Strong hallucinations from negation and how to fix them

arXiv:2402.10543v1 Announce Type: new
Abstract: Despite great performance on many tasks, language models (LMs) still struggle with reasoning, sometimes providing responses that cannot possibly be true because they stem from logical incoherence. We call such responses \textit{strong hallucinations} and prove that they follow from an LM's computation of its internal representations for logical operators and outputs from those representations. Focusing on negation, we provide a novel solution in which negation is treated not as another element of a latent representation, …

abstract arxiv call computation cs.ai cs.cl hallucinations language language models lms performance prove reasoning responses stem struggle tasks them true type