Software Engineering Methods For AI-Driven Deductive Legal Reasoning

সংরক্ষণ করুন:
গ্রন্থ-পঞ্জীর বিবরন
প্রকাশিত:arXiv.org (Jun 27, 2024), p. n/a
প্রধান লেখক: Padhye, Rohan
প্রকাশিত:
Cornell University Library, arXiv.org
বিষয়গুলি:
অনলাইন ব্যবহার করুন:Citation/Abstract
Full text outside of ProQuest
ট্যাগগুলো: ট্যাগ যুক্ত করুন
কোনো ট্যাগ নেই, প্রথমজন হিসাবে ট্যাগ করুন!

MARC

LEADER 00000nab a2200000uu 4500
001 3039629860
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3039629860 
045 0 |b d20240627 
100 1 |a Padhye, Rohan 
245 1 |a Software Engineering Methods For AI-Driven Deductive Legal Reasoning 
260 |b Cornell University Library, arXiv.org  |c Jun 27, 2024 
513 |a Working Paper 
520 3 |a The recent proliferation of generative artificial intelligence (AI) technologies such as pre-trained large language models (LLMs) has opened up new frontiers in computational law. An exciting area of development is the use of AI to automate the deductive rule-based reasoning inherent in statutory and contract law. This paper argues that such automated deductive legal reasoning can now be viewed from the lens of software engineering, treating LLMs as interpreters of natural-language programs with natural-language inputs. We show how it is possible to apply principled software engineering techniques to enhance AI-driven legal reasoning of complex statutes and to unlock new applications in automated meta-reasoning such as mutation-guided example generation and metamorphic property-based testing. 
653 |a Mathematical logic 
653 |a Large language models 
653 |a Artificial intelligence 
653 |a Documents 
653 |a Reasoning 
653 |a Generative artificial intelligence 
653 |a Contract law 
653 |a Program verification (computers) 
653 |a Software engineering 
653 |a Automation 
653 |a Natural language processing 
653 |a Natural language 
653 |a Software testing 
773 0 |t arXiv.org  |g (Jun 27, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3039629860/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2404.09868