Publication details
Towards Hybrid Evaluation Methodologies for Large Language Models in the Legal Domain
| Authors | |
|---|---|
| Year of publication | 2024 |
| Type | Article in Proceedings |
| Conference | Frontiers in Artificial Intelligence and Applications, Vol. 395 Legal Knowledge and Information Systems. Proceedings of JURIX 2024. |
| MU Faculty or unit | |
| Citation | |
| web | Open access sborníku |
| Doi | https://doi.org/10.3233/FAIA241279 |
| Keywords | Large Language Models; Thematic Analysis; Performance Evaluation |
| Description | This paper analyses automated and human-driven evaluation approaches for Large Language Models (LLMs) performance in the legal domain, stressing the need to combine both into hybrid evaluation frameworks. This conclusion is reinforced by a qualitative case study that uncovers assessment factors considered by lawyers when using LLMs. The diverse nature of these factors, requiring distinct evaluation approaches, underscores the need for adopting a hybrid methodology. |