LLMs Will Always Hallucinate, and We Need to Live With This

> Still struggling to find anything in your wall of words that actually backs up your claims. I mean, one easy thing you could do is to explain how LLMs are adequate as >> thinking machines, search engines, knowledge archives, … How much practical experience do you have with LLMs? Have you even tried running models locally? Then how have you not experienced yourself tweaking few parameters and gotten the same model to say one thing and its opposite just after? Through your extensive use of commercial LLMs, aren't you getting daily occurrences of confabulations? Making stuff up is what defines¹ LLMs, and that's not me saying it. If your field is so inconsequential that reliability and faithfulness of your output has no practical merit or repercussion, I'm glad that you get some entertainment out of this. Still doesn't make it the norm, though. ¹: https://arxiv.org/abs/2409.05746

Much like you can search the internet until you find a source that agrees with you, you can select a set of papers that "confirm" a particular viewpoint, especially in developing fields of research. In this case, the selected papers all support the view LLMs "know what they know" on some internal level, which iiuc is not (yet?) a consensus viewpoint (from my outsider perspective). But from the list alone, you might get that impression. Related: Still no lie detector for language models: probing empirical and conceptual roadblocks - https://link.springer.com/article/10.1007/s11098-023-02094-3 Hallucination is Inevitable: An Innate Limitation of Large Language Models - https://arxiv.org/abs/2401.11817 LLMs Will Always Hallucinate, and We Need to Live With This - https://arxiv.org/abs/2409.05746 (disclaimer, I also have not read any of these papers beyond the title!)

On what basis you think you will avoid hallucination(s) ? LLM will always hallucinate. People did already some research, among which : https://arxiv.org/abs/2409.05746 and https://arxiv.org/abs/2401.11817 for example.

I'm not overthinking it, some papers describe it [0] and [1] for example. I agree for some subjects you can deal with some error. The problem is not how often but how bad just one single error can be. My point was on controversial topic, where a single error can deal serious damage. Yes it must be error-free like for a nuclear reactor. Just imagine a Q&A chatbot answering questions on the subject of Israel and Palestine or something else really touchy, do you really think you can afford any error/hallucination ? [0] : https://arxiv.org/abs/2409.05746 [1] : https://arxiv.org/abs/2401.11817

Since the first day I consider AI as a noob working very fast and always making errors. My main usage is for tedious and non-critical tasks such as boilerplates. And I always review what has been generated like a merge/pull request, because in a sense that's what it is. What reinforces my opinion are papers like these : https://arxiv.org/abs/2409.05746 https://arxiv.org/abs/2401.11817