Skip to content

SRC01 — Hallucination Taxonomy Survey — Scorecard

Source

Field Value
Title A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
Publisher arXiv / ACM Transactions on Information Systems
Authors Huang et al.
Date 2023 (updated 2024)
URL https://arxiv.org/abs/2311.05232
Type Academic survey paper

Summary Ratings

Dimension Rating
Reliability High
Relevance High
Missing data Low
Measurement bias Low
Selective reporting Low
Randomization N/A
Protocol deviation N/A
COI/Funding Low

Rationale

Dimension Rationale
Reliability Published in ACM TOIS; comprehensive survey of the field
Relevance Provides the taxonomy that training materials should but do not use
Bias Academic survey; systematic coverage

Evidence Extracts

Evidence Summary
SRC01-E01 Taxonomy includes intrinsic/extrinsic, factuality/faithfulness; hallucination types range from easily detectable to almost undetectable