Metraipolis › archive › dc_fa6b791502d8

Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning — arXiv:2609.00367

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00367
License (as archived)
CC0-1.0
Archived
2026-10-17T06:33:16.511Z
SHA-256 of the archived text
2359a9f8d3f71a4a471229653e7819bc482222d1dd2ff97acf97c67110708804
Stable URL of this page
https://metraipolis.com/documento/dc_fa6b791502d8

How to cite

Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning — arXiv:2609.00367 — arXiv (en), https://arxiv.org/abs/2609.00367 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa6b791502d8 (Metraipolis archive dc_fa6b791502d8, sha256 2359a9f8d3f71a4a471229653e7819bc482222d1dd2ff97acf97c67110708804)
BibTeX
@misc{dcfa6b791502d8,
  title = {Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning — arXiv:2609.00367},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00367},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa6b791502d8; sha256 2359a9f8d3f71a4a471229653e7819bc482222d1dd2ff97acf97c67110708804},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00367. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models are increasingly deployed for sophisticated data engineering tasks such as generating structured queries from natural language, Text-to-SQL, and automating complex spreadsheet operations. However, maximizing their utility demands both higher finetuning-free accuracy and solutions to the computational bottleneck imposed by the Transformer architectures inherent quadratic (On2) time complexity. This paper introduces a novel drop-in neurosymbolic layer designed to seamlessly integrate into existing LLM backbones enhancing logical reasoning and mitigating long-context resource consumption. On the reasoning front, the layer immediately and significantly improves performance yielding an average accuracy increase of 85% across rigorous benchmarks including BIRD-CRITIC and LiveSQLBench, critically achieving these gains without any task specific finetuning or RLHF. Concurrently, we repurpose this approach to address the severe computational strain of long context inference. By leveraging symbolic processing to prioritize and compress relevant contextual information the layer reduces the effective token usage by over 50% and brings the effective time complexity down from O(n2) to approximately O(n) on certain long context tasks. This dual impact approach not only makes LLMs substantially more reliable for data engineering but also drastically reduces the computational pressure on inference chips, making long context tasks more manageable and cost effective.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.00367 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:15:12.774Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).