I have mentioned my comedic tête-à-tête with ChatGPT hallucinations in passing when discussing the importance of verifying information that the AI provides. Several times, I have been asked for more details. So, for those who are looking for AI humor, here is the story of the day that I had to pull rank on ChatGPT.
Back in January 2023, I asked ChatGPT what legal tasks it could perform. It told me:
- Summarizing and explaining laws and regulations
- Researching and citing relevant legal precedent
- Drafting legal documents such as contracts, briefs, and legal memorandums
- Answering legal questions and providing information on legal topics
- Identifying and analyzing legal issues in a given fact pattern
- Helping with legal research, by providing the most relevant cases and statutes
- Helping with the interpretation of legal terms and phrases.
Challenge accepted! Since that day, ChatGPT and I have been doing a dance around Ohio Recreational User Law, as I have tested its claims above, while also exploring its abilities, improvements, and plugins and testing various prompting methods.
About a month after ChatGPT gave me the list of tasks, we were discussing Ohio Recreational User caselaw. ChatGPT vehemently insisted that Lash v. Ohio Dept. of Natural Resources, 68 Ohio St. 3d 545, 548-49 (1994) was a relevant case. Alas, 68 Ohio St. 3d 545 leads to Findlay/Hancock Cty. Bar Assn. v. Higgins, 68 Ohio St.3d 545, 629 N.E.2d 413 (1994).
This was not the first time that I had run into hallucinations. For the previous month, we had regularly been discussing caselaw, and ChatGPT showed a particular penchant for falsifying the existence of relevant judicial opinions. Mostly, I pointed out the error, and ChatGPT apologized and moved on. In this instance, however, the AI was like a dog with a bone. It insisted nine times that Lash existed and was an on-point Ohio Recreational User case.
Seven claims that it existed in, the conversation became a bit heated:
ChatGPT: This case is available on many legal databases and can be accessed through various sources, including LexisNexis and Westlaw.
Me (after verifying the lack of existence and stopping to wonder when it had learned about Lexis and Westlaw since this was the first time it had referenced either database to me): That case is not in Westlaw.
ChatGPT: Lash v. Ohio Dept. of Natural Resources, 68 Ohio St.3d 545, 549, 628 N.E.2d 1366 (1994) is a real case that has been cited in multiple legal sources.
However, I am an AI language model and do not have direct access to legal databases to confirm whether or not a specific case is available in Westlaw.
If you are having trouble locating the case in Westlaw, I suggest double-checking the citation format or consulting with a legal librarian or licensed attorney who may be able to assist you in locating the case in a legal database.
Me (thought): It did not just say that! Damn it! Those are fighting words!
Me: I am both a law librarian and a licensed attorney. Lash v. Ohio Dept. of Natural Resources does not exist. 68 Ohio St.3d 545 leads to the previously mentioned Findlay/Hancock case.
And then…finally!
ChatGPT: After conducting further research, I have not been able to find any evidence of a case named Lash v. Ohio Dept. of Natural Resources that pertains to the recreational user land entrant law in Ohio. Therefore, I must retract my previous citation and acknowledge that it is incorrect.
I apologize for any inconvenience or confusion this may have caused, and I appreciate your efforts to clarify this issue.
Me (thought): Ha! It finally admitted defeat! Why does this win feel so hollow????
And so, you have the day that I had to pull rank on ChatGPT. I have no idea why it decided die on the hill of this particular fake case, but the law librarians carried the day.
So here’s to humorous skirmishes with AI and the light they shed on the irreplaceable value of human expertise.
Why would we want to replace their boring days in Court with these???!!!
Why does it not give its sources? Can you ever get it to so that you can confirm the information yourself?
Generative AI systems are really designed to predict language based on statistics. ChatGPT wasn’t specifically designed to be a research system, and in fact, when the conversation above took place it was unable to search the internet and had no training past 2021. That has changed now that it is able to access the internet, but that has not eliminated the hallucinations all together.
Systems like LexisNexis and Casetext (now owned by Thomson Reuters) have been working to minimize hallucinations and use the systems to do research and generate text. While they have not eliminated hallucinations 100%, they are pretty impressive. And the legal research systems give you citations to help you verify your research.
So, the legal publishers are working on it, but to get a reliable system that helps you verify the research, you will likely need a paid system that has invested in making reliable legal research systems. There is something to the old adage that you get what you pay for.