Out of curiosity, why has ‘hallucination’ been chosen as the word to describe these errors? It seems more appropriate to describe them as confabulations, but my background is in neuroscience/neurology rather than computer science. I’m sure I’m missing something simple. Grateful for any insights. B…

I think your idea here is great, Confabulations are definitely a more accurate term than hallucinations, I think the term hallucinations where chosen because it’s a general, more readily understandable term by must humans. Confabulations are more correct but most people, especially those who are no…

[image] colin.m.smith115: Out of curiosity, why has ‘hallucination’ been chosen as the word to describe these errors? Started running this down in the research papers. At present found this Survey of Hallucination in Natural Language Generation by Ziwei Ji , Nayeon Lee , Rita Frieske , Tiezhen…

Good job searching the litterature! Out of curiosity, can you describe your method for finding that paper? I especially liked this figure in the section about visual hallucinations: [IMG_20230422_155051]

[image] N2U: Out of curiosity, can you describe your method for finding that paper? I can’t remember the exact Google query used but it was like this because the paper was near the top of the list. natural language hallucination ai word origin pdf In earlier research learned of the Wikipe…

This is interesting, based off of the historical context, could the processes that lead to the initial hallucination cases (reporting things that aren’t there in an image, computer vision?) be considered something entirely different than the processes that result in confabulation in LLMs? Would it b…

[image] colin.m.smith115: Would it be useful to separate these terms while we’re trying to understand these errors more deeply? My personal view is no. Both words have an established meaning. Reusing a word with an established meaning and/or adding another meaning to it just compounds the pro…

This is why I love bringing so many different fields of study together. Great collaboration and I just learned something this Saturday morning!

Yeah I agree with Eric on this, i don’t think it makes sense to separate them, but if you can create some demarcation criteria that separates them, I’ll say go for it :laughing:

While we’re at it: I’d like to share this absolutely amazing tool for searching research papers. I found yesterday so I’ve only done minimal testing: [image] GitHub - kennethleungty/Keyword-Analysis-with-KeyBERT-and-Taipy: Keyword... Keyword Extraction and Analysis Pipeline & Applicati…

Yes, I have noticed its tendency to please. And I know I should make my questions more neutral. It makes me realize that, when talking to people, I tend to load my question towards the desired answer. I have been practicing my critical thinking. I guess I need to try harder.

Hallucination vs Confabulation

Community

freddyvega August 27, 2024, 5:38pm 23

We can candy-coat it all we want. It’s flat out lying!

Topic		Replies	Views
Scientific Criticisms of LLMs are Somewhat BS Community research	15	1126	June 10, 2024
Addressing confabulation Community	2	840	June 10, 2021
Why language models hallucinate [OpenAI Research Paper] Community hallucinations	2	586	September 5, 2025
AI hallucinations are basically randomized thoughts? Community chatgpt , dalle3	5	555	September 23, 2025
Mitigating Hallucinations in RAG - a 2025 review Community rag	7	495	October 12, 2025

Hallucination vs Confabulation

Related topics