arXiv subjects

Jairo Gudiño-Rosero

Publications and source records attributed to Jairo Gudiño-Rosero.

4 recordsLinked to original sources

arXiv2026

Reasoning Enhances Robustness to Prompt Injection in LLM-Based Consensus

Large Language Models (LLMs) are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, participants can introduce critical vulnerabilities in LLM-based systems. Here, we examine the vulnerability and robustness of off-the-shelf consensus-generating LLMs to prompt-injection attacks, which consist of introducing strategically designed texts to amplify particular viewpoints, erase certain opinions, or divert consensus toward unrelated or irrelevant topics. Using data collected from a 2023 experiment conducted in the UK and predefining a majority-rule, we construct attack-free and adversarial variants of prompts containing public policy questions and opinion texts, classify opinion and consensus valences with a fine-tuned BERT model, and estimate LLM--human majority agreement rates. Overall, we find that default LLMs exhibit widespread vulnerability, especially when: (i) disagreement and agreement are finely balanced, (ii) under rational, instruction-like rhetorical strategies, and (iii) for attacks that shift consensus toward positions aligned with GB-unionist conservative manifestos relative to pro-independence left manifestos. A robustness pipeline combining GPT-OSS-SafeGuard injection detection, structured opinion representations, and GSPO-based reinforcement learning substantially reduces directional failures, outperforming state-of-the-art alternatives. While more effective detectors may enable more sophisticated attacks, these findings advance our understanding of both the vulnerabilities and the potential defenses of consensus-generating LLMs in digital democracy applications.

cs.CY↗

arXiv2026

Large Language Models and Augmented Democracy

Artificial intelligence enables computational agents to represent political preferences and take part in collective decision-making. In this thesis, I investigate the opportunities and challenges of digital twins (DTs) based on Large Language Models (LLMs) as intermediaries in augmented democracy, focusing on individual preference representation, collective representation of political organizations, and the vulnerability of those representations to attackers. First, using data from an online experiment in Brazil, I examine whether personalized DTs can predict citizens' preferences for unseen policy proposals. Second, I extend the DT framework from individuals to political organizations. Using Swiss parliamentary data, I build topic-specific knowledge graphs from lawmakers' legislative records and connect them to LLM-based lawmaker agents, which are organized into party-level DTs representing collective positions. Agentic deliberation among these agents tests whether aggregated party representations capture a broader range of intra-party perspectives than official party communications. Finally, I study the vulnerability and robustness of LLM-mediated deliberation against prompt-injection attacks that amplify viewpoints, suppress opinions, or redirect consensus. Using data from a 2023 deliberative experiment in the United Kingdom, I analyze how attack effectiveness varies with the distribution of opinions and rhetorical strategies, and evaluate a pipeline combining injection detection, structured opinion representations, and reinforcement learning to improve resistance. These findings characterize the opportunities and challenges of LLM-based digital twins in augmented democracy, stressing accurate preference representation, faithful aggregation, and robustness to strategic interaction.

cs.CY↗

arXiv2026

Algorithmic Shortlisting in Participatory Budgeting

Participatory budgeting is a democratic innovation that allows citizens to propose and vote on public investment projects. To help organizers manage large volumes of submissions, we design and test privacy-preserving methods for algorithmic shortlisting. These algorithms predict which projects are likely to be funded using only project features and anonymous historical voting data. We demonstrate the limitations of a naive approach that uses a large language model to rank projects based on past success and propose a vote-based pipeline that enables state-of-the-art LLMs to perform on par with classical machine learning. Our findings indicate that user preferences in participatory budgeting are stable enough to allow algorithmic shortlisting to approximate an initial selection of projects effectively.

cs.CY↗

arXiv2024

Large Language Models (LLMs) as Agents for Augmented Democracy

We explore an augmented democracy system built on off-the-shelf LLMs fine-tuned to augment data on citizen's preferences elicited over policies extracted from the government programs of the two main candidates of Brazil's 2022 presidential election. We use a train-test cross-validation setup to estimate the accuracy with which the LLMs predict both: a subject's individual political choices and the aggregate preferences of the full sample of participants. At the individual level, we find that LLMs predict out of sample preferences more accurately than a "bundle rule", which would assume that citizens always vote for the proposals of the candidate aligned with their self-reported political orientation. At the population level, we show that a probabilistic sample augmented by an LLM provides a more accurate estimate of the aggregate preferences of a population than the non-augmented probabilistic sample alone. Together, these results indicates that policy preference data augmented using LLMs can capture nuances that transcend party lines and represents a promising avenue of research for data augmentation.

cs.CY↗