Empirical study on five LLMs finds pretrained-to-aligned paths yield bigger gains over baseline than finetuned-to-aligned paths, though absolute accuracy remains lower for pretrained starts.
naacl-long.248/
2 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
2
Pith papers citing it
7
external citations · OpenAlex
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Fisher information from the target data distribution supplies a task-dependent criterion for selecting LoRA directions that outperforms weight-magnitude heuristics.
citing papers explorer
-
Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation
Empirical study on five LLMs finds pretrained-to-aligned paths yield bigger gains over baseline than finetuned-to-aligned paths, though absolute accuracy remains lower for pretrained starts.
-
Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
Fisher information from the target data distribution supplies a task-dependent criterion for selecting LoRA directions that outperforms weight-magnitude heuristics.