Saved in:
Bibliographic Details
Main Author: Lu, Tingmingke
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.05481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913724533571584
author Lu, Tingmingke
author_facet Lu, Tingmingke
contents Large language models (LLMs) often generate inaccurate yet credible-sounding content, known as hallucinations. This inherent feature of LLMs poses significant risks, especially in critical domains. I analyze LLMs as a new class of engineering products, treating hallucinations as a product attribute. I demonstrate that, in the presence of imperfect awareness of LLM hallucinations and misinformation externalities, net welfare improves when the maximum acceptable level of LLM hallucinations is designed to vary with two domain-specific factors: the willingness to pay for reduced LLM hallucinations and the marginal damage associated with misinformation.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05481
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Maximum Hallucination Standards for Domain-Specific Large Language Models
Lu, Tingmingke
General Economics
Economics
Large language models (LLMs) often generate inaccurate yet credible-sounding content, known as hallucinations. This inherent feature of LLMs poses significant risks, especially in critical domains. I analyze LLMs as a new class of engineering products, treating hallucinations as a product attribute. I demonstrate that, in the presence of imperfect awareness of LLM hallucinations and misinformation externalities, net welfare improves when the maximum acceptable level of LLM hallucinations is designed to vary with two domain-specific factors: the willingness to pay for reduced LLM hallucinations and the marginal damage associated with misinformation.
title Maximum Hallucination Standards for Domain-Specific Large Language Models
topic General Economics
Economics
url https://arxiv.org/abs/2503.05481