ReFT: Representation Finetuning for LMs
Free while signed in. Answers cite the passages they came from.
Stanford's ReFT freezes the base model and instead learns small interventions on hidden representations at selected layers, offering a more parameter-efficient alternative to LoRA-style PEFT.
Representations as targets: Instead of updating weights, ReFT trains lightweight linear interventions that modify a rank-limited subspace of the hidden state at specified layers and positions.
LoReFT variant: Low-rank LoReFT is the headline method and is drop-in compatible with the PEFT ecosystem, acting as a direct LoRA replacement.
15-65x fewer parameters than LoRA: Across commonsense reasoning, arithmetic, instruction tuning, and GLUE, LoReFT matches or beats LoRA while using 15-65x fewer trainable parameters.
Interpretability-informed: The method is motivated by interpretability results showing that semantic content is encoded in compact subspaces of the hidden state, and it exploits that structure directly.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack