← all papers · overview

Generation Constraint Scaling Can Mitigate Hallucination

Abstract

Addressing the issue of hallucinations in large language models (LLMs) is a critical challenge. As the cognitive mechanisms of hallucination have been related to memory, here we explore hallucination for LLM that is enabled with explicit memory mechanisms. We empirically demonstrate that by simply scaling the readout vector that constrains generation in a memory-augmented LLM decoder, hallucinatio

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).