# Potato 2.0 at ACL 2026

Source: https://www.potatoannotator.com/blog/potato-2-acl-2026

**Potato 2.0 is published in the ACL 2026 System Demonstrations.** The paper describes what Potato looks like now: 39 annotation task types across text, audio, image, and video, support for labeling the outputs of AI agents, and an AI-in-the-loop workflow where one annotator works alongside an LLM through iterative prompt refinement. If you use Potato in your research, this is the paper to cite.

You can read it on the [ACL Anthology](https://aclanthology.org/2026.acl-demo.37/).

## What the paper covers

The first Potato paper, back at EMNLP 2022, described a config-first tool for text annotation: write a YAML file, get a working interface, skip the custom front-end code. That idea still holds, but the tool has grown well past text since then.

Potato 2.0 reports on what arrived with that growth:

- The 39 task types now cover text, audio, image, and video, so one config can describe a sentiment scale, an audio event timeline, a bounding-box task, or a video rating.
- As people started evaluating LLMs and agents, Potato added displays for agent trajectories, tool calls, and multi-step outputs that annotators can label directly.
- A human annotator and an LLM can work the same task together, with the human refining prompts as they go rather than labeling every item by hand.

For the longer version of any of these, the [feature docs](/docs/features) go into detail.

## Potato's publication record

Potato has shown up in the research record a few times. For most uses, cite the ACL 2026 paper.

- **Potato 2.0: A Comprehensive Annotation Platform with AI-in-the-Loop Support.** Jurgens, Chen, and Iyer. ACL 2026, Volume 3: System Demonstrations. [ACL Anthology](https://aclanthology.org/2026.acl-demo.37/)
- **Potato: The Portable Text Annotation Tool.** Pei et al. EMNLP 2022: System Demonstrations. [ACL Anthology](https://aclanthology.org/2022.emnlp-demos.33/) · [arXiv](https://arxiv.org/abs/2212.08620)

The Potato demo also received the Best Demo Award at HCOMP 2024.

## How to cite Potato

```bibtex
@inproceedings{jurgens-etal-2026-potato,
    title = "Potato 2.0: A Comprehensive Annotation Platform with {AI}-in-the-Loop Support",
    author = "Jurgens, David and Chen, Michael and Iyer, Lina",
    booktitle = "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    pages = "374--386",
    url = "https://aclanthology.org/2026.acl-demo.37/",
}
```

If you are citing the original text-annotation work specifically, the EMNLP 2022 paper is still the right reference:

```bibtex
@inproceedings{pei-etal-2022-potato,
    title = "{POTATO}: The Portable Text Annotation Tool",
    author = "Pei, Jiaxin and Ananthasubramaniam, Aparna and Wang, Xingyao and Zhou, Naitian and Dedeloudis, Apostolos and Sargent, Jackson and Jurgens, David",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-demos.33/",
    pages = "327--337",
}
```

Thanks to everyone who has used Potato, filed issues, and sent annotation tasks we had not thought of. If you build something with it, we would like to hear about it on [GitHub](https://github.com/davidjurgens/potato).