Activation patching reveals that citation decisions in Llama-3.1-8B RAG are implemented by a distributed attributional ensemble of heads and layers; targeted interventions fix most missed and spurious citations on PopQA.
Attributing response to context: A jensen-shannon divergence driven mechanistic study of context attribution in retrieval-augmented generation
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1
external citations · external index
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Algorithms based on the least core approximate stable credit assignments for AI-generated content using orders of magnitude fewer LLM calls than alternatives.
citing papers explorer
-
How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
Activation patching reveals that citation decisions in Llama-3.1-8B RAG are implemented by a distributed attributional ensemble of heads and layers; targeted interventions fix most missed and spurious citations on PopQA.
-
In-Context Credit Assignment via the Core
Algorithms based on the least core approximate stable credit assignments for AI-generated content using orders of magnitude fewer LLM calls than alternatives.