LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models.
Neel GuhaJulian NyarkoDaniel E. HoChristopher RéAdam ChiltonAditya KAlex Chohlas-WoodAustin PetersBrandon WaldonDaniel N. RockmoreDiego ZambranoDmitry TalismanEnam HoqueFaiz SuraniFrank FaganGalit SarfatyGregory M. DickinsonHaggai PoratJason HeglandJessica WuJoe NudellJoel NiklausJohn J. NayJonathan H. ChoiKevin TobiaMargaret HaganMegan MaMichael A. LivermoreNikon Rasumov-RaheNils HolzenbergerNoam KoltPeter HendersonSean RehaagSharad GoelShang GaoSpencer WilliamsSunny GandhiTom ZurVarun IyerZehua LiPublished in: NeurIPS (2023)
Keyphrases
- language model
- legal reasoning
- language modeling
- case based reasoning
- probabilistic model
- document retrieval
- defeasible reasoning
- n gram
- information retrieval
- retrieval model
- statistical language models
- artificial intelligence and law
- test collection
- inference rules
- language modelling
- context sensitive
- speech recognition
- query expansion
- ad hoc information retrieval
- smoothing methods
- language models for information retrieval
- query terms
- legal cases
- pseudo relevance feedback
- relevance model
- language model for information retrieval
- translation model
- vector space model
- text classification
- expert systems