Hallucination
A confident response by an AI that does not seem to be justified by its training data.
- from
- Naming
- added
- 2026-10-10
- likes
- 0
similar
-
Cleanlab cleanlab.ai
An API for detecting and scoring hallucinations in LLM outputs.
-
Artificial Condition goodreads.com
[4.3]
-
Anthropic anthropic.com
Provides access to a class of advanced large language models called Claude designed to provide human-like text responses and engage in conversational interactions.
-
Oracle en.wikipedia.org
A black box that magically gives answers even to undecidable questions like the halting problem.
-
UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations aclanthology.org
NAACL'24, 2024. [All Versions]. This paper explores the task of uncommonsense abductive reasoning. Given a piece of context with an unexpected outcome, this task requires reasoning abductively to generate an explanation that makes the unexpected outcome more likely in the…
-
How We Know What Not To Think sciencedirect.com
Trends in Cognitive Sciences, 2019. [All Versions]. Humans often represent and reason about unrealized possible actions---the vast infinity of things that were not (or have not yet been) chosen. This capacity is central to the most impressive of human abilities: causal…
Naming › Machine Learning and Artificial Intelligence: “A confident response by an AI that does not seem to be justified by its training data.”