Trusted Source Alignment in Large Language Models
Large language models (LLMs) are trained on web-scale corpora that inevitably include contradictory factual information from sources of varying reliability. In this paper, we propose measuring an LLM property called trusted source alignment (TSA): the model's propensity to align with content pr...
Gespeichert in:
Hauptverfasser: | , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Large language models (LLMs) are trained on web-scale corpora that inevitably
include contradictory factual information from sources of varying reliability.
In this paper, we propose measuring an LLM property called trusted source
alignment (TSA): the model's propensity to align with content produced by
trusted publishers in the face of uncertainty or controversy. We present
FactCheckQA, a TSA evaluation dataset based on a corpus of fact checking
articles. We describe a simple protocol for evaluating TSA and offer a detailed
analysis of design considerations including response extraction, claim
contextualization, and bias in prompt formulation. Applying the protocol to
PaLM-2, we find that as we scale up the model size, the model performance on
FactCheckQA improves from near-random to up to 80% balanced accuracy in
aligning with trusted sources. |
---|---|
DOI: | 10.48550/arxiv.2311.06697 |