arXiv subjects

Matt Ratto

Publications and source records attributed to Matt Ratto.

5 recordsLinked to original sources

arXiv2026

Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory

As AI systems are deployed across increasingly diverse social contexts, alignment can no longer be framed as the optimization of a single, unified set of values. Instead, systems must be able to recognize, represent, and respond to multiple legitimate perspectives. This has led to growing interest in pluralistic alignment, which seeks to move beyond one-size-fits-all models of appropriate behaviour. However, current approaches often lack a clear account of how values are socially organized, contested, and coordinated in practice. In this paper, we argue that social theory provides essential conceptual and design resources for addressing these challenges. Drawing on established traditions in sociology, we show how perspectives can be understood as structured by roles, shaped through interaction, and distributed across fields of power and expertise. We translate these insights into concrete implications for AI system design, including role-based representations, structured coordination among perspectives, and context-sensitive evaluation. For agentic systems, this requires aligning not only final outputs, but also the role activations, deliberative traces, aggregation rules, and feedback loops through which those outputs are produced. Our contribution is to reposition pluralistic alignment as a problem of socially grounded coordination rather than output diversification. We outline a design space for systems that engage multiple perspectives in structured and accountable ways, and we identify directions for future work to implement and empirically evaluate these approaches in real-world settings.

cs.AI↗

arXiv2026

Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive Variation

This study examines how persona prompting shapes language generated by two multimodal large language models in urban perception, a setting for examining subjective interpretations of shared visual evidence. We organize outputs into three functional levels: descriptive grounding (captions), intermediate semantic layer (perception tags), and interpretive framing (justifications). Using approximately 60,000 persona-conditioned annotations per model from Qwen3-VL-8B and Gemma-4-E4B-it, we find that captions converge strongly across persona profiles and show only small attribute-associated differences. Justifications vary substantially more: economic status produces the largest difference in both models, with political orientation and personality also prominent. Paired image-level comparisons confirm larger justification than caption differences for these three attributes. For perception tags, personas sharing the same attribute level produce more similar tag sets than personas with different attribute levels, with the largest separation observed for economic status. Exploratory topic analysis further reveals persona-specific evaluative emphasis. Across models, profile-pair similarity patterns are strongly correlated for all three output types, although agreement is lowest for justifications. Overall, persona prompting affects interpretive framing more strongly than descriptive grounding.

cs.CL↗

arXiv2025

A Fully Generative Motivational Interviewing Counsellor Chatbot for Moving Smokers Towards the Decision to Quit

The conversational capabilities of Large Language Models (LLMs) suggest that they may be able to perform as automated talk therapists. It is crucial to know if these systems would be effective and adhere to known standards. We present a counsellor chatbot that focuses on motivating tobacco smokers to quit smoking. It uses a state-of-the-art LLM and a widely applied therapeutic approach called Motivational Interviewing (MI), and was evolved in collaboration with clinician-scientists with expertise in MI. We also describe and validate an automated assessment of both the chatbot's adherence to MI and client responses. The chatbot was tested on 106 participants, and their confidence that they could succeed in quitting smoking was measured before the conversation and one week later. Participants' confidence increased by an average of 1.7 on a 0-10 scale. The automated assessment of the chatbot showed adherence to MI standards in 98% of utterances, higher than human counsellors. The chatbot scored well on a participant-reported metric of perceived empathy but lower than typical human counsellors. Furthermore, participants' language indicated a good level of motivation to change, a key goal in MI. These results suggest that the automation of talk therapy with a modern LLM has promise.

cs.CL↗

arXiv2011

Learning in a Landscape: Simulation-building as Reflexive Intervention

This article makes a dual contribution to scholarship in science and technology studies (STS) on simulation-building. It both documents a specific simulation-building project, and demonstrates a concrete contribution to interdisciplinary work of STS insights. The article analyses the struggles that arise in the course of determining what counts as theory, as model and even as a simulation. Such debates are especially decisive when working across disciplinary boundaries, and their resolution is an important part of the work involved in building simulations. In particular, we show how ontological arguments about the value of simulations tend to determine the direction of simulation-building. This dynamic makes it difficult to maintain an interest in the heterogeneity of simulations and a view of simulations as unfolding scientific objects. As an outcome of our analysis of the process and reflections about interdisciplinary work around simulations, we propose a chart, as a tool to facilitate discussions about simulations. This chart can be a means to create common ground among actors in a simulation-building project, and a support for discussions that address other features of simulations besides their ontological status. Rather than foregrounding the chart's classificatory potential, we stress its (past and potential) role in discussing and reflecting on simulation-building as interdisciplinary endeavor. This chart is a concrete instance of the kinds of contributions that STS can make to better, more reflexive practice of simulation-building.

physics.hist-ph↗

arXiv2001

Leveraging Software, Advocating Ideology: Free Software and Open Source

This paper uses the software program Linux and the discourse around it in order to examine how software programs can be used to articulate and defend social and economic positions. Although I do not use the term "expression" in a strict legal sense, I claim that in order to make policy decisions involving software, it is important to understand how the functionality of software is expressive. Another way to state this is that software programs like Linux are socially meaningful through functionality and talk about functionality. In section I, I review some recent legal scholarship about software and explain why understanding how embedded technical expression works is important given the increasingly large role of software in governance. In section II, I explore software construction as a combination of social and technical practices. In section III, I describe some examples of meaning-making around the software program Linux. In section IV I conclude with a short description of why such analyses are important.

cs.CY↗