arXiv subjects

Dirk Helbing

Publications and source records attributed to Dirk Helbing.

At least 19 recordsLinked to original sources

arXiv2026

From Opinions to Commitments: Unstable Assignments and Silent Choices in AI-Mediated Proposals

Large language models (LLMs) are increasingly being used to turn citizens' opinions into collective proposals. These proposals can make assignments: who should act, what must be done, how much one should spend and by when. However, if the assignments change when the same opinions are processed again, publishing a single proposal can hide alternatives that participants never get to see. We examined this issue in four LLM mediators (three open-weight and one commercial) using opinions from DeliberationBank and Polis. For each task, a mediator drafted a proposal from thirty opinions five times, varying either the random seed or the order of the opinions. In 17% of five-run sets from the open-weight mediators and 20% from the commercial one, some runs contained assignments while others did not. Reordering the opinions changed the assignments almost as often as replacing them with opinions from different citizens. Three human annotators confirmed that the detected differences between runs were real, although the LLM judge overstated how often they occurred. Substantial variation remained under four safeguards: temperature zero, a commercial mediator, draft selection, and draft merging. The mediator's objective also shaped representation: prompts seeking agreement covered minority positions much less often than prompts asking to describe differences. A single proposal can therefore obscure choices in both the assignments it proposes and the views it excludes. We propose audits that make alternative assignments visible and disclose the objective behind each proposal.

cs.AI↗

arXiv2026

Agentic Graph Retrieval-Augmented Generation for Auditable Commercial Registry Analysis

Public commercial registries are formally open, yet their practical analysis remains difficult because relevant facts are scattered across millions of records that combine structured metadata, multilingual legal notices, temporal events, and entity aliases. This paper presents a controlled, tool-mediated agentic GraphRAG architecture for auditable natural-language analysis of such registries. The proposed pipeline transforms publications from the Swiss Official Gazette of Commerce into a Neo4j knowledge graph comprising over five million nodes and 4.7 million relationships. It combines deterministic ingestion of structured registry fields, LLM-assisted extraction of latent actors from unstructured notices, and a deterministic identity-resolution layer. An analytical agent operates on this graph through intent routing, restricted graph tools, bounded reflection, and state-machine-guided response synthesis. We evaluate the system using a multi-tier protocol covering answer quality, retrieval behavior, entity resolution, and multi-turn conversational performance. The complete architecture is compared with dense, lexical, and hybrid flat-retrieval baselines and with controlled architectural ablations. On a manually curated benchmark, graph-mediated retrieval increases factual correctness from 0.26 for the strongest flat-retrieval baseline to 0.83 for the complete system, with comparable improvements in relevance and completeness. Ablation results show that bounded reflection improves answer quality while intent routing and LLM-based graph enrichment improve reliability in difficult entity resolution tasks. An exploratory dashboard displays the graph evidence and execution traces underlying each response, allowing users to inspect how answers were produced.

cs.IR↗

arXiv2026

Beyond the Townhall: Spatial Anchoring and LLM Agents for Scalable Participatory Urban Planning

LLMs are increasingly explored for public participation, but less is known about how they should be designed around the information citizens encounter beforehand. In an experiment (N=200) on participatory urban planning, participants learned about a sustainability project adapted from a real street redesign, through text and images or narrated 360-degree video with spatial audio and spatial anchoring; they subsequently engaged with factual and reflective LLM personas. The immersive condition improved recall and changed what participants said to the agents: they named beneficiaries more often, asked directionally more project-related questions, and provided more positive feedback. We contribute (1) a conceptualization of LLMs as dialogue partners complementing a shared information baseline, (2) causal evidence that this baseline shapes those conversations, (3) an account of how citizens use and judge factual versus reflective agent roles, and (4) a method for cities to test information packages and agent configurations before public release.

cs.HC↗

arXiv2026

OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models

We present OGD4All, a transparent, auditable, and reproducible framework based on Large Language Models (LLMs) to enhance citizens' interaction with geospatial Open Government Data (OGD). The system combines semantic data retrieval, agentic reasoning for iterative code generation, and secure sandboxed execution that produces verifiable multimodal outputs. Evaluated on a 199-question benchmark covering both factual and unanswerable questions, across 430 City-of-Zurich datasets and 11 LLMs, OGD4All reaches 98% analytical correctness and 94% recall while reliably rejecting questions unsupported by available data, which minimizes hallucination risks. Statistical robustness tests, as well as expert feedback, show reliability and social relevance. The proposed approach shows how LLMs can provide explainable, multimodal access to public data, advancing trustworthy AI for open governance.

