Arthur Charpentier on Nostr: "Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models" ...
"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models"
https://arxiv.org/abs/2401.01301 "We find that legal hallucinations are alarmingly prevalent, occurring between 69% of the time with ChatGPT 3.5 and 88% with Llama 2, when these models are asked specific, verifiable questions about random federal court cases. (....) We illustrate that LLMs often fail to correct a user's incorrect legal assumptions in a contra-factual question setup"
Published at
2024-06-01 15:48:40Event JSON
{
"id": "aab33682744e4821722ccb7bad4409d1534b4fa90ea04eea621dd9545829be2a",
"pubkey": "3c989aa8626cfb78be01531a3cedee2f1e810325e00ab43911669d19e5b7a97e",
"created_at": 1717256920,
"kind": 1,
"tags": [
[
"proxy",
"https://mastodon.social/users/freakonometrics/statuses/112542149520325994",
"activitypub"
]
],
"content": "\"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models\" https://arxiv.org/abs/2401.01301 \"We find that legal hallucinations are alarmingly prevalent, occurring between 69% of the time with ChatGPT 3.5 and 88% with Llama 2, when these models are asked specific, verifiable questions about random federal court cases. (....) We illustrate that LLMs often fail to correct a user's incorrect legal assumptions in a contra-factual question setup\"",
"sig": "a5d2940bddc2b296ee869da1f5cdf6899bba1518e3cbb7d6624ad79e6bce9eaa3f4b22fdedd22648ee83d3ca64847f4509c28e8e1db979a09811cbc241b521a9"
}
