BLT: Can Large Language Models Handle Basic Legal Text?
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917806668251136 |
|---|---|
| author | Blair-Stanek, Andrew Holzenberger, Nils Van Durme, Benjamin |
| author_facet | Blair-Stanek, Andrew Holzenberger, Nils Van Durme, Benjamin |
| contents | We find that the best publicly available LLMs like GPT-4 and Claude currently perform poorly on basic legal text handling. This motivates the creation of a benchmark consisting of examples that lawyers and paralegals would expect LLMs to handle zero-shot, such as looking up the text at a line of a witness deposition or at a subsection of a contract. LLMs' poor performance on this benchmark casts into doubt their reliability as-is for legal practice. However, fine-tuning on our training set brings even a small model to near-perfect performance. This benchmark will be useful for fine-tuning LLMs for downstream legal tasks, as well as for tracking LLMs' reliability as-is for basic legal tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_09693 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | BLT: Can Large Language Models Handle Basic Legal Text? Blair-Stanek, Andrew Holzenberger, Nils Van Durme, Benjamin Computation and Language Artificial Intelligence I.2.1; I.2.7; J.7 We find that the best publicly available LLMs like GPT-4 and Claude currently perform poorly on basic legal text handling. This motivates the creation of a benchmark consisting of examples that lawyers and paralegals would expect LLMs to handle zero-shot, such as looking up the text at a line of a witness deposition or at a subsection of a contract. LLMs' poor performance on this benchmark casts into doubt their reliability as-is for legal practice. However, fine-tuning on our training set brings even a small model to near-perfect performance. This benchmark will be useful for fine-tuning LLMs for downstream legal tasks, as well as for tracking LLMs' reliability as-is for basic legal tasks. |
| title | BLT: Can Large Language Models Handle Basic Legal Text? |
| topic | Computation and Language Artificial Intelligence I.2.1; I.2.7; J.7 |
| url | https://arxiv.org/abs/2311.09693 |