# AI Assistance for Human Review of Default Judgments

arXiv: https://arxiv.org/abs/2607.01256 · HTML: https://mlsanity.com/paper/2607.01256/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making](https://mlsanity.com/paper/2305.07722/) (2023)
- [Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies](https://mlsanity.com/paper/2502.08554/) (2025)
- [Citation-Enhanced Generation for LLM-based Chatbots](https://mlsanity.com/paper/2402.16063/) (2024)
- [The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations](https://mlsanity.com/paper/2411.17375/) (2024)
- [Tasks and Roles in Legal AI: Data Curation, Annotation, and Verification](https://mlsanity.com/paper/2504.01349/) (2025)
- [LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance](https://mlsanity.com/paper/2501.00106/) (2024)

## Abstract (arXiv)

Overwhelmed courts in the United States review millions of default judgments each year. Unfortunately, such manual reviews are time-consuming and prone to error. In an audit of 188 debt collection cases granted default judgment by the Superior Court of Los Angeles, we find that 4% contained major defects that should have entirely prevented default judgment, 10% contained inconsistencies requiring reduced judgments, and 32% contained errors requiring amendment prior to judgment. To support courthouses in default judgment review, we collaborated with courthouse attorneys and judges in designing a Default Assistant. The Default Assistant employs large language models to evaluate a case with respect to predetermined legal requirements and provide cited recommendations for an expert user's review. We equip users to verify these recommendations by grounding the assistant's explanations in cited quotes and tables from the original case filings. We conduct a controlled study with 66 law students that conservatively simulates court review, with more time and resources than court staff. We nevertheless find users aided by the Default Assistant were 6.0% more accurate on the average requirement than unaided reviewers (p < 1.0e-4). Simultaneously, users were 25.9% faster in reviewing the average requirement than unaided reviewers (p < 2.5e-10). Statutory requirements demanding extensive document search realized the largest gains, with error reductions and time savings from AI assistance up to 62% and 34%, respectively, relative to unassisted user performance and with differences statistically significant (p < 0.05). Our work provides a proof-of-concept that AI assistants with citations have the potential to help resource-constrained courts conduct default judgment review more accurately and efficiently.