I have loaded a dataset of about 50K rows of survey data. There’s 8 columns, two of which are free-text data. When I ask it to pull quotes that demonstrate examples of a given topic, it consistently hallucinates the quote. Each one starts off matching my source data, but quickly becomes nonsense. Wh…

Thanks for the heads up! I Tried again with only 100 rows of data (8,100 tokens) and it still is only paraphrasing the exact quotes, all while telling me they are precise. Still, if the tool can only handle 100 rows at a time, I would rather just look at the data manually… I will try it with Claude…

I also find it difficult to use ChatGPT to analyze tables & numbers. In case it helps, I tried to develop a custom GPT to self-report hallucinations, feel free to test it out in your research here & good luck! ChatGPT - Diagnostics Mode for analysis & research An advanced GPT that provi…

I think you’d better using API of ACTION. there is free API service like ‘Sheety’. I have solved some problem like you….

ChatGPT 4.0 keeps hallucinating exact quotes from the free-response data I've loaded

Prompting

AndersenWebworks April 3, 2024, 1:29pm 2

GPT4 can only handle up to ~ 8000 tokens, so feeding it 50k rows of data can’t work. It will just remember the last ~ 8000 tokens from those. And if that wasn’t bad enough there is more problems currently:

Topic		Replies	Views
How to Reduce Hallucinations in ChatGPT Responses to Data Queries Prompting gpt-4 , adv-data-analytics	5	20477	December 2, 2024
GPT-4 extremely lazy while working with just 100-150 test results tables Prompting gpt-4	2	503	April 30, 2024
Accuracy of retrieved data (large CSV) GPT builders	5	1415	April 17, 2024
Hallucinations and headaches using GPT-5 in production Feedback gpt-5	19	13252	September 17, 2025
Gpt-4o hallucinates a lot Community api	27	6156	December 2, 2024

ChatGPT 4.0 keeps hallucinating exact quotes from the free-response data I've loaded

Related topics