Attention heads of large language models: A survey

Z Zheng, Y Wang, Y Huang, S Song, M Yang… - arXiv preprint arXiv …, 2024 - arxiv.org
Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various
tasks but remain as black-box systems. Consequently, the reasoning bottlenecks of LLMs …

Distinguishing Ignorance from Error in LLM Hallucinations

A Simhi, J Herzig, I Szpektor, Y Belinkov - arXiv preprint arXiv:2410.22071, 2024 - arxiv.org
Large language models (LLMs) are susceptible to hallucinations-outputs that are
ungrounded, factually incorrect, or inconsistent with prior generations. We focus on close …

Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs

A Simhi, J Herzig, I Szpektor, Y Belinkov - arXiv preprint arXiv:2404.09971, 2024 - arxiv.org
Large language models (LLMs) are susceptible to hallucination, which sparked a
widespread effort to detect and prevent them. Recent work attempts to mitigate …