resolution parameter is typically difficult and can be especially problematic in domains like cybersecurity, where anomalous behavior may emerge at multiple time scales. We address this challenge by proposing ANIE (Adaptive Network Intensity Estimation), a multi-resolution framework designed to automatically identify the time scales at which network structure evolves, enabling the joint detection of both rapid and gradual changes. Modeling interactions as Poisson processes, our method proceeds in two steps: (1) estimating a low-dimensional subspace of node behavior, and (2) deriving a set of novel empirical affinity coefficients that quantify change in interaction intensity between latent factors and support statistical testing for structural change across time scales. We provide theoretical guarantees for subspace estimation and the asymptotic behavior of the affinity coefficients, enabling model-based change detection. Experiments on synthetic networks show that ANIE adapts to the appropriate time resolution and is able to capture sharp structural changes while remaining robust to noise. Furthermore, applications to real-world data showcase the practical benefits of ANIE's multiresolution approach to detecting structural change over fixed resolution methods.

cs.LG↗

arXiv2025

JobHop: A Large-Scale Dataset of Career Trajectories

Understanding labor market dynamics is essential for policymakers, employers, and job seekers. However, comprehensive datasets that capture real-world career trajectories are scarce. In this paper, we introduce JobHop, a large-scale public dataset derived from anonymized resumes provided by VDAB, the public employment service in Flanders, Belgium. Utilizing Large Language Models (LLMs), we process unstructured resume data to extract structured career information, which is then normalized to standardized ESCO occupation codes using a multi-label classification model. This results in a rich dataset of over 1.67 million work experiences, extracted from and grouped into more than 361,000 user resumes and mapped to standardized ESCO occupation codes, offering valuable insights into real-world occupational transitions. This dataset enables diverse applications, such as analyzing labor market mobility, job stability, and the effects of career breaks on occupational transitions. It also supports career path prediction and other data-driven decision-making processes. To illustrate its potential, we explore key dataset characteristics, including job distributions, career breaks, and job transitions, demonstrating its value for advancing labor market research.

cs.CL↗

arXiv2025

Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration

Creating robust occupation taxonomies, vital for applications ranging from job recommendation to labor market intelligence, is challenging. Manual curation is slow, while existing automated methods are either not adaptive to dynamic regional markets (top-down) or struggle to build coherent hierarchies from noisy data (bottom-up). We introduce CLIMB (CLusterIng-based Multi-agent taxonomy Builder), a framework that fully automates the creation of high-quality, data-driven taxonomies from raw job postings. CLIMB uses global semantic clustering to distill core occupations, then employs a reflection-based multi-agent system to iteratively build a coherent hierarchy. On three diverse, real-world datasets, we show that CLIMB produces taxonomies that are more coherent and scalable than existing methods and successfully capture unique regional characteristics. We release our code and datasets at https://anonymous.4open.science/r/CLIMB.

cs.AI↗

arXiv2025

Building and Measuring Trust between Large Language Models

As large language models (LLMs) increasingly interact with each other, most notably in multi-agent setups, we may expect (and hope) that `trust' relationships develop between them, mirroring trust relationships between human colleagues, friends, or partners. Yet, though prior work has shown LLMs to be capable of identifying emotional connections and recognizing reciprocity in trust games, little remains known about (i) how different strategies to build trust compare, (ii) how such trust can be measured implicitly, and (iii) how this relates to explicit measures of trust. We study these questions by relating implicit measures of trust, i.e. susceptibility to persuasion and propensity to collaborate financially, with explicit measures of trust, i.e. a dyadic trust questionnaire well-established in psychology. We build trust in three ways: by building rapport dynamically, by starting from a prewritten script that evidences trust, and by adapting the LLMs' system prompt. Surprisingly, we find that the measures of explicit trust are either little or highly negatively correlated with implicit trust measures. These findings suggest that measuring trust between LLMs by asking their opinion may be deceiving. Instead, context-specific and implicit measures may be more informative in understanding how LLMs trust each other.

cs.MA↗

arXiv2025

BiMi Sheets: Infosheets for bias mitigation methods

Over the past 15 years, hundreds of bias mitigation methods have been proposed in the pursuit of fairness in machine learning (ML). However, algorithmic biases are domain-, task-, and model-specific, leading to a `portability trap': bias mitigation solutions in one context may not be appropriate in another. Thus, a myriad of design choices have to be made when creating a bias mitigation method, such as the formalization of fairness it pursues, and where and how it intervenes in the ML pipeline. This creates challenges in benchmarking and comparing the relative merits of different bias mitigation methods, and limits their uptake by practitioners. We propose BiMi Sheets as a portable, uniform guide to document the design choices of any bias mitigation method. This enables researchers and practitioners to quickly learn its main characteristics and to compare with their desiderata. Furthermore, the sheets' structure allow for the creation of a structured database of bias mitigation methods. In order to foster the sheets' adoption, we provide a platform for finding and creating BiMi Sheets at bimisheet.com.

