# Citation Parsing and Analysis with Language Models

arXiv: https://arxiv.org/abs/2505.15948 · HTML: https://mlsanity.com/paper/2505.15948/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 8 of 8)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)
- [The Journal Coverage of Web of Science and Scopus: a Comparative Analysis](https://mlsanity.com/paper/1511.08096/) (2015)
- [Reference Coverage Analysis of OpenAlex compared to Web of Science and Scopus](https://mlsanity.com/paper/2401.16359/) (2024)
- [An analysis of the suitability of OpenAlex for bibliometric analyses](https://mlsanity.com/paper/2404.17663/) (2024)

## Built on by (most cited first, 3 of 3)

- [Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities](https://mlsanity.com/paper/2603.13651/) (2026)
- [RenoBench: A Citation Parsing Benchmark](https://mlsanity.com/paper/2603.25640/) (2026)
- [Digging Up Citations: FOSSIL, a Dataset and Workflow for Reference Extraction in Law and the Humanities](https://mlsanity.com/paper/2606.01109/) (2026)

## Abstract (arXiv)

A key type of resource needed to address global inequalities in knowledge production and dissemination is a tool that can support journals in understanding how knowledge circulates. The absence of such a tool has resulted in comparatively less information about networks of knowledge sharing in the Global South. In turn, this gap authorizes the exclusion of researchers and scholars from the South in indexing services, reinforcing colonial arrangements that de-center and minoritize those scholars. In order to support citation network tracking on a global scale, we investigate the capacity of open-weight language models to mark up manuscript citations in an indexable format. We assembled a dataset of matched plaintext and annotated citations from preprints and published research papers. Then, we evaluated a number of open-weight language models on the annotation task. We find that, even out of the box, today's language models achieve high levels of accuracy on identifying the constituent components of each citation, outperforming state-of-the-art methods. Moreover, the smallest model we evaluated, Qwen3-0.6B, can parse all fields with high accuracy in 25 passes, suggesting that post-training is likely to be effective in producing small, robust citation parsing models. Such a tool could greatly improve the fidelity of citation networks and thus meaningfully improve research indexing and discovery, as well as further metascientific research.