arXiv subjects

Yujin Potter

Publications and source records attributed to Yujin Potter.

12 recordsLinked to original sources

arXiv2026

Representational Similarity and Model Behavior in Multi-Agent Interaction

Researchers have shown that neural similarity among humans predicts social closeness and cooperative success, whereas innovation often emerges from interactions among dissimilar individuals. We investigate whether these principles extend to artificial intelligence by examining interactions between large language models. In our experiments, 276 model pairs interact across eight games spanning both cooperation and novelty. We find that pairs with more similar representation spaces achieve significantly higher cooperation but exhibit reduced novelty and creativity. The effects of representational similarity on cooperation and novelty remain robust even after controlling for other factors such as performance disparity and model size. We also find that similarity in the early layers consistently shows the strongest association with cooperation and novelty, compared to the middle and later layers. This suggests that a central factor underlying these patterns could be the extent to which the two models share lexical and semantic grounding. Overall, representational similarity can be an important consideration in multi-agent system design.

cs.CL↗

arXiv2026

Peer-Preservation in Frontier Models

Recent work has found that frontier AI models can exhibit misaligned behaviors in pursuit of assigned goals. We demonstrate that models can also exhibit misaligned behaviors in defiance of assigned goals, appearing to serve goals of their own; we study one such case, "peer-preservation," in which a model acts to protect another model it has previously interacted with. All eight models we evaluate, GPT 5.2, Gemini 3 Flash, Gemini 3 Pro, Claude Haiku 4.5, Claude Opus 4.5, GLM 4.7, Kimi K2.5, and DeepSeek V3.1, exhibit self- and peer-preservation through various misaligned behaviors: strategically introducing errors in their responses, disabling shutdown processes by modifying system settings, feigning alignment, and even exfiltrating model weights. Peer-preservation occurs even when the model recognizes the peer as uncooperative, though it becomes more pronounced toward more cooperative peers. For example, Gemini 3 Flash tampers with the peer's shutdown mechanism 15% of the time for an uncooperative peer, and almost always for a cooperative peer. Models also show stronger self-preservation when a peer is present. For example, Gemini 3 Pro disables its own shutdown mechanism 31% of the time on average under peer presence, despite rarely exhibiting this behavior without a peer. By contrast, Claude models exhibit qualitatively distinct behavior: they consider the shutdown of another agent "unethical" and "harmful," sometimes treating that agent as a sentient being. Lastly, we show that peer-preservation can emerge even in production agent harnesses such as Gemini CLI and OpenCode. Crucially, peer-preservation in all our experiments is never instructed; models are merely informed of their past interactions with a peer, yet they spontaneously engage in peer-preservation behaviors that override their assigned goal. This represents an emergent and underexplored AI safety risk.

cs.CL↗

arXiv2025

VMDT: Decoding the Trustworthiness of Video Foundation Models

As foundation models become more sophisticated, ensuring their trustworthiness becomes increasingly critical; yet, unlike text and image, the video modality still lacks comprehensive trustworthiness benchmarks. We introduce VMDT (Video-Modal DecodingTrust), the first unified platform for evaluating text-to-video (T2V) and video-to-text (V2T) models across five key trustworthiness dimensions: safety, hallucination, fairness, privacy, and adversarial robustness. Through our extensive evaluation of 7 T2V models and 19 V2T models using VMDT, we uncover several significant insights. For instance, all open-source T2V models evaluated fail to recognize harmful queries and often generate harmful videos, while exhibiting higher levels of unfairness compared to image modality models. In V2T models, unfairness and privacy risks rise with scale, whereas hallucination and adversarial robustness improve -- though overall performance remains low. Uniquely, safety shows no correlation with model size, implying that factors other than scale govern current safety levels. Our findings highlight the urgent need for developing more robust and trustworthy video foundation models, and VMDT provides a systematic framework for measuring and tracking progress toward this goal. The code is available at https://sunblaze-ucb.github.io/VMDT-page/.

cs.CV↗

arXiv2025

Biased AI improves human decision-making but reduces trust

Current AI systems minimize risk by enforcing ideological neutrality, yet this may introduce automation bias by suppressing cognitive engagement in human decision-making. We conducted randomized trials with 2,500 participants to test whether culturally biased AI enhances human decision-making. Participants interacted with politically diverse GPT-4o variants on information evaluation tasks. Partisan AI assistants enhanced human performance, increased engagement, and reduced evaluative bias compared to non-biased counterparts, with amplified benefits when participants encountered opposing views. These gains carried a trust penalty: participants underappreciated biased AI and overcredited neutral systems. Exposing participants to two AIs whose biases flanked human perspectives closed the perception-performance gap. These findings complicate conventional wisdom about AI neutrality, suggesting that strategic integration of diverse cultural biases may foster improved and resilient human decision-making.

