arXiv subjects

Zoë Hitzig

Publications and source records attributed to Zoë Hitzig.

5 recordsLinked to original sources

arXiv2026

The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes

Large language models are increasingly deployed in agentic pipelines that depend on the model evaluating its own outputs without external verification. The reliability of these pipelines depends on an implicit assumption: that the model applies relevant concepts the same way when it generates an output and later evaluates that output. We propose a new measure, generator-evaluator self-consistency, to test this assumption directly and apply it to 10 frontier models across 491 concepts. We find, first, that there is substantial variation in self-consistency. Second, we find that in a clinical setting with physician-validated mistakes (Proniakin et al., 2025), across models, those with higher self-consistency are linked to greater vulnerability to mistakes. Thus, even when models consistently apply concepts they may not be safe to deploy. This is evidence of a consistency dilemma in LLMs: self-consistency is operationally useful, but models that are more consistent are also more prone to mistakes.

cs.CY↗

arXiv2025

Contextually Private Mechanisms

We introduce a framework for comparing the privacy of different mechanisms. A mechanism designer employs a dynamic protocol to elicit agents' private information. Protocols produce a set of contextual privacy violations -- information learned about agents that may be superfluous given the context. A protocol is \emph{maximally contextually private} if there is no protocol that produces a proper subset of the violations it produces, while still implementing the choice rule. Contextual privacy violations arise when a choice rule makes some agents collectively, but not individually, pivotal. In auctions, designing for contextual privacy requires choosing an initial question posed to each agent and the order in which agents are queried. We study a particular maximally contextually private protocol for $k$-item Vickrey auctions -- the ascending-join protocol -- and show that it achieves maximal contextual privacy by delaying queries to bidders whose privacy it protects.

econ.TH↗

arXiv2025

Personhood credentials: Artificial intelligence and the value of privacy-preserving tools to distinguish who is real online

Anonymity is an important principle online. However, malicious actors have long used misleading identities to conduct fraud, spread disinformation, and carry out other deceptive schemes. With the advent of increasingly capable AI, bad actors can amplify the potential scale and effectiveness of their operations, intensifying the challenge of balancing anonymity and trustworthiness online. In this paper, we analyze the value of a new tool to address this challenge: "personhood credentials" (PHCs), digital credentials that empower users to demonstrate that they are real people -- not AIs -- to online services, without disclosing any personal information. Such credentials can be issued by a range of trusted institutions -- governments or otherwise. A PHC system, according to our definition, could be local or global, and does not need to be biometrics-based. Two trends in AI contribute to the urgency of the challenge: AI's increasing indistinguishability from people online (i.e., lifelike content and avatars, agentic activity), and AI's increasing scalability (i.e., cost-effectiveness, accessibility). Drawing on a long history of research into anonymous credentials and "proof-of-personhood" systems, personhood credentials give people a way to signal their trustworthiness on online platforms, and offer service providers new tools for reducing misuse by bad actors. In contrast, existing countermeasures to automated deception -- such as CAPTCHAs -- are inadequate against sophisticated AI, while stringent identity verification solutions are insufficiently private for many use-cases. After surveying the benefits of personhood credentials, we also examine deployment risks and design challenges. We conclude with actionable next steps for policymakers, technologists, and standards bodies to consider in consultation with the public.

cs.CY↗

arXiv2024

Contextual Confidence and Generative AI

Generative AI models perturb the foundations of effective human communication. They present new challenges to contextual confidence, disrupting participants' ability to identify the authentic context of communication and their ability to protect communication from reuse and recombination outside its intended context. In this paper, we describe strategies--tools, technologies and policies--that aim to stabilize communication in the face of these challenges. The strategies we discuss fall into two broad categories. Containment strategies aim to reassert context in environments where it is currently threatened--a reaction to the context-free expectations and norms established by the internet. Mobilization strategies, by contrast, view the rise of generative AI as an opportunity to proactively set new and higher expectations around privacy and authenticity in mediated communication.

cs.AI↗

arXiv2022

Optimal Defaults, Limited Enforcement and the Regulation of Contracts

We study how governments promote social welfare through the design of contracting environments. We model the regulation of contracting as default delegation: the government chooses a delegation set of contract terms it is willing to enforce, and influences the default terms that serve as outside options in parties' negotiations. Our analysis shows that limiting the delegation set principally mitigates externalities, while default terms primarily achieve distributional objectives. Applying our model to the regulation of labor contracts, we derive comparative statics on the optimal default delegation policy. As equity concerns or externalities increase, in-kind support for workers increases (e.g. through benefits requirements and public health insurance). Meanwhile, when worker bargaining power decreases away from parity, support for workers increases in cash (e.g. through cash transfers and minimum wage laws).

econ.TH↗