# A Dynamic Self-Evolving Extraction System

arXiv: https://arxiv.org/abs/2603.06915 · HTML: https://mlsanity.com/paper/2603.06915/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Self-evolving search agents, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 4 of its 14 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-evolving search agents](https://mlsanity.com/synth/self-evolving-search-agents/)

## Builds on (most cited first, 4 of 4)

- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [Rethinking Language Models as Symbolic Knowledge Graphs](https://mlsanity.com/paper/2308.13676/) (2023)
- [Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replay](https://mlsanity.com/paper/2402.00580/) (2024)

## Abstract (arXiv)

The extraction of structured information from raw text is a fundamental component of many NLP applications, including document retrieval, ranking, and relevance estimation. High-quality extractions often require domain-specific accuracy, up-to-date understanding of specialized taxonomies, and the ability to incorporate emerging jargon and rare outliers. In many domains--such as medical, legal, and HR--the extraction model must also adapt to shifting terminology and benefit from explicit reasoning over structured knowledge. We propose DySECT, a Dynamic Self-Evolving Extraction and Curation Toolkit, which continually improves as it is used. The system incrementally populates a versatile, self-expanding knowledge base (KB) with triples extracted by the LLM. The KB further enriches itself through the integration of probabilistic knowledge and graph-based reasoning, gradually accumulating domain concepts and relationships. The enriched KB then feeds back into the LLM extractor via prompt tuning, sampling of relevant few-shot examples, or fine-tuning using KB-derived synthetic data. As a result, the system forms a symbiotic closed-loop cycle in which extraction continuously improves knowledge, and knowledge continuously improves extraction.