cs.LG↗

arXiv2025

What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices

Large Language Models (LLMs) are increasingly deployed as gateways to information, yet their content moderation practices remain underexplored. This work investigates the extent to which LLMs refuse to answer or omit information when prompted on political topics. To do so, we distinguish between hard censorship (i.e., generated refusals, error messages, or canned denial responses) and soft censorship (i.e., selective omission or downplaying of key elements), which we identify in LLMs' responses when asked to provide information on a broad range of political figures. Our analysis covers 14 state-of-the-art models from Western countries, China, and Russia, prompted in all six official United Nations (UN) languages. Our analysis suggests that although censorship is observed across the board, it is predominantly tailored to an LLM provider's domestic audience and typically manifests as either hard censorship or soft censorship (though rarely both concurrently). These findings underscore the need for ideological and geographic diversity among publicly available LLMs, and greater transparency in LLM moderation strategies to facilitate informed user choices. All data are made freely available.

cs.CL↗

arXiv2025

Biased Heritage: How Datasets Shape Models in Facial Expression Recognition

In recent years, the rapid development of artificial intelligence (AI) systems has raised concerns about our ability to ensure their fairness, that is, how to avoid discrimination based on protected characteristics such as gender, race, or age. While algorithmic fairness is well-studied in simple binary classification tasks on tabular data, its application to complex, real-world scenarios-such as Facial Expression Recognition (FER)-remains underexplored. FER presents unique challenges: it is inherently multiclass, and biases emerge across intersecting demographic variables, each potentially comprising multiple protected groups. We present a comprehensive framework to analyze bias propagation from datasets to trained models in image-based FER systems, while introducing new bias metrics specifically designed for multiclass problems with multiple demographic groups. Our methodology studies bias propagation by (1) inducing controlled biases in FER datasets, (2) training models on these biased datasets, and (3) analyzing the correlation between dataset bias metrics and model fairness notions. Our findings reveal that stereotypical biases propagate more strongly to model predictions than representational biases, suggesting that preventing emotion-specific demographic patterns should be prioritized over general demographic balance in FER datasets. Additionally, we observe that biased datasets lead to reduced model accuracy, challenging the assumed fairness-accuracy trade-off.

cs.CV↗

arXiv2025

Large Language Models Reflect the Ideology of their Creators

Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI) assistants like ChatGPT and already play an influential role in how humans access information. However, the behavior of LLMs varies depending on their design, training, and use. In this paper, we prompt a diverse panel of popular LLMs to describe a large number of prominent personalities with political relevance, in all six official languages of the United Nations. By identifying and analyzing moral assessments reflected in their responses, we find normative differences between LLMs from different geopolitical regions, as well as between the responses of the same LLM when prompted in different languages. Among only models in the United States, we find that popularly hypothesized disparities in political views are reflected in significant normative differences related to progressive values. Among Chinese models, we characterize a division between internationally- and domestically-focused models. Our results show that the ideological stance of an LLM appears to reflect the worldview of its creators. This poses the risk of political instrumentalization and raises concerns around technological and regulatory efforts with the stated aim of making LLMs ideologically 'unbiased'.

cs.CL↗

arXiv2025

SimHawNet: A Modified Hawkes Process for Temporal Network Simulation

Temporal networks allow representing connections between objects while incorporating the temporal dimension. While static network models can capture unchanging topological regularities, they often fail to model the effects associated with the causal generative process of the network that occurs in time. Hence, exploiting the temporal aspect of networks has been the focus of many recent studies. In this context, we propose a new framework for generative models of continuous-time temporal networks. We assume that the activation of the edges in a temporal network is driven by a specified temporal point process. This approach allows to directly model the waiting time between events while incorporating time-varying history-based features as covariates in the predictions. Coupled with a thinning algorithm designed for the simulation of point processes, SimHawNet enables simulation of the evolution of temporal networks in continuous time. Finally, we introduce a comprehensive evaluation framework to assess the performance of such an approach, in which we demonstrate that SimHawNet successfully simulates the evolution of networks with very different generative processes and achieves performance comparable to the state of the art, while being significantly faster.

cs.LG↗