The paper defines faithfulness as reproducibility and reports moderate to high reproducibility for LLM-generated layperson algorithms in law, finance, and health, but the algorithms are not shown to reflect the models' internal mechanisms.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains
The paper defines faithfulness as reproducibility and reports moderate to high reproducibility for LLM-generated layperson algorithms in law, finance, and health, but the algorithms are not shown to reflect the models' internal mechanisms.