# Street-Level AI: Are Large Language Models Ready for Real-World Judgments?

arXiv: https://arxiv.org/abs/2508.08193 · HTML: https://mlsanity.com/paper/2508.08193/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 83 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Large language models in healthcare and medical domain: A review](https://mlsanity.com/paper/2401.06775/) (2023)
- [Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support](https://mlsanity.com/paper/2204.02310/) (2022)
- [Understanding Frontline Workers' and Unhoused Individuals' Perspectives on AI Used in Homeless Services](https://mlsanity.com/paper/2303.09743/) (2023)
- [Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values](https://mlsanity.com/paper/2502.00313/) (2025)
- [Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment](https://mlsanity.com/paper/2504.10886/) (2025)
- [Discretionary Trees: Understanding Street-Level Bureaucracy via Machine Learning](https://mlsanity.com/paper/2312.10694/) (2023)
- [Evaluating Large Language Models for Fair and Reliable Organ Allocation](https://mlsanity.com/paper/2504.03716/) (2025)

## Built on by (most cited first, 3 of 3)

- [MolMark: Safeguarding Molecular Structures through Learnable Atom-Level Watermarking](https://mlsanity.com/paper/2508.17702/) (2025)
- [LLMs Should Incorporate Explicit Mechanisms for Human Empathy](https://mlsanity.com/paper/2604.10557/) (2026)
- [Can LLMs Rank? A Tale of Triads and Triage](https://mlsanity.com/paper/2606.30412/) (2026)

## Abstract (arXiv)

A surge of recent work explores the ethical and societal implications of large-scale AI models that make "moral" judgments. Much of this literature focuses either on alignment with human judgments through various thought experiments or on the group fairness implications of AI judgments. However, the most immediate and likely use of AI is to help or fully replace the so-called street-level bureaucrats, the individuals deciding to allocate scarce social resources or approve benefits. There is a rich history underlying how principles of local justice determine how society decides on prioritization mechanisms in such domains. In this paper, we examine how well LLM judgments align with human judgments, as well as with socially and politically determined vulnerability scoring systems currently used in the domain of homelessness resource allocation. Crucially, we use real data on those needing services (maintaining strict confidentiality by only using local large models) to perform our analyses. We find that LLM prioritizations are extremely inconsistent in several ways: internally on different runs, between different LLMs, and between LLMs and the vulnerability scoring systems. At the same time, LLMs demonstrate qualitative consistency with lay human judgments in pairwise testing. Findings call into question the readiness of current generation AI systems for naive integration in high-stakes societal decision-making.