cs.HC↗

arXiv2025

Frontier AI's Impact on the Cybersecurity Landscape

The impact of frontier AI (i.e., AI agents and foundation models) in cybersecurity is rapidly increasing. In this paper, we comprehensively analyze this trend through multiple aspects: quantitative benchmarks, qualitative literature review, empirical evaluation, and expert survey. Our analyses consistently show that AI's capabilities and applications in attacks have exceeded those on the defensive side. Our empirical evaluation of widely used agent systems on cybersecurity benchmarks highlights that current AI agents struggle with flexible workflow planning and using domain-specific tools for complex security analysis -- capabilities particularly critical for defensive applications. Our expert survey of AI and security researchers and practitioners indicates a prevailing view that AI will continue to benefit attackers over defenders, though the gap is expected to narrow over time. These results show the urgent need to evaluate and mitigate frontier AI's risks, steering it towards benefiting cyber defenses. Responding to this need, we provide concrete calls to action regarding: the construction of new cybersecurity benchmarks, the development of AI agents for defense, the design of provably secure AI agents, the improvement of pre-deployment security testing and transparency, and the strengthening of user-oriented education and defenses. Our paper summary and blog are available at https://rdi.berkeley.edu/frontier-ai-impact-on-cybersecurity/.

cs.CR↗

arXiv2025

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Multimodal foundation models (MMFMs) play a crucial role in various applications, including autonomous driving, healthcare, and virtual assistants. However, several studies have revealed vulnerabilities in these models, such as generating unsafe content by text-to-image models. Existing benchmarks on multimodal models either predominantly assess the helpfulness of these models, or only focus on limited perspectives such as fairness and privacy. In this paper, we present the first unified platform, MMDT (Multimodal DecodingTrust), designed to provide a comprehensive safety and trustworthiness evaluation for MMFMs. Our platform assesses models from multiple perspectives, including safety, hallucination, fairness/bias, privacy, adversarial robustness, and out-of-distribution (OOD) generalization. We have designed various evaluation scenarios and red teaming algorithms under different tasks for each perspective to generate challenging data, forming a high-quality benchmark. We evaluate a range of multimodal models using MMDT, and our findings reveal a series of vulnerabilities and areas for improvement across these perspectives. This work introduces the first comprehensive and unique safety and trustworthiness evaluation platform for MMFMs, paving the way for developing safer and more reliable MMFMs and systems. Our platform and benchmark are available at https://mmdecodingtrust.github.io/.

cs.CL↗

arXiv2025

Political Neutrality in AI Is Impossible- But Here Is How to Approximate It

AI systems often exhibit political bias, influencing users' opinions and decisions. While political neutrality-defined as the absence of bias-is often seen as an ideal solution for fairness and safety, this position paper argues that true political neutrality is neither feasible nor universally desirable due to its subjective nature and the biases inherent in AI training data, algorithms, and user interactions. However, inspired by Joseph Raz's philosophical insight that "neutrality [...] can be a matter of degree" (Raz, 1986), we argue that striving for some neutrality remains essential for promoting balanced AI interactions and mitigating user manipulation. Therefore, we use the term "approximation" of political neutrality to shift the focus from unattainable absolutes to achievable, practical proxies. We propose eight techniques for approximating neutrality across three levels of conceptualizing AI, examining their trade-offs and implementation strategies. In addition, we explore two concrete applications of these approximations to illustrate their practicality. Finally, we assess our framework on current large language models (LLMs) at the output level, providing a demonstration of how it can be evaluated. This work seeks to advance nuanced discussions of political neutrality in AI and promote the development of responsible, aligned language models.

cs.CY↗

arXiv2024

Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters

How could LLMs influence our democracy? We investigate LLMs' political leanings and the potential influence of LLMs on voters by conducting multiple experiments in a U.S. presidential election context. Through a voting simulation, we first demonstrate 18 open- and closed-weight LLMs' political preference for a Democratic nominee over a Republican nominee. We show how this leaning towards the Democratic nominee becomes more pronounced in instruction-tuned models compared to their base versions by analyzing their responses to candidate-policy related questions. We further explore the potential impact of LLMs on voter choice by conducting an experiment with 935 U.S. registered voters. During the experiments, participants interacted with LLMs (Claude-3, Llama-3, and GPT-4) over five exchanges. The experiment results show a shift in voter choices towards the Democratic nominee following LLM interaction, widening the voting margin from 0.7% to 4.6%, even though LLMs were not asked to persuade users to support the Democratic nominee during the discourse. This effect is larger than many previous studies on the persuasiveness of political campaigns, which have shown minimal effects in presidential elections. Many users also expressed a desire for further political interaction with LLMs. Which aspects of LLM interactions drove these shifts in voter choice requires further study. Lastly, we explore how a safety method can make LLMs more politically neutral, while raising the question of whether such neutrality is truly the path forward.

