arXiv subjects

Stefan Feuerriegel

Publications and source records attributed to Stefan Feuerriegel.

At least 19 recordsLinked to original sources

arXiv2026

Designing Against Deskilling: Metacognitive Feedback Reduces Cognitive Offloading to LLM Assistants

Cognitive offloading to AI can reduce opportunities to practice skills, creating risks of deskilling. However, it remains unclear how to prevent deskilling without restricting access to AI. Here, we design two interventions to reduce offloading decisions: (1) metacognitive feedback that makes the implications of offloading for users explicit, and (2) an effort-based reward that incentivizes less extensive LLM assistance. We test both in a preregistered online experiment ($N = 704$) with a 2$\times$2 design and a no-AI control. The task was to practice fraction arithmetic with an LLM-based assistant that provided solutions only on explicit request, followed by an unaided test. Metacognitive feedback reduced answer offloading (OR $= 0.47$) and improved test performance (OR $= 1.51$). We found no evidence that the reward affected either outcome. Our results identify metacognitive feedback as a promising design choice to reduce cognitive offloading.

cs.HC↗

arXiv2026

XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?

Evaluating the quality of explanations produced by explainable AI (XAI) methods remains challenging because existing approaches often rely on subjective human judgment, limiting reproducibility, scalability, and comparability between studies. We examine whether LLMs can serve as a reproducible and scalable mechanism to make comparative assessments of the quality of XAI explanations. We introduce XAI-Arena, an LLM-as-a-judge framework for scalable, reproducible, multidimensional, and stakeholder-sensitive evaluation of XAI explanation quality. XAI-Arena then allows us to compare XAI explanations along various dimensions, namely, perceived simplicity, clarity, task adequacy, trust calibration, actionability, transparency, faithfulness, and overall interpretability. We then benchmark XAI explanation methods across various datasets, machine learning models, and stakeholder personas. Human validation shows a strong positive association between LLM-generated and human ratings (Spearman's rho=.693, p<.001). Together, LLM-based evaluations can capture systematic differences in XAI explanation quality and provide a scalable and reproducible framework for comparative assessment of XAI explanations.

cs.AI↗

arXiv2026

Beyond Surface Cues: Disentangling Sociocultural Signals in Multilingual LLMs

Multilingual LLM outputs can vary across sociocultural contexts. However, evidence of cultural grounding can be misleading: identity labels may be inferred from explicit or indirect textual cues, while names and wording can reveal the source language. Treating all these signals as evidence of cultural grounding may obscure potential biases. We present a human-validated, multi-agent audit that separates three questions: whether outputs reproduce social biases, whether identity groups are represented differently, and whether outputs reflect cross-cultural patterns. The study analyzes 89,253 outputs from 12 LLMs in English, French, and Chinese, spanning 18 occupations and three task conditions. We find that bias representation varies systematically across languages and tasks. Removing direct identity cues sharply reduces identity-label prediction in English and Chinese, but has a much smaller effect in French. Across all language-genre settings, the cultural context associated with the source language receives the highest average relevance score, with moderate agreement between automated and human ratings. However, the ability to identify the source language drops substantially after translation and again after masking names. Without these controls, multilingual audits may mistake surface cues for cultural understanding, leading to misleading conclusions about cross-cultural variation and bias. Our audit offers a practical framework for separating such shortcuts from more meaningful cross-cultural patterns.

cs.CL↗

arXiv2026

LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports

Large language models (LLMs) increasingly support decisions about uncertain future events, yet evaluating their ability to forecast real-world outcomes remains difficult. In particular, existing benchmarks are typically static and retrospective, and therefore cannot test how information is synthesized by LLMs to predict future events under uncertainty. We introduce LLM-SoccerArena (https://llm-soccerarena.com), a prospective live benchmark that evaluates how well LLMs forecast real-world sports events before the outcomes are known. LLM-SoccerArena provides (1) a prospective live benchmark protocol, (2) a public open-source platform, and (3) a factorial benchmark design together with tournament-related questions (e.g., which team will win). LLM-SoccerArena automatically records timestamped, schema-validated forecasts of unresolved events, together with prompts, model versions, tool traces, and costs. The factorial design varies along four dimensions: (1) model version (e.g., GPT-5.5, Claude Opus 4.8); (2) information access; (3) prompting strategy, and (4) forecast horizon. We demonstrate LLM-SoccerArena through a large-scale evaluation of the 2026 FIFA World Cup, in which seven LLMs generated forecasts for all 104 matches and 15 tournament-related questions. We provide a detailed analysis of model performance across information access, prompting strategy, and forecast horizon. As a result, LLM-SoccerArena provides new evidence about the forecasting performance of state-of-the-art LLMs. For example, LLMs with web access outperform those without, but only by a small margin (i.e., a 0.023 improvement in Brier score). Overall, LLM-SoccerArena provides a flexible, open-source platform for prospective benchmarking of unresolved events. LLM-SoccerArena will be continuously updated, and can be directly applied to future national and international tournaments and league competitions.

