GPT-5, 법적 추론 실험에서 연방 판사보다 100% 대 52% 성과

출처: Hacker News — https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6155012

연구 개요

• GPT-5의 법적 추론 능력을 평가하는 실험 진행

주요 결과

• GPT-5: 100% 정확도
• 연방 판사들: 52% 정확도

출처

• 연구 논문 링크
• 댓글 링크

의견

댓글/토론에서 나온 의견을 참고용으로 정리했습니다. (사실로 단정하지 말고 맥락 확인 권장)

• Hacker News · @arctic-true: What’s interesting here from a legal perspective is that they acknowledge a somewhat unsettled question of law regarding South Dakota’s choice-of-law regime. The AI got the “right” answer every time, but I am curious to know if it ever grappled with the uncertainty. This is the trouble with the concept of AI judging: …
  • 링크: https://news.ycombinator.com/item?id=46983458
• Hacker News · @thewanderer1983: I was diagnosed with a rare blood disease called Essential Thrombocythemia (ET) which is part of a group of diseases called myeloproliferative neoplasms. This happened about three years ago. Recently, I decided to get a second opinion and my new specialist changed my diagnosis from ET to Polycythemia Vera (PV). She al…
  • 링크: https://news.ycombinator.com/item?id=46983587
• Hacker News · @Zafira: > nonzero risk of unfair judgement from a computer I feel like this is really poor take on what justice really is. The law itself can be unjust. Empowering a seemingly “unbiased” machine with biased data or even just assuming that justice can be obtained from a “justice machine” is deeply flawed. Whether you like i…
  • 링크: https://news.ycombinator.com/item?id=46983554
• Hacker News · @codingdave: IANAL, but this seems like an odd test to me. Judges do what their name implies - make judgment calls. I find it re-assuring that judges get different answers under different scenarios, because it means they are listening and making judgment calls. If LLMs give only one answer, no matter what nuances are at play, that…
  • 링크: https://news.ycombinator.com/item?id=46982894
• Hacker News · @swisniewski: The premise seems flawed. From the paper: “we find that the LLM adheres to the legally correct outcome significantly more often than human judges” That presupposes that a “legally correct” outcome exists The Common Law, which is the foundation of federal law and the law of 49/50 states, is a “bottom up” legal sys…
  • 링크: https://news.ycombinator.com/item?id=46983118
• Hacker News · @jmalicki: The title is wrong. The title of the paper is "Silicon Formalism: Rules, Standards, and Judge AI" When they say legally correct they are clear that they mean in a surface formal reading of the law. They are using it to characterize the way judges vs. GPT-5 treat legal decisions, and leave it as an open quest…
  • 링크: https://news.ycombinator.com/item?id=46983553

댓글

댓글을 읽어오는 중입니다.