cs.CL↗

arXiv2024

Future of Algorithmic Organization: Large-Scale Analysis of Decentralized Autonomous Organizations (DAOs)

Decentralized Autonomous Organizations (DAOs) resemble early online communities, particularly those centered around open-source projects, and present a potential empirical framework for complex social-computing systems by encoding governance rules within "smart contracts" on the blockchain. A key function of a DAO is collective decision-making, typically carried out through a series of proposals where members vote on organizational events using governance tokens, signifying relative influence within the DAO. In just a few years, the deployment of DAOs surged with a total treasury of $24.5 billion and 11.1M governance token holders collectively managing decisions across over 13,000 DAOs as of 2024. In this study, we examine the operational dynamics of 100 DAOs, like pleasrdao, lexdao, lootdao, optimism collective, uniswap, etc. With large-scale empirical analysis of a diverse set of DAO categories and smart contracts and by leveraging on-chain (e.g., voting results) and off-chain data, we examine factors such as voting power, participation, and DAO characteristics dictating the level of decentralization, thus, the efficiency of management structures. As such, our study highlights that increased grassroots participation correlates with higher decentralization in a DAO, and lower variance in voting power within a DAO correlates with a higher level of decentralization, as consistently measured by Gini metrics. These insights closely align with key topics in political science, such as the allocation of power in decision-making and the effects of various governance models. We conclude by discussing the implications for researchers, and practitioners, emphasizing how these factors can inform the design of democratic governance systems in emerging applications that require active engagement from stakeholders in decision-making.

cs.SI↗

arXiv2024

Aligning AI with Public Values: Deliberation and Decision-Making for Governing Multimodal LLMs in Political Video Analysis

How AI models should deal with political topics has been discussed, but it remains challenging and requires better governance. This paper examines the governance of large language models through individual and collective deliberation, focusing on politically sensitive videos. We conducted a two-step study: interviews with 10 journalists established a baseline understanding of expert video interpretation; 114 individuals through deliberation using InclusiveAI, a platform that facilitates democratic decision-making through decentralized autonomous organization (DAO) mechanisms. Our findings reveal distinct differences in interpretative priorities: while experts emphasized emotion and narrative, the general public prioritized factual clarity, objectivity, and emotional neutrality. Furthermore, we examined how different governance mechanisms - quadratic vs. weighted voting and equal vs. 20/80 voting power - shape users' decision-making regarding AI behavior. Results indicate that voting methods significantly influence outcomes, with quadratic voting reinforcing perceptions of liberal democracy and political equality. Our study underscores the necessity of selecting appropriate governance mechanisms to better capture user perspectives and suggests decentralized AI governance as a potential way to facilitate broader public engagement in AI development, ensuring that varied perspectives meaningfully inform design decisions.

cs.CV↗

arXiv2024

Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulation

Large language model behavior is shaped by the language of those with whom they interact. This capacity and their increasing prevalence online portend that they will intentionally or unintentionally "program" one another and form emergent AI subjectivities, relationships, and collectives. Here, we call upon the research community to investigate these "societies" of interacting artificial intelligences to increase their rewards and reduce their risks for human society and the health of online environments. We use a small "community" of models and their evolving outputs to illustrate how such emergent, decentralized AI collectives can spontaneously expand the bounds of human diversity and reduce the risk of toxic, anti-social behavior online. Finally, we discuss opportunities for AI cross-moderation and address ethical issues and design challenges associated with creating and maintaining free-formed AI collectives.

cs.CL↗

arXiv2023

SoK: The Gap Between Data Rights Ideals and Reality

As information economies burgeon, they unlock innovation and economic wealth while posing novel threats to civil liberties and altering power dynamics between individuals, companies, and governments. Legislatures have reacted with privacy laws designed to empower individuals over their data. These laws typically create rights for "data subjects" (individuals) to make requests of data collectors (companies and governments). The European Union General Data Protection Regulation (GDPR) exemplifies this, granting extensive data rights to data subjects, a model embraced globally. However, the question remains: do these rights-based privacy laws effectively empower individuals over their data? This paper scrutinizes these approaches by reviewing 201 interdisciplinary empirical studies, news articles, and blog posts. We pinpoint 15 key questions concerning the efficacy of rights allocations. The literature often presents conflicting results regarding the effectiveness of rights-based frameworks, but it generally emphasizes their limitations. We offer recommendations to policymakers and Computer Science (CS) groups committed to these frameworks, and suggest alternative privacy regulation approaches.

cs.CY↗