arXiv subjects

Leon Fröhling

Publications and source records attributed to Leon Fröhling.

10 recordsLinked to original sources

arXiv2026

When Persona Attributes Improve Population Alignment in Large Language Models

Large Language Models (LLMs) are increasingly used to predict the responses of human participants in survey panels. Towards that goal, persona prompting has recently emerged as a technique to inform and align large pretrained language models. Persona prompting refers to the practice of using short textual descriptions of 'personas' in prompts to steer the LLM's generations. Personas describe individuals through different attributes such as their socio-demographics, attitudes, or behaviors, with the aim of aligning LLMs to produce responses that correlate with the corresponding human responses. Yet, recent work has produced mixed and partly conflicting results of persona prompting without clear patterns of success and failure. Among the few consistent findings is that the selection of persona attributes matters, and that using more attributes does not necessarily lead to better performance. It remains unclear how different attribute selection methods perform and how to choose among them. In this paper, we propose that observed human response variation of a survey question is a potential explanation for the mixed performance observed so far. In addition, we compare the performance of persona prompting associated with different methods for selecting persona attributes. We evaluate these methods on four different (general) social surveys across two countries, six LLMs, and twenty prediction tasks per survey. Our work helps to identify when persona prompting can be expected to be useful in survey prediction tasks, and provides new insights on the effectiveness of different attribute selection methods for LLM-based survey prediction using persona prompting.

cs.CL↗

arXiv2026

Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgment

AI impact assessments often stress near-term risks because human judgment degrades over longer horizons, exemplifying the Collingridge dilemma: foresight is most needed when knowledge is scarcest. To address long-term systemic risks, we introduce a scalable approach that simulates in-silico agents using the strategic foresight method of the Futures Wheel. We applied it to four AI uses spanning Technology Readiness Levels (TRLs): Chatbot Companion (TRL 9, mature), AI Toy (TRL 7, medium), Griefbot (TRL 5, low), and Death App (TRL 2, conceptual). Across 30 agent runs per use, agents produced 86-110 consequences, condensed into 27-47 unique risks. To benchmark the agent outputs against human perspectives, we collected evaluations from 290 domain experts and 7 leaders, and conducted Futures Wheel sessions with 42 experts and 42 laypeople. Agents generated many systemic consequences across runs. Compared with these outputs, experts identified fewer risks, typically less systemic but judged more likely, whereas laypeople surfaced more emotionally salient concerns that were generally less systemic. We propose a hybrid foresight workflow, wherein agents broaden systemic coverage, and humans provide contextual grounding. Our dataset is available at: https://social-dynamics.net/ai-risks/foresight.

cs.HC↗

arXiv2025

German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies

The use of Large Language Models (LLMs) for simulating human perspectives via persona prompting is gaining traction in computational social science. However, well-curated, empirically grounded persona collections remain scarce, limiting the accuracy and representativeness of such simulations. Here, we introduce the German General Social Survey Personas (GGSS Personas) collection, a comprehensive and representative persona prompt collection built from the German General Social Survey (ALLBUS). The GGSS Personas and their persona prompts are designed to be easily plugged into prompts for all types of LLMs and tasks, steering models to generate responses aligned with the underlying German population. We evaluate GGSS Personas by prompting various LLMs to simulate survey response distributions across diverse topics, demonstrating that GGSS Personas-guided LLMs outperform state-of-the-art classifiers, particularly under data scarcity. Furthermore, we analyze how the representativity and attribute selection within persona prompts affect alignment with population responses. Our findings suggest that GGSS Personas provide a potentially valuable resource for research on LLM-based social simulations that enables more systematic explorations of population-aligned persona prompting in NLP and social science research.

cs.CL↗

arXiv2025

Political Ideology Shifts in Large Language Models

Large language models (LLMs) are increasingly deployed in politically sensitive contexts, raising concerns about their susceptibility to ideological biases. In this work, we examine how synthetic persona conditioning shapes ideological expression across seven open-weight instruction-tuned models (7B-72B parameters) using the Political Compass Test (62 statements) as a standardized behavioral probe. Across three studies involving 200,000 synthetic personas and more than 260 million model responses, we analyze implicit and explicit malleability, as well as theme-associated variations. We find that: (i) larger models exhibit broader implicit ideological coverage, increasing from 14-35% for 7-8B models to up to 49% for 70B+ models; (ii) explicit ideological priming induces large and statistically significant shifts, with right-authoritarian cues moving all models in the intended direction and producing larger effects in most model-axis comparisons; (iii) left-libertarian priming produces more heterogeneous responses, including counter-directional economic shifts in three of four 7-8B models, while all 70B+ models move in the intended direction; and (iv) theme-associated semantic content in persona descriptions is linked to systematic and interpretable directional shifts in ideological space. While our results identify an upstream mechanism through which persona conditioning can alter model responses under a standardized ideological probe, we do not test whether such shifts affect users beliefs, decisions, or political behavior. Our findings are best understood as evidence of ideological malleability at the generation layer, highlighting the need to account for interactional factors when evaluating political neutrality, fairness, and safety in English-prompted, persona-conditioned language models.

