/explore
|
You are here 
|
www.alignmentforum.org | ||
| | | | |
joecarlsmith.com
|
|
| | | | | On a career move, and on AI-safety-focused people working at AI companies. | |
| | | | |
www.lesswrong.com
|
|
| | | | | On boxing AIs, and on making deals with them. | |
| | | | |
www.lesswrong.com
|
|
| | | | | We founded Anthropic because we believe the impact of AI might be comparable to that of the industrial and scientific revolutions, but we aren't conf... | |
| | | | |
lilianweng.github.io
|
|
| | | Hallucination in large language models usually refers to the model generating unfaithful, fabricated, inconsistent, or nonsensical content. As a term, hallucination has been somewhat generalized to cases when the model makes mistakes. Here, I would like to narrow down the problem of hallucination to cases where the model output is fabricated and not grounded by either the provided context or world knowledge. There are two types of hallucination: In-context hallucination: The model output should be consistent with the source content in context. Extrinsic hallucination: The model output should be grounded by the pre-training dataset. However, given the size of the pre-training dataset, it is too expensive to retrieve and identify conflicts per generation. If w... | ||