cs.AI↗

arXiv2026

SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis

Survival analysis is a cornerstone of clinical research by modeling time-to-event outcomes such as metastasis, disease relapse, or patient death. Unlike standard tabular data, survival data often come with incomplete event information due to dropout, or loss to follow-up. This poses unique challenges for synthetic data generation, where it is crucial for clinical research to faithfully reproduce both the event-time distribution and the censoring mechanism. In this paper, we propose SurvDiff an end-to-end diffusion model specifically designed for generating synthetic data in survival analysis. SurvDiff is tailored to capture the data-generating mechanism by jointly generating mixed-type covariates, event times, and right-censoring, guided by a survival-tailored loss function. The loss encodes the time-to-event structure and directly optimizes for downstream survival tasks, which ensures that SurvDiff (i) reproduces realistic event-time distributions and (ii) preserves the censoring mechanism. Across multiple datasets, we show that SurvDiff consistently outperforms state-of-the-art generative baselines in both distributional fidelity and survival model evaluation metrics across multiple medical datasets. To the best of our knowledge, SurvDiff is the first end-to-end diffusion model explicitly designed for generating synthetic survival data.

cs.LG↗

arXiv2026

Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference

Foundation models based on prior-data fitted networks (PFNs) have shown strong empirical performance in causal inference by framing the task as an in-context learning problem. However, it is unclear whether PFN-based causal estimators provide uncertainty quantification that is consistent with classical frequentist estimators. In this work, we address this gap by analyzing the frequentist consistency of PFN-based estimators for the average treatment effect (ATE). (1) We show that existing PFNs, when interpreted as Bayesian ATE estimators, can exhibit prior-induced confounding bias: the prior is not asymptotically overwritten by data, which, in turn, prevents frequentist consistency. (2) As a remedy, we suggest employing a calibration procedure based on a one-step posterior correction (OSPC). We show that the OSPC helps to restore frequentist consistency and can yield a semi-parametric Bernstein-von Mises theorem for calibrated PFNs (i.e., both the calibrated PFN-based estimators and the classical semi-parametric efficient estimators converge in distribution with growing data size). (3) Finally, we implement OSPC through tailoring martingale posteriors on top of the PFNs. In this way, we are able to recover functional nuisance posteriors from PFNs, required by the OSPC. In multiple (semi-)synthetic experiments, PFNs calibrated with our martingale posterior OSPC produce ATE uncertainty that (i) asymptotically matches frequentist uncertainty and (ii) is well calibrated in finite samples in comparison to other Bayesian ATE estimators.

cs.LG↗

arXiv2026

AutoSynthesis: An agentic system for automated meta-analysis

Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis. Given a research question in natural language, AutoSynthesis formulates a search strategy, retrieves scientific literature, screens candidate studies, assesses full-text eligibility, extracts quantitative statistics, computes standardized effect sizes, and finally performs random-effects meta-analysis. AutoSynthesis further supports heterogeneity analysis to examine how effect sizes vary across moderators, as well as risk-of-bias assessment. As output, AutoSynthesis produces a transparent report aligned with PRISMA guidelines. In our application, AutoSynthesis screened over 28 studies and extracted more than 20 quantitative claims. The pooled effect estimates produced by AutoSynthesis are similar to Hedges' $g$ of expert-conducted meta-analyses, indicating close agreement with manual evidence synthesis. Together, these results show that AutoSynthesis can make quantitative evidence synthesis more scalable, thereby supporting evidence-based decision-making across disciplines.

