Prism-Δ: Differential Subspace Steering for Prompt Highlighting in Large Language Models

YuyaoGe, Shenghua Liu, Yiwei Wang, Bibaolong, Lingrui Mei, Jiayu Yao, Jiafeng Guo, Xueqi Cheng

Prism-Δ: Differential Subspace Steering for Prompt Highlighting in Large Language Models: 12 upvotes on Hugging Face Daily Papers, #13 of 29 papers on 2026-03-12. Day-by-day upvote history.

Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge of existing Key-editing approaches is extracting steering directions that capture the difference between relevant and irrelevant contexts, rather than shared structural patterns common to both. We propose PRISM-Δ (Projection-based Relevance-Informed Steering Method), which decomposes the difference between positive and negative cross-covariance matrices to maximize discriminative energy while eliminating shared directions. Each attention head receives a continuous softplus importance weight, letting weak-but-useful heads contribute at reduced strength. The framework extends naturally to Value representations, capturing content-channel signal that Key-only methods leave unused. Across four benchmarks and five models, our methods match or exceed the best existing method on 19 of 20 configurations, with relative gains up to +13.0%, while halving the fluency cost of steering. Our methods also scale to long-context retrieval, outperforming the best existing method by up to +5.1% relative gain. PRISM-Δ is compatible with FlashAttention and adds negligible memory overhead.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.