arXiv:2611.01909v1 Announce Type: new
Abstract: Hybrid language models interleave linear-attention layers with a small number of softmax-attention layers. Prior work largely attributes in-context retrieval to softmax attention, treating linear attention primarily as a mechanism for compressing past context. We revisit this division of labor and show that linear attention plays a direct role in retrieval by constructing the query used by softmax attention. Studying Qwen3.5 (Gated DeltaNet) and Granite4.0 (Mamba-2), we identify an Encode–Address circuit. An early Encode block preserves token identity, while an Address block constructs the final-position representation from which a softmax \emph{reader} forms its attention query. Transplanting this representation between prompts with different queried keys redirects retrieval in 0.97–0.99 of cases. The Address block's recurrent state carries the retrieval target, and its computation transfers across architectures: replacing Granite's Address block with Qwen's restores retrieval accuracy to 0.92–0.94 without updating either model's weights. Across six Qwen3.5 models, Address computation becomes distributed at larger scales over a chain of blocks, each guiding a successive reader, as the query no longer passes from one reader to the next through attention. These findings reveal a division of labor in hybrid retrieval: linear attention constructs the query, while softmax attention performs the lookup. Code is available at https://github.com/yuang-chen/LinearQuery
Abstract: Hybrid language models interleave linear-attention layers with a small number of softmax-attention layers. Prior work largely attributes in-context retrieval to softmax attention, treating linear attention primarily as a mechanism for compressing past context. We revisit this division of labor and show that linear attention plays a direct role in retrieval by constructing the query used by softmax attention. Studying Qwen3.5 (Gated DeltaNet) and Granite4.0 (Mamba-2), we identify an Encode–Address circuit. An early Encode block preserves token identity, while an Address block constructs the final-position representation from which a softmax \emph{reader} forms its attention query. Transplanting this representation between prompts with different queried keys redirects retrieval in 0.97–0.99 of cases. The Address block's recurrent state carries the retrieval target, and its computation transfers across architectures: replacing Granite's Address block with Qwen's restores retrieval accuracy to 0.92–0.94 without updating either model's weights. Across six Qwen3.5 models, Address computation becomes distributed at larger scales over a chain of blocks, each guiding a successive reader, as the query no longer passes from one reader to the next through attention. These findings reveal a division of labor in hybrid retrieval: linear attention constructs the query, while softmax attention performs the lookup. Code is available at https://github.com/yuang-chen/LinearQuery
This article has been indexed from cs.AI updates on arXiv.org
Read the original article:
Who Asks, Who Answers: Linear Attention Builds the Query in Hybrid Language Models