TracLLM traces an LLM output back to the specific text passages in a long context that caused it, using hierarchical group scoring with denoising and ensembling.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TracLLM: A Generic Framework for Attributing Long Context LLMs
TracLLM traces an LLM output back to the specific text passages in a long context that caused it, using hierarchical group scoring with denoising and ensembling.