OpenAI’s popular generative AI, ChatGPT, has been hailed for its many abilities including writing essays and speeches, completing homework assignments, cracking computer code and even penning poems. However, the technology is not infallible—two New York lawyers were recently fined for submitting a legal brief with fake case citations generated by ChatGPT.
Bad Faith and Misinformation
Steven Schwartz of law firm Levidow, Levidow & Oberman had used the chatbot to research a client’s personal injury case against airline Avianca. Unfortunately for him though and his colleague Peter LoDuca who was named on the brief—the citations they submitted were almost entirely fictitious.
The Colombian carrier’s lawyers told the court that several examples cited could not be found; some were completely fabricated while others misidentified judges or involved airlines that didn’t exist. District Judge Peter Kevin Castel ruled that Schwartz and LoDuca had acted in bad faith by submitting “gibberish” portions of their brief containing nonsensical content—including fake quotes—and making false statements to the court.
Hallucinations and Disinformation Risks
While impressive in many respects, generative AI like OpenAI’s ChatGPT often tend to “hallucinate” when giving answers due to lack of true understanding about information inputted into it. The risk of disinformation spreading through such technological means remains a concern among critics wary about potential misuse.
Asked whether it should be used to help write legal briefs after this incident came up in Sky News interview with OpenAI’s GPT-3 language model (ChatGPT), it said: “While I can provide general information and assistance, it is important to note I am an AI language model and not a qualified legal professional.”
Judge Castel noted there are inherent dangers in lawyers using AI for assistance, and warned them to ensure their filings are accurate. He ruled that the lawyers had “continued to stand by the fake opinions” even after being questioned by both the court and airline.
Schwartz, LoDuca, and their law firm were fined $5,000 in total (£3,926). Levidow, Levidow & Oberman has said it is considering an appeal as they say they made a good faith mistake in failing to believe that a piece of technology could make up cases out of whole cloth.
Lawyers Fined for Fake ChatGPT Citations written by Hoda F.
Learn here more about AI and Machine Learning.
You can also reach out our social media team by following our pages on Facebook, Instagram and Twitter.