cs.CL↗

arXiv2024

SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs

As increasingly capable large language models (LLMs) emerge, researchers have begun exploring their potential for subjective tasks. While recent work demonstrates that LLMs can be aligned with diverse human perspectives, evaluating this alignment on downstream tasks (e.g., hate speech detection) remains challenging due to the use of inconsistent datasets across studies. To address this issue, in this resource paper we propose a two-step framework: we (1) introduce SubData, an open-source Python library designed for standardizing heterogeneous datasets to evaluate LLMs perspective alignment; and (2) present a theory-driven approach leveraging this library to test how differently-aligned LLMs (e.g., aligned with different political viewpoints) classify content targeting specific demographics. SubData's flexible mapping and taxonomy enable customization for diverse research needs, distinguishing it from existing resources. We illustrate its usage with an example application and invite contributions to extend our initial release into a multi-construct benchmark suite for evaluating LLMs perspective alignment on natural language processing tasks.

cs.CL↗

arXiv2024

Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas

The analysis of political biases in large language models (LLMs) has primarily examined these systems as single entities with fixed viewpoints. While various methods exist for measuring such biases, the impact of persona-based prompting on LLMs' political orientation remains unexplored. In this work we leverage PersonaHub, a collection of synthetic persona descriptions, to map the political distribution of persona-based prompted LLMs using the Political Compass Test (PCT). We then examine whether these initial compass distributions can be manipulated through explicit ideological prompting towards diametrically opposed political orientations: right-authoritarian and left-libertarian. Our experiments reveal that synthetic personas predominantly cluster in the left-libertarian quadrant, with models demonstrating varying degrees of responsiveness when prompted with explicit ideological descriptors. While all models demonstrate significant shifts towards right-authoritarian positions, they exhibit more limited shifts towards left-libertarian positions, suggesting an asymmetric response to ideological manipulation that may reflect inherent biases in model training.

cs.CL↗

arXiv2024

Personas with Attitudes: Controlling LLMs for Diverse Data Annotation

We present a novel approach for enhancing diversity and control in data annotation tasks by personalizing large language models (LLMs). We investigate the impact of injecting diverse persona descriptions into LLM prompts across two studies, exploring whether personas increase annotation diversity and whether the impacts of individual personas on the resulting annotations are consistent and controllable. Our results show that persona-prompted LLMs produce more diverse annotations than LLMs prompted without personas and that these effects are both controllable and repeatable, making our approach a suitable tool for improving data annotation in subjective NLP tasks like toxicity detection.

cs.CL↗

arXiv2024

The Unseen Targets of Hate -- A Systematic Review of Hateful Communication Datasets

Machine learning (ML)-based content moderation tools are essential to keep online spaces free from hateful communication. Yet, ML tools can only be as capable as the quality of the data they are trained on allows them. While there is increasing evidence that they underperform in detecting hateful communications directed towards specific identities and may discriminate against them, we know surprisingly little about the provenance of such bias. To fill this gap, we present a systematic review of the datasets for the automated detection of hateful communication introduced over the past decade, and unpack the quality of the datasets in terms of the identities that they embody: those of the targets of hateful communication that the data curators focused on, as well as those unintentionally included in the datasets. We find, overall, a skewed representation of selected target identities and mismatches between the targets that research conceptualizes and ultimately includes in datasets. Yet, by contextualizing these findings in the language and location of origin of the datasets, we highlight a positive trend towards the broadening and diversification of this research space.

cs.CL↗

arXiv2023

Total Error Sheets for Datasets (TES-D) -- A Critical Guide to Documenting Online Platform Datasets

This paper proposes a template for documenting datasets that have been collected from online platforms for research purposes. The template should help to critically reflect on data quality and increase transparency in research fields that make use of online platform data. The paper describes our motivation, outlines the procedure for developing a specific documentation template that we refer to as TES-D (Total Error Sheets for Datasets) and has the current version of the template, guiding questions and a manual attached as supplementary material. The TES-D approach builds upon prior work in designing error frameworks for data from online platforms, namely the Total Error Framework for digital traces of human behavior on online platforms (TED-On, https://doi.org/10.1093/poq/nfab018).

cs.CY↗

arXiv2023

You are a Bot! -- Studying the Development of Bot Accusations on Twitter

The characterization and detection of bots with their presumed ability to manipulate society on social media platforms have been subject to many research endeavors over the last decade. In the absence of ground truth data (i.e., accounts that are labeled as bots by experts or self-declare their automated nature), researchers interested in the characterization and detection of bots may want to tap into the wisdom of the crowd. But how many people need to accuse another user as a bot before we can assume that the account is most likely automated? And more importantly, are bot accusations on social media at all a valid signal for the detection of bots? Our research presents the first large-scale study of bot accusations on Twitter and shows how the term bot became an instrument of dehumanization in social media conversations since it is predominantly used to deny the humanness of conversation partners. Consequently, bot accusations on social media should not be naively used as a signal to train or test bot detection models.

cs.SI↗