cs.AI↗

arXiv2026

Hyperlocal monitoring of urban activity reveals responses to heat exposure

Rising temperatures create new challenges for local heat adaptation. Yet, it remains unclear how urban activity changes during hot periods and which urban environments people concentrate in as temperatures rise. Here, we perform a hyperlocal spatiotemporal analysis of urban activity across 10 German cities over a two-month period in 2024 with different levels of heat exposure. To monitor urban activity, we use fine-grained telecommunication data to map locations of people with high spatio-temporal resolution (i.e., hourly at 100m x 155m grid cells), yielding more than 100 million data points. We then link activity counts with hourly weather records and point-of-interest data. We find that sustained periods of hot weather, defined as at least three consecutive days with daily maximum temperatures $\geq 25$°C, are characterized by below-expected city-wide presence, with activity counts that are 1.5 percentage points below regular urban activity. During hot periods, urban activity concentrates more strongly around leisure- and culture-oriented amenities (e.g., cafés or swimming pools), with an increase of up to around 10 percentage points relative to cooler days, while public-service environments (e.g., educational and health facilities) show weaker or negative shifts. Our study provides policy-makers with fine-grained monitoring of which urban areas attract citizens during heat exposure, which can enable evidence-based, spatially-targeted urban heat adaptation plans.

physics.soc-ph↗

arXiv2026

Synthetic Interaction Data for Scalable Personalization in Large Language Models

Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users. This gap is primarily due to (i) the absence of high-quality, privacy-sensitive data that capture personalized user-LLM interactions at scale, and (ii) the lack of robust reward signals for individual preferences. To overcome existing data limitations, we introduce a high-fidelity synthetic data generation framework called PersonaGym. Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process via an agentic LLM system to simulate realistic preference behaviors and semantic-aware noise in order to generate personalized multi-turn interaction trajectories. Using PersonaGym, we release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories that closely mirror real-world preference expression and noise patterns. We further propose Personalized Prompt Optimization (PPOpt), a scalable and model-agnostic framework that optimizes user prompts based on interaction histories without modifying the deployed LLM. PPOpt adopts a reason-then-optimize paradigm that infers an explicit user profile and conditions prompt rewriting on the user profile to avoid reward hacking. Our training procedure for PPOpt integrates a cold-start supervised prior with outcome-driven multi-objective reinforcement learning. We present extensive experiments to demonstrate consistent improvements over state-of-the-art baselines in terms of task performance, personalization quality, and robustness to noisy as well as to sparse preference signals.

cs.LG↗

arXiv2026

Automated reproducibility assessments in the social and behavioral sciences using large language models

Reproducibility in the social and behavioral sciences is typically evaluated by independent researchers who reanalyze the original data to assess whether the published findings can be recovered. However, such approaches are resource-intensive and difficult to scale. Here, we show that large language models (LLMs) can automate reproducibility assessments. Using N = 180 published studies with predefined claims from the behavioral and social sciences, we compare LLM-generated analyses with the original findings. For 11 studies, the LLM pipeline could not produce a viable effect size estimate. For the remaining studies, the LLM reached the same qualitative conclusion as the original study in 80% of cases, and recovered the original effect sizes (using a +/-0.05 tolerance in Cohen's d) in 24% of studies. In a subset with human reanalyses, the LLM reached the same qualitative conclusion as the original study in 95% of studies, similar to human reanalysts (83%), and the LLM recovered the original effect sizes using a +/-0.05 tolerance in 40% of studies, again broadly similar to human reanalysts (28%). Given the current capabilities and limitations of LLMs, the findings show that LLMs can support systematic audits of empirical results rather than substitute expert judgment. As such, LLMs can serve as a scalable screening tool to improve the rigor and reproducibility in empirical research.

cs.AI↗

arXiv2026

OncoSynth: Synthetic data generation for treatment effect estimation in oncology

In oncology, access to patient-level data is often restricted. Synthetic data provides an alternative for analyzing treatment effectiveness, but existing methods for synthetic data generation fail to preserve the causal relationships between covariates, treatments, and outcomes, thereby leading to biased estimates of treatment effects. Here, we introduce OncoSynth, a generative, causally-aware machine learning framework designed to produce synthetic cohorts that enable accurate estimation of population- and patient-level treatment effects. OncoSynth uses a diffusion-based sequential approach to model how covariates influence treatment assignment and how treatment affects survival. We evaluate OncoSynth using large lung (N = 37,128) and breast cancer (N = 17,046) cohorts. Our results show that OncoSynth generates high-fidelity synthetic patient cohorts that preserve real-world patient, treatment, and outcome distributions. Notably, OncoSynth improves treatment effect estimation over existing approaches, by reducing population-level treatment effect error by up to 66%, and patient-level treatment effect error by up to 58%. Thereby, OncoSynth supports reliable evidence generation for precision oncology in settings where data sharing is restricted.

