# Tag Embedding and Well-defined Intermediate Representation improve Auto-Formulation of Problem Description

arXiv: https://arxiv.org/abs/2212.03575 · HTML: https://mlsanity.com/paper/2212.03575/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 2 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 2 of 2)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions](https://mlsanity.com/paper/2209.15565/) (2022)

## Built on by (most cited first, 5 of 5)

- [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023)
- [From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifesto](https://mlsanity.com/paper/2402.16269/) (2024)
- [Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks](https://mlsanity.com/paper/2410.22296/) (2024)
- [Highlighting Named Entities in Input for Auto-Formulation of Optimization Problems](https://mlsanity.com/paper/2212.13201/) (2022)
- [CP-Model-Zoo: A Natural Language Query System for Constraint Programming Models](https://mlsanity.com/paper/2509.07867/) (2025)

## Abstract (arXiv)

In this report, I address auto-formulation of problem description, the task of converting an optimization problem into a canonical representation. I first simplify the auto-formulation task by defining an intermediate representation, then introduce entity tag embedding to utilize a given entity tag information. The ablation study demonstrate the effectiveness of the proposed method, which finally took second place in NeurIPS 2022 NL4Opt competition subtask 2.