RAPTOR introduces a tree-organized retrieval method using recursive abstractive summaries, achieving a 20% absolute accuracy improvement on the QuALITY benchmark when paired with GPT-4.
Do Long-Range Language Models Actually Use Long-Range Context?
2 Pith papers cite this work, alongside 36 external citations. Polarity classification is still indexing.
2
Pith papers citing it
36
external citations · OpenAlex
verdicts
UNVERDICTED 2representative citing papers
Empirical Jacobian analysis reveals that token influence in trained language models decays as a power law with distance (exponent ~0.8), a learned property not present in random models.
citing papers explorer
-
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
RAPTOR introduces a tree-organized retrieval method using recursive abstractive summaries, achieving a 20% absolute accuracy improvement on the QuALITY benchmark when paired with GPT-4.
-
How Token Influence Decays with Distance: A Green-Function View of Trained Language Models
Empirical Jacobian analysis reveals that token influence in trained language models decays as a power law with distance (exponent ~0.8), a learned property not present in random models.