# A Dual-Track Framework for Template-Constrained LaTeX Conversion

arXiv: https://arxiv.org/abs/2606.23107 · HTML: https://mlsanity.com/paper/2606.23107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds](https://mlsanity.com/paper/2506.02009/) (2025)
- [READoc: A Unified Benchmark for Realistic Document Structured Extraction](https://mlsanity.com/paper/2409.05137/) (2024)
- [TeXpert: A Multi-Level Benchmark for Evaluating LaTeX Code Generation by LLMs](https://mlsanity.com/paper/2506.16990/) (2025)
- [RAGOps: Operating and Managing Retrieval-Augmented Generation Pipelines](https://mlsanity.com/paper/2506.03401/) (2025)
- [Structural Hallucination in Large Language Models: A Network-Based Evaluation of Knowledge Organization and Citation Integrity](https://mlsanity.com/paper/2603.01341/) (2026)
- [MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop](https://mlsanity.com/paper/2605.17159/) (2026)
- [Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production](https://mlsanity.com/paper/2605.18818/) (2026)

## Abstract (arXiv)

With the increasing demands for advanced document conversion, mapping structured Markdown drafts into template-compliant formats like LaTeX remains a challenge. Existing approaches largely depend on either deterministic rule-based converters or pure end-to-end Large Language Model (LLM) generation. The former fails to correctly handle asset insertions and template-specific constraints, while the latter tends to induce semantic drift, leading to hallucinations that are difficult to debug. To address these limitations, we introduce a robust Dual-Track Framework that systematically decouples template formatting from document processing: an offline track extracts template constraints into a reusable manifest, while an online track implements a hybrid execution pipeline. This pipeline confines LLM usage exclusively to reasoning-intensive components (e.g., semantic metadata, bibliographic references, and complex visual/tabular layouts) while delegating rule-based engines for deterministic processing. Empirical evaluation across 7 LaTeX templates and 56 published research papers demonstrates that our method preserves better structural fidelity, satisfies diverse layout constraints, and achieves a higher compilation success rate compared to the previous baselines.