The paper releases the AusLaw Citation Benchmark and shows that instruction-tuned 7B-8B LLMs plus retrieval re-ranking outperform general and law-specific pretrained LLMs for legal citation prediction, reaching about 52% accuracy with a large gap remaining.
BLT: Can Large Language Models Handle Basic Legal Text?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating LLM-based Approaches to Legal Citation Prediction: Domain-specific Pre-training, Fine-tuning, or RAG? A Benchmark and an Australian Law Case Study
The paper releases the AusLaw Citation Benchmark and shows that instruction-tuned 7B-8B LLMs plus retrieval re-ranking outperform general and law-specific pretrained LLMs for legal citation prediction, reaching about 52% accuracy with a large gap remaining.