MiA-Signature: Approximating Global Activation for Long-Context Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909022398971904 |
|---|---|
| author | Li, Yuqing Li, Jiangnan Yu, Mo Lin, Zheng Wang, Weiping Zhou, Jie |
| author_facet | Li, Yuqing Li, Jiangnan Yu, Mo Lin, Zheng Wang, Weiping Zhou, Jie |
| contents | A growing body of work in cognitive science suggests that reportable conscious access is associated with \emph{global ignition} over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension suggests a plausible mechanism that cognition may rely on a compact representation that approximates the global influence of activation on downstream processing. Inspired by this idea, we introduce the concept of \textbf{Mindscape Activation Signature (MiA-Signature)}, a compressed representation of the global activation pattern induced by a query. In LLM systems, this is instantiated via submodular-based selection of high-level concepts that cover the activated context space, optionally refined through lightweight iterative updates using working memory. The resulting MiA-Signature serves as a conditioning signal that approximates the effect of the full activation state while remaining computationally tractable. Integrating MiA-Signatures into both RAG and agentic systems yields consistent performance gains across multiple long-context understanding tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06416 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MiA-Signature: Approximating Global Activation for Long-Context Understanding Li, Yuqing Li, Jiangnan Yu, Mo Lin, Zheng Wang, Weiping Zhou, Jie Computation and Language A growing body of work in cognitive science suggests that reportable conscious access is associated with \emph{global ignition} over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension suggests a plausible mechanism that cognition may rely on a compact representation that approximates the global influence of activation on downstream processing. Inspired by this idea, we introduce the concept of \textbf{Mindscape Activation Signature (MiA-Signature)}, a compressed representation of the global activation pattern induced by a query. In LLM systems, this is instantiated via submodular-based selection of high-level concepts that cover the activated context space, optionally refined through lightweight iterative updates using working memory. The resulting MiA-Signature serves as a conditioning signal that approximates the effect of the full activation state while remaining computationally tractable. Integrating MiA-Signatures into both RAG and agentic systems yields consistent performance gains across multiple long-context understanding tasks. |
| title | MiA-Signature: Approximating Global Activation for Long-Context Understanding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.06416 |