Contrastive Decoding Diffing recovers exact implanted facts from finetuned LLMs via logit-space differences between finetuned and base models, outperforming white-box baselines with less access.
Cladder: Assessing causal reasoning in language models, 2024 a
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Instrumented data augments observations with mechanistic models, uncertainty, and counterfactuals to enable causal interventions via Pearl's do-operator in scientific machine learning.
citing papers explorer
-
Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
Contrastive Decoding Diffing recovers exact implanted facts from finetuned LLMs via logit-space differences between finetuned and base models, outperforming white-box baselines with less access.
-
Instrumented data for causal scientific machine learning
Instrumented data augments observations with mechanistic models, uncertainty, and counterfactuals to enable causal interventions via Pearl's do-operator in scientific machine learning.