cs.LG↗

arXiv2026

Democracy in the Era of Artificial Intelligence

Interfacing Artificial Intelligence (AI) with democracy is one of the most profound challenges of our times. On the one hand, AI comes with opportunities to overcome long-standing challenges in democracy, such as low participation in deliberative and voting processes with poor representation of people. On the other hand, new risks arise from AI algorithms that are privacy-intrusive, biased, manipulative, spread misinformation and influence election results. Moving beyond the over-simplistic question of whether AI is good or bad for democracy, the Handbook on Democracy in the Era of Artificial Intelligence asks instead: how to upgrade democracies and the principles they are built on, using AI? How to engage with AI and on what terms? Which new values and design principles are required to build democratic resilience? In 34 chapters by 59 authors across the world from different disciplines, we explore how AI can empower collective intelligence for democracy (Part 1) and what is the future of deliberative democracy using large language models and social media (Part 2). We also illustrate the role of AI for building resilient self-governance systems (Part 3) and the challenges of transforming democracy in the age of AI (Part 4). We conclude with broader perspectives (Part 5) that re-imagine the interplay of democracy and AI.

cs.CY↗

arXiv2026

Large cities lose their growth advantage as countries urbanize

The share of the world population living in cities with more than one million people rose from 11% in 1975 to 24% in 2025 (our estimates). Will this trend towards greater concentration in large cities continue or level off? We introduce two new city population datasets that use consistent city definitions across countries and over time. The first covers the world between 1975 and 2025, using satellite imagery. The second covers the U.S. between 1850 and 2020, using census microdata. We find that urban growth follows a characteristic life cycle. In the early stages of a country's urbanization process, large cities grow faster than smaller ones. At later stages, growth rates equalize across sizes. We use this life cycle to project future population concentration in large cities. Our projections suggest that 38% of the world population will be living in cities with more than one million people by 2100. This estimate is higher than the 33% implied by the well-known theory of proportional growth, but lower than the 42% obtained by extrapolating current trends.

physics.soc-ph↗

arXiv2025

Upgrading Democracies with Fairer Voting Methods

Voting methods are instrumental design elements of democracies. Citizens use them to express and aggregate their preferences to reach a collective decision. However, voting outcomes can be as sensitive to voting rules as they are to people's voting choices. Despite significance and interdisciplinary scientific progress, several democracies keep relying on outdated voting methods that do not fit modern, pluralistic societies well, while lacking social innovation. Here, we demonstrate how one can upgrade real-world democracies, namely by using alternative preferential voting methods such as cumulative voting and the method of equal shares designed for a proportional representation of voters' preferences. We rigorously evaluate the striking voting outcomes of these fair voting methods in a new participatory budgeting approach applied in the city of Aarau, Switzerland, including past and follow-up evidence. Results show more winning projects with the same budget. They also show broader geographic and preference representation of citizens by the elected projects, in particular for voters who used to be under-represented. We provide causal evidence showing that citizens prefer proportional voting methods, which possess strong legitimacy without the need of very specialized technical explanations. We also reveal strong underlying democratic values exhibited by citizens who support fair voting methods such as altruism and compromise. These findings come with the momentum to unleash a new and long-awaited participation blueprint of how to upgrade democracies globally.

cs.CY↗

arXiv2025

A Replica for our Democracies? On Using Digital Twins to Enhance Deliberative Democracy

Deliberative democracy depends on carefully designed institutional frameworks, such as participant selection, facilitation methods, and decision-making mechanisms, that shape how deliberation performs. However, identifying optimal institutional designs for specific contexts remains challenging when relying solely on real-world observations or laboratory experiments: they can be expensive, ethically and methodologically tricky, or too limited in scale to give us clear answers. Computational experiments offer a complementary approach, enabling researchers to conduct large-scale investigations while systematically analyzing complex dynamics, emergent and unexpected collective behavior, and risks or opportunities associated with novel democratic designs. Therefore, this paper explores Digital Twin (DT) technology as a computational testing ground for deliberative systems (with potential applicability to broader institutional analysis). By constructing dynamic models that simulate real-world deliberation, DTs allow researchers and policymakers to rigorously test "what-if" scenarios across diverse institutional configurations in a controlled virtual environment. This approach facilitates evidence-based assessment of novel designs using synthetically generated data, bypassing the constraints of real-world or lab-based experimentation, and without societal disruption. The paper also discusses the limitations of this new methodological approach and suggests where future research should focus.

