INTRALIGN trains language models to produce citations from both retrieved documents and parametric memory, with confidence scores on internal citations and improved trustworthiness metrics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation
INTRALIGN trains language models to produce citations from both retrieved documents and parametric memory, with confidence scores on internal citations and improved trustworthiness metrics.