DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wedgwood, James, Muhamed, Aashiq, Diab, Mona T., Smith, Virginia
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908905843458048
author Wedgwood, James
Muhamed, Aashiq
Diab, Mona T.
Smith, Virginia
author_facet Wedgwood, James
Muhamed, Aashiq
Diab, Mona T.
Smith, Virginia
contents Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional. From preference triples, DSPA computes a conditional-difference map linking prompt features to generation-control features; during decoding, it modifies only token-active latents, without base-model weight updates. Across Gemma-2-2B/9B and Qwen3-8B, DSPA improves MT-Bench and is competitive on AlpacaEval while preserving multiple-choice accuracy. Under restricted preference data, DSPA remains robust and can rival the two-stage RAHF-SCIT pipeline while requiring up to $4.47\times$ fewer alignment-stage FLOPs. Finally, we audit the SAE features DSPA modifies, finding that preference directions are dominated by discourse and stylistic signals, and provide theory clarifying the conditional-difference map estimate and when top-$k$ ablation is principled.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21461
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
Wedgwood, James
Muhamed, Aashiq
Diab, Mona T.
Smith, Virginia
Machine Learning
Artificial Intelligence
Computation and Language
Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional. From preference triples, DSPA computes a conditional-difference map linking prompt features to generation-control features; during decoding, it modifies only token-active latents, without base-model weight updates. Across Gemma-2-2B/9B and Qwen3-8B, DSPA improves MT-Bench and is competitive on AlpacaEval while preserving multiple-choice accuracy. Under restricted preference data, DSPA remains robust and can rival the two-stage RAHF-SCIT pipeline while requiring up to $4.47\times$ fewer alignment-stage FLOPs. Finally, we audit the SAE features DSPA modifies, finding that preference directions are dominated by discourse and stylistic signals, and provide theory clarifying the conditional-difference map estimate and when top-$k$ ablation is principled.
title DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2603.21461