cs.LG↗

arXiv2026

ProbeLLM: Automating Principled Diagnosis of LLM Failures

Understanding how and why large language models (LLMs) fail is becoming a central challenge as models rapidly evolve and static evaluations fall behind. While automated probing has been enabled by dynamic test generation, existing approaches often discover isolated failure cases, lack principled control over exploration, and provide limited insight into the underlying structure of model weaknesses. We propose ProbeLLM, a benchmark-agnostic automated probing framework that elevates weakness discovery from individual failures to structured failure modes. ProbeLLM formulates probing as a hierarchical Monte Carlo Tree Search, explicitly allocating limited probing budgets between global exploration of new failure regions and local refinement of recurring error patterns. By restricting probing to verifiable test cases and leveraging tool-augmented generation and verification, ProbeLLM grounds failure discovery in reliable evidence. Discovered failures are further consolidated into interpretable failure modes via failure-aware embeddings and boundary-aware induction. Across diverse benchmarks and LLMs, ProbeLLM reveals substantially broader, cleaner, and more fine-grained failure landscapes than static benchmarks and prior automated methods, supporting a shift from case-centric evaluation toward principled weakness discovery.

cs.CL↗

arXiv2026

Gender-based discrepancies in the algorithmic delivery of political ads on social media

Social media has become a key channel for political advertising during election campaigns. However, algorithmic biases in the delivery of these ads may distort the public's exposure to political messaging. This can hinder citizens' ability to make informed choices and undermine equal access to political discourse, raising concerns about the integrity of electoral processes. In this study, we examine gender-based discrimination in the delivery of political ads during the 2024 European Parliament elections. Using a large-scale dataset of over 110000 ads from 453 political parties and 968 candidates that generated over 7 billion impressions across 25 EU countries, we find that men were significantly more likely to be shown ads from populist and far-right parties than women -- even after accounting for ad content, platform-level competition, and targeting strategies. All else equal, ads by populist parties reach, on average, a 6 percentage point higher male share. Such imbalances restrict the ability of parties to reach diverse audiences and prevent voters from engaging equally with the full range of political viewpoints. This pattern is particularly concerning given that far-right and populist ads may reinforce political polarization and widen existing gender gaps in political engagement. Our findings underscore the need for platforms and policymakers to audit algorithmic ad delivery in political campaigns on social media and to implement safeguards that ensure fairness and protect democratic processes.

cs.CY↗

arXiv2026

Nonparametric LLM Evaluation from Preference Data

Evaluating the performance of large language models (LLMs) from human preference data is crucial for obtaining LLM leaderboards. However, many existing approaches either rely on restrictive parametric assumptions or lack valid uncertainty quantification when flexible machine learning methods are used. In this paper, we propose a nonparametric statistical framework, called DMLRank, for comparing and ranking LLMs from preference data using debiased machine learning (DML). For this, we introduce generalized average ranking scores (GARS), which generalize commonly used ranking models, including the Bradley-Terry model or PageRank/ Rank centrality, with complex human responses such as ties. DMLRank comes with the following advantages: (i)~It produces statistically efficient estimates of GARS ranking scores. (ii) It naturally allows the incorporation of black-box machine learning methods for estimation. (iii) It can be combined with pre-trained LLM evaluators (e.g., using LLM-as-a-judge). (iv) It suggests optimal policies for collecting preference data under budget constraints. We demonstrate these advantages both theoretically and empirically using both synthetic and real-world preference datasets. In summary, our framework provides practitioners with powerful, state-of-the-art methods for comparing or ranking LLMs for leaderboards.

cs.LG↗

arXiv2026

Orthogonal Learner for Estimating Heterogeneous Long-Term Treatment Effects

Estimation of heterogeneous long-term treatment effects (HLTEs) is relevant for personalized decision-making in marketing, economics, and medicine, where short-term observational datasets are often combined with long-term observational datasets. However, HLTE estimation is challenging due to limited overlap in treatment assignments or in long-term outcomes for certain subpopulations, which can lead to unstable HLTE estimates with large finite-sample variance. To address this challenge, we introduce the LT-O-learners (Long-Term Orthogonal Learners), a set of novel orthogonal learners for HLTE estimation in the canonical HLTE setting with surrogacy. The key idea of our LT-O-learners is to retarget the loss via custom overlap weights that downweight low-overlap samples. We show that the retargeted loss recovers the true HLTE pointwise and satisfies Neyman-orthogonality. We further prove two key theoretical results: (i) The nuisance error enters the error bound only through higher-order terms, which means our learners are robust to nuisance estimation error. (ii) Under a linear function class, the retargeting effectively controls the asymptotic variance of the HLTE estimator via the overlap weights in low-overlap regimes. We conduct experiments on synthetic and real-world datasets to confirm the theoretical properties of our LT-O-learners, particularly robustness in low-overlap regimes. To our knowledge, ours are the first orthogonal learners for HLTE estimation robust to low overlap in long-term settings.

cs.LG↗

arXiv2026

Rank-Learner: Orthogonal Ranking of Treatment Effects

Many decision-making problems require ranking individuals by their treatment effects rather than estimating the exact effect magnitudes. Examples include prioritizing patients for preventive care interventions, or ranking customers by the expected incremental impact of an advertisement. Surprisingly, while causal effect estimation has received substantial attention in the literature, the problem of directly learning rankings of treatment effects has largely remained unexplored. In this paper, we introduce Rank-Learner, a novel two-stage learner that directly learns the ranking of treatment effects from observational data. We first show that naive approaches based on precise treatment effect estimation solve a harder problem than necessary for ranking, while our Rank-Learner optimizes a pairwise learning objective that recovers the true treatment effect ordering, without explicit CATE estimation. We further show that our Rank-Learner is Neyman-orthogonal and thus comes with strong theoretical guarantees, including robustness to estimation errors in the nuisance functions. In addition, our Rank-Learner is model-agnostic, and can be instantiated with arbitrary machine learning models (e.g., neural networks). We demonstrate the effectiveness of our method through extensive experiments where Rank-Learner consistently outperforms standard CATE estimators and non-orthogonal ranking methods. Overall, we provide practitioners with a new, orthogonal two-stage learner for ranking individuals by their treatment effects.

cs.LG↗

arXiv2026

Causal methods for LLM development and evaluation

Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and evaluation pipelines. Here, we argue that many central questions in LLM development and evaluation are inherently causal: What is the effect of adding a data domain during pretraining? How do annotator preferences change when LLMs generate text in a different style? Should a prompt be routed to a larger or smaller model given inference cost constraints? In general, causal methods are well-suited to such settings where interventions change outcomes but, surprisingly, are underrepresented in LLM development. Our contribution is threefold: (1) We explain how causal methods can help develop modern LLM development and evaluation: LLM development relies heavily on logged data, which are often subject to confounding and distribution shifts; evaluation uses learned but potentially biased judges; and deployment environments are non-stationary. These conditions make purely predictive approaches fragile and create opportunities for principled identification and estimation methods from causal inference. (2) We further map opportunities for causal methods in the entire LLM development pipeline, including pretraining, alignment, routing, agentic workflows, and evaluation. (3) We discuss new research opportunities around leveraging causal methods for LLM development and evaluation. Overall, we argue that causal methods are potentially underutilized for the LLM development and evaluation pipeline, despite the fact that such methods can ensure a reliable and scientifically grounded design.

cs.LG↗

arXiv2026

Adaptive Experimentation for Censored Survival Outcomes

Adaptive experimentation enables efficient estimation of causal effects, but existing methods are not designed for survival data with censoring, where event times are only partially observed (e.g., overall survival in cancer trials but with dropout). In this paper, we develop a novel framework for adaptive experimentation to estimate causal effects under right censoring. For this, we derive the semiparametric efficiency bound for the average survival effect curve as a function of the treatment allocation policy and thereby obtain a closed-form efficiency-optimal allocation policy. The policy generalizes classical Neyman allocation to survival settings by prioritizing patient strata where both event and censoring dynamics induce high uncertainty. Building on this, we propose the Adaptive Survival Estimator (ASE), an adaptive framework that learns the allocation policy and estimates the average survival effect curve sequentially. Our framework has three main benefits: (i) it accommodates arbitrary machine learning models for nuisance estimation; (ii) it is guided by a closed-form efficiency-optimal allocation policy; and (iii) it admits strong theoretical guarantees, including asymptotic normality via a martingale central limit theorem. We demonstrate our framework across various numerical experiments to show consistent efficiency gains over uniform randomization and censoring-agnostic baselines.

cs.LG↗