EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Query-Aware Context Compression for Efficient Long-Context Language Model Inference

Maya Laurent, Aaron McLeod

Computer Life · 13.11.2026 · 15 (2) · 48-54

DOI: 10.54097/zhed3474 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Life, online erschienen am 13.11.2026. Verfasst von Maya Laurent und 1 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Query-aware context compression can reduce the amount of source text forwarded to a language model, but keyword ranking may discard evidence connected through intermediate entities. We present QAB-R, a training-free sentence selector combining BM25, query-identifier-constrained anchor selection, canonicalized entity matching, and at most two bridge-linked candidates under a fixed sentence budget. We first evaluate a single-bridge baseline on 300 synthetic single- and two-hop queries. We then execute 300 additional held-out stress cases covering paraphrases, competing entity notes, identifier formatting variation, and combined changes; a separate 60-case test extends source contexts to 58,368 whitespace-delimited words. At a 10% sentence budget, QAB-R preserved complete two-hop support in all 60 cases of each stress condition, whereas single-bridge retention fell to 0% under competing notes and format changes. For 1,024 fact pairs, the median QAB-R CPU preprocessing time was 66.3 ms, and the selected text contained 5,741 of 58,368 input words. The study reports evidence completeness, retained input length, and CPU preprocessing cost; downstream reader accuracy and GPU inference speed are distinct system-level outcomes.

Zitieren

APA

Laurent, M., & McLeod, A. (2026). Query-Aware Context Compression for Efficient Long-Context Language Model Inference. Computer Life, 15(2), 48-54. https://doi.org/10.54097/zhed3474

Vancouver

Laurent M, McLeod A. Query-Aware Context Compression for Efficient Long-Context Language Model Inference. Computer Life. 2026;15(2):48-54. doi:10.54097/zhed3474

BibTeX
@article{Laurent2026,
  author = {Laurent, Maya and McLeod, Aaron},
  title = {Query-Aware Context Compression for Efficient Long-Context Language Model Inference},
  journal = {Computer Life},
  year = {2026},
  volume = {15},
  number = {2},
  pages = {48--54},
  doi = {10.54097/zhed3474}
}
Kostenlos starten →