Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.14348 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910238084431872 |
|---|---|
| author | Stammbach, Dominik Zhang, Kylie Liu, Patty Nadeem, Nimra Cheong, Inyoung Zheng, Lucia Henderson, Peter |
| author_facet | Stammbach, Dominik Zhang, Kylie Liu, Patty Nadeem, Nimra Cheong, Inyoung Zheng, Lucia Henderson, Peter |
| contents | AI tools are suggested as solutions to assist public agencies with heavy workloads. In public defense -- where a constitutional right to counsel meets the complexities of law, overwhelming caseloads, and constrained resources -- practitioners face especially taxing conditions. Yet, there is little evidence of how AI could meaningfully support defenders' day-to-day work. In partnership with the New Jersey Office of the Public Defender, we develop the NJ BriefBank, a retrieval tool which surfaces relevant appellate briefs to streamline legal research and writing. We show that existing retrieval benchmarks fail to transfer to real public defense research, however adding domain knowledge improves retrieval quality. This includes query expansion with legal reasoning, domain-specific data and curated synthetic examples. To facilitate further research, we release a taxonomy of realistic defender search queries and a manually annotated evaluation dataset for public defense retrieval. This benchmark is highly correlated with a proprietary retrieval dataset annotated by experienced public defenders. Our work improves on the status quo of realistic legal retrieval benchmarking and illustrates one approach to applying AI in a real-world public interest setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14348 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Legal Retrieval for Public Defenders Stammbach, Dominik Zhang, Kylie Liu, Patty Nadeem, Nimra Cheong, Inyoung Zheng, Lucia Henderson, Peter Information Retrieval AI tools are suggested as solutions to assist public agencies with heavy workloads. In public defense -- where a constitutional right to counsel meets the complexities of law, overwhelming caseloads, and constrained resources -- practitioners face especially taxing conditions. Yet, there is little evidence of how AI could meaningfully support defenders' day-to-day work. In partnership with the New Jersey Office of the Public Defender, we develop the NJ BriefBank, a retrieval tool which surfaces relevant appellate briefs to streamline legal research and writing. We show that existing retrieval benchmarks fail to transfer to real public defense research, however adding domain knowledge improves retrieval quality. This includes query expansion with legal reasoning, domain-specific data and curated synthetic examples. To facilitate further research, we release a taxonomy of realistic defender search queries and a manually annotated evaluation dataset for public defense retrieval. This benchmark is highly correlated with a proprietary retrieval dataset annotated by experienced public defenders. Our work improves on the status quo of realistic legal retrieval benchmarking and illustrates one approach to applying AI in a real-world public interest setting. |
| title | Legal Retrieval for Public Defenders |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2601.14348 |