cs.MA↗

arXiv2025

Breaking the Code: Multi-level Learning in the Eurovision Song Contest

Organizations learn from the market, political, and societal responses to their actions. While in some cases both the actions and responses take place in an open manner, in many others, some aspects may be hidden from external observers. The Eurovision Song Contest offers an interesting example to study organizational level learning at two levels: organizers and participants. We find evidence for changes in the rules of the Contest in response to undesired outcomes such as runaway winners. We also find strong evidence of participant learning in the characteristics of competing songs over the 70-years of the Contest. English has been adopted as the lingua franca of the competing songs and pop has become the standard genre. Number of words of lyrics has also grown in response to this collective learning. Remarkably, we find evidence that four participating countries have chosen to ignore the "lesson" that English lyrics increase winning probability. This choice is consistent with utility functions that award greater value to featuring national language than to winning the Contest. Indeed, we find evidence that some countries -- but not Germany -- appear to be less susceptible to "peer" pressure. These observations appear to be valid beyond Eurovision.

physics.soc-ph↗

arXiv2024

LLM Voting: Human Choices and AI Collective Decision Making

This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a human voting experiment to establish a baseline for human preferences and conducting a corresponding experiment with LLM agents. We observed that the choice of voting methods and the presentation order influenced LLM voting outcomes. We found that varying the persona can reduce some of these biases and enhance alignment with human choices. While the Chain-of-Thought approach did not improve prediction accuracy, it has potential for AI explainability in the voting process. We also identified a trade-off between preference diversity and alignment accuracy in LLMs, influenced by different temperature settings. Our findings indicate that LLMs may lead to less diverse collective outcomes and biased assumptions when used in voting scenarios, emphasizing the need for cautious integration of LLMs into democratic processes.

cs.CL↗

arXiv2024

VoteLab: A Modular and Adaptive Experimentation Platform for Online Collective Decision Making

Digital democracy and new forms for direct digital participation in policy making gain unprecedented momentum. This is particularly the case for preferential voting methods and decision-support systems designed to promote fairer, more inclusive and legitimate collective decision-making processes in citizens assemblies, participatory budgeting and elections. However, a systematic human experimentation with different voting methods is cumbersome and costly. This paper introduces VoteLab, an open-source and thoroughly-documented platform for modular and adaptive design of voting experiments. It supports to visually and interactively build reusable campaigns with a choice of different voting methods, while voters can easily respond to subscribed voting questions on a smartphone. A proof-of-concept with four voting methods and questions on COVID-19 in an online lab experiment have been used to study the consistency of voting outcomes. It demonstrates the capability of VoteLab to support rigorous experimentation of complex voting scenarios.

cs.CY↗

arXiv2024

Designing Digital Voting Systems for Citizens: Achieving Fairness and Legitimacy in Participatory Budgeting

Participatory Budgeting (PB) has evolved into a key democratic instrument for resource allocation in cities. Enabled by digital platforms, cities now have the opportunity to let citizens directly propose and vote on urban projects, using different voting input and aggregation rules. However, the choices cities make in terms of the rules of their PB have often not been informed by academic studies on voter behaviour and preferences. Therefore, this work presents the results of behavioural experiments where participants were asked to vote in a fictional PB setting. We identified approaches to designing PB voting that minimise cognitive load and enhance the perceived fairness and legitimacy of the digital process from the citizens' perspective. In our study, participants preferred voting input formats that are more expressive (like rankings and distributing points) over simpler formats (like approval voting). Participants also indicated a desire for the budget to be fairly distributed across city districts and project categories. Participants found the Method of Equal Shares voting rule to be fairer than the conventional Greedy voting rule. These findings offer actionable insights for digital governance, contributing to the development of fairer and more transparent digital systems and collective decision-making processes for citizens.

cs.HC↗

arXiv2024

How networks shape diversity for better or worse

Socio-diversity, the variety of human opinions, ideas, behaviors and styles, has profound implications for social systems. While it fuels innovation, productivity, and collective intelligence, it can also complicate communication and erode trust. So what mechanisms can influence it? This paper studies how fundamental characteristics of social networks can support or hinder socio-diversity. It employs models of cultural evolution, mathematical analysis, and numerical simulations. We find that pronounced inequalities in the distribution of connections obstruct socio-diversity. In contrast, the prevalence of close-knit communities, a scarcity of long-range connections, and a significant tie density tend to promote it. These results open new perspectives for understanding how to change social networks to sustain more socio-diversity and, thereby, societal innovation, collective intelligence, and productivity.

physics.soc-ph↗

arXiv2022

Digital Twins: Potentials, Ethical Issues, and Limitations

After Big Data and Artificial Intelligence (AI), the subject of Digital Twins has emerged as another promising technology, advocated, built, and sold by various IT companies. The approach aims to produce highly realistic models of real systems. In the case of dynamically changing systems, such digital twins would have a life, i.e. they would change their behaviour over time and, in perspective, take decisions like their real counterparts \textemdash so the vision. In contrast to animated avatars, however, which only imitate the behaviour of real systems, like deep fakes, digital twins aim to be accurate "digital copies", i.e. "duplicates" of reality, which may interact with reality and with their physical counterparts. This chapter explores, what are possible applications and implications, limitations, and threats.

