Data-similarity and data-influence produce significantly overlapping rankings of training documents for LLM outputs, with asymmetry allowing a favorable cost-accuracy trade-off.
Position: Curvature matrices should be democratized via linear operators
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Bayesian fine-tuning of large models can be done efficiently by projecting uncertainties into low-dimensional subspaces, yielding improved calibration and generalization while keeping computational costs low.
citing papers explorer
-
Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior
Data-similarity and data-influence produce significantly overlapping rankings of training documents for LLM outputs, with asymmetry allowing a favorable cost-accuracy trade-off.
-
Bayesian Fine-tuning in Projected Subspaces
Bayesian fine-tuning of large models can be done efficiently by projecting uncertainties into low-dimensional subspaces, yielding improved calibration and generalization while keeping computational costs low.