# Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning

arXiv: https://arxiv.org/abs/2609.00367 · HTML: https://mlsanity.com/paper/2609.00367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 12 of its 14 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 12 of 12)

- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [Efficient Attention: Attention with Linear Complexities](https://mlsanity.com/paper/1812.01243/) (2018)
- [SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation](https://mlsanity.com/paper/2406.14991/) (2024)
- [Long Context RAG Performance of Large Language Models](https://mlsanity.com/paper/2411.03538/) (2024)
- [Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective](https://mlsanity.com/paper/2412.10390/) (2024)
- [LongFuncEval: Measuring the effectiveness of long context models for function calling](https://mlsanity.com/paper/2505.10570/) (2025)
- [From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems](https://mlsanity.com/paper/2410.01066/) (2024)
- [SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications](https://mlsanity.com/paper/2506.18951/) (2025)
- [InstructExcel: A Benchmark for Natural Language Instruction in Excel](https://mlsanity.com/paper/2310.14495/) (2023)
- [Evaluating Large Language Models for Real-World Engineering Tasks](https://mlsanity.com/paper/2505.13484/) (2025)
- [CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs](https://mlsanity.com/paper/2509.00971/) (2025)
- [Breaking the Attention Bottleneck](https://mlsanity.com/paper/2406.10906/) (2024)

## Abstract (arXiv)

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.