physics.soc-ph↗

arXiv2022

Experiments as Code: A Concept for Reproducible, Auditable, Debuggable, Reusable, & Scalable Experiments

A common concern in experimental research is the auditability and reproducibility of experiments. Experiments are usually designed, provisioned, managed, and analyzed by diverse teams of specialists (e.g., researchers, technicians and engineers) and may require many resources (e.g. cloud infrastructure, specialized equipment). Even though researchers strive to document experiments accurately, this process is often lacking, making it hard to reproduce them. Moreover, when it is necessary to create a similar experiment, very often we end up "reinventing the wheel" as it is easier to start from scratch than trying to reuse existing work, thus losing valuable embedded best practices and previous experiences. In behavioral studies this has contributed to the reproducibility crisis. To tackle this challenge, we propose the "Experiments as Code" paradigm, where the whole experiment is not only documented but additionally the automation code to provision, deploy, manage, and analyze it is provided. To this end we define the Experiments as Code concept, provide a taxonomy for the components of a practical implementation, and provide a proof of concept with a simple desktop VR experiment that showcases the benefits of its "as code" representation, i.e., reproducibility, auditability, debuggability, reusability, and scalability.

cs.CY↗

arXiv2022

Nanowars can cause epidemic resurgence and fail to promote cooperation

In a non-sustainable, "over-populated" world, what might the use of nanotechnology-based targeted, autonomous weapons mean for the future of humanity? In order to gain some insights, we make a simplified game-theoretical thought experiment. We consider a population where agents play the public goods game, and where in parallel an epidemic unfolds. Agents that are infected defectors are killed with a certain probability and replaced by susceptible cooperators. We show that such "nanowars", even if aiming to promote good behavior and planetary health, fail not only to promote cooperation, but they also significantly increase the probability of repetitive epidemic waves. In fact, newborn cooperators turn out to be easy targets for defectors in their neighborhood. Therefore, counterintuitively, the discussed intervention may even have the opposite effect as desired, promoting defection. We also find a critical threshold for the death rate of infected defectors, beyond which resurgent epidemic waves become a certainty. In conclusion, we urgently call for international regulation of nanotechnology and autonomous weapons.

physics.soc-ph↗

arXiv2021

Finance 4.0: Design principles for a value-sensitive cryptoecnomic system to address sustainability

Cryptoeconomic systems derive their power but can not be controlled by the underlying software systems and the rules they enshrine. This adds a level of complexity to the software design process. At the same time, such systems, when designed with human values in mind, offer new approaches to tackle sustainability challenges, that are plagued by commons dilemmas and negative external effects caused by a one-dimensional monetary system. This paper proposes a design science research methodology with value-sensitive design methods to derive design principles for a value-sensitive socio-ecological cryptoeconomic system that incentivizes actions toward sustainability via multi-dimensional token incentives. These design principles are implemented in a software that is validated in user studies that demonstrate its relevance, usability and impact. Our findings provide new insights on designing cryptoeconomic systems. Moreover, the identified design principles for a value-sensitive socio-ecological financial system indicate opportunities for new research directions and business innovations.

cs.CY↗

arXiv2021

Some Challenges in Monitoring Epidemics

Epidemic models often reflect characteristic features of infectious spreading processes by coupled non-linear differential equations considering different states of health (such as Susceptible, Infected, or Recovered). This compartmental modeling approach, however, delivers an incomplete picture of the dynamics of epidemics, as it neglects stochastic and network effects, and also the role of the measurement process, on which the estimation of epidemiological parameters and incidence values relies. In order to study the related issues, we extend established epidemiological spreading models with a model of the measurement (i.e. testing) process, considering the problems of false positives and false negatives as well as biased sampling. Studying a model-generated ground truth in conjunction with simulated observation processes (virtual measurements) allows one to gain insights into the limitations of purely data-driven methods to assess the epidemic situation. We conclude that epidemic monitoring, simulation, and forecasting are wicked problems, as applying a conventional data-driven approach to a complex system with non-linear dynamics, network effects, and uncertainty can be misleading. Nevertheless, some of the errors can be corrected for, using scientific knowledge of the spreading dynamics and the measurement process. We conclude that such corrections should generally be part of epidemic monitoring, modeling, and forecasting efforts.

physics.soc-ph↗