{"id":678613,"date":"2025-07-04T21:35:14","date_gmt":"2025-07-04T18:35:14","guid":{"rendered":"https:\/\/buradabiliyorum.com\/en\/pilot-program-integrates-ai-generated-notes-with-human-community-notes-on-x-platform\/"},"modified":"2025-07-04T21:35:14","modified_gmt":"2025-07-04T18:35:14","slug":"pilot-program-integrates-ai-generated-notes-with-human-community-notes-on-x-platform","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/pilot-program-integrates-ai-generated-notes-with-human-community-notes-on-x-platform\/","title":{"rendered":"Pilot program integrates AI-generated notes with human community notes on X platform"},"content":{"rendered":"
\n
\n
\n
\n \"Pilot
\n An expansion of the Community Notes pipeline from \u201call-human\u201d to a hybrid \u201chuman-LLM\u201d model. Today (top): Human note writers draft proposed notes in response to a misleading post, and other human contributors rate their helpfulness; the bridging algorithm picks the broadly helpful notes. Future (bottom): LLMs will also participate in the writing stage, producing notes or assisting human writers, while the rating stage remains human-only. Community feedback from human raters flows back to improve LLM note generation (RLCF). Credit: arXiv<\/i> (2025). DOI: 10.48550\/arxiv.2506.24118
\n <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n

X (formerly Twitter) launched its “Community Notes” program in 2021 to combat misinformation by allowing users to add contextual notes on posts that might be deceptive or lead to misinterpretation. An example would be users labeling an AI-generated video as such, so that other users would not be tricked into believing the event in the video actually occurred. Community notes are rated by the decentralized social media<\/a> community to determine their usefulness. Only the notes determined useful by raters are shown on the post. X’s Community Notes later inspired other platforms to launch similar programs.<\/p>\n

Until this point, these community-based, fact-checking systems consisted entirely of human generated notes and human raters. However, X is now piloting a new program, allowing AI\u2014in the form of large learning models (LLMs)\u2014to generate community notes alongside humans.<\/p>\n

The proposed model, published<\/a> recently by X researchers, integrates both human and AI notes into the pipeline, but still only allows humans to determine which notes are helpful. In an age of rampant misinformation, the researchers believe the speed and scale of notes generated by LLMs is necessary. They write, “allowing automated note creation would enable the system to operate at a scale and speed that is impossible for human writers, potentially providing context for orders of magnitude more content across the web.”<\/p>\n

The LLM note generation will be further improved by learning from community feedback in a process referred to as reinforcement learning from community feedback (RLCF). This process is meant to refine future note generation through a diverse array of feedback from community members with a variety of views and is expected to result in more accurate, unbiased and helpful notes.<\/p>\n

\n
\n
\n \"Pilot
\n A research agenda for LLM-powered Community Notes. (1) Customized LLMs for note generation; (2) AI \u2018co-pilots\u2019 for human writers; (3) AI assistance for human raters; (4) Intelligent note \u2018matching\u2019 adapts existing helpful notes to new, similar contexts; (5) Evolving the core algorithm for AI-generated content; (6) Building a robust and open infrastructure. Credit: arXiv<\/i> (2025). DOI: 10.48550\/arxiv.2506.24118
\n <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n

Although the new model is expected to improve the misinformation checking process overall, there are some potential risks. The researchers note potential issues with AI-generated notes being persuasive and inaccurate\u2014a known issue with other models\u2014and a risk of over-homogenizing notes. There is also some concern that human note writers might engage less often, due to the abundance of AI-generated notes, and that this abundance might overwhelm the capacity of human raters to sufficiently determine what is helpful and what is not.<\/p>\n

<\/p>\n

The study also discusses many future possibilities involving even more AI integration into the community note pipeline, while still keeping human checks in place. Future directions might involve integrating AI co-pilots for human writers to conduct research and put out more notes faster and AI-assistance to help human raters audit notes more efficiently. The researchers also propose verification and authentication methods for screening human raters and writers, customization of LLMs and methods for adapting and reapp<\/a>lying already-validated notes to similar contexts, so that raters are not rating the same concepts over and over.<\/p>\n

There is potential for these human-AI collaboration methods, with humans providing nuance and diversity and LLMs providing the speed and scale to deal with the abundance of available information online, but there is still a good deal of testing to be done to ensure the human touch is not lost. The study authors describe their end goal by saying, “the goal is not to create an AI assistant that tells users what to think, but to build an ecosystem that empowers humans to think more critically and understand the world better.”<\/p>\n

\n

\n Written for you by our author Krystal Kasal<\/a>,
\n edited by Andrew Zinin<\/a>\u2014this article is the result of careful human work. We rely on readers like you to keep independent science<\/a> journalism alive.
\n If this reporting matters to you,
\n please consider a donation<\/a> (especially monthly).
\n You’ll get an ad-free<\/b> account as a thank-you.\n <\/p>\n<\/p><\/div>\n

\n

More information:<\/strong>
\n\t\t\t\t\t\t\t\t\t\t\t\tHaiwen Li et al, Scaling Human Judgment in Community Notes with LLMs, arXiv<\/i> (2025). DOI: 10.48550\/arxiv.2506.24118<\/a><\/p>\n

\n\t\t\t\t\t\t\t\t\t\t\t\t\tJournal information:<\/strong>
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tarXiv<\/cite>
\n
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/svg>
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n<\/p><\/div>\n

\n \u00a9 2025 Science X Network\n <\/p>\n

<\/p>\n

\n

\n Citation<\/strong>:
\n Pilot program integrates AI-generated notes with human community notes on X platform (2025, July 4)
\n retrieved 4 July 2025
\n from https:\/\/techxplore.com\/news<\/a>\/2025-07-ai-generated-human-community-platform.html\n <\/p>\n

\n This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
\n part may be reproduced without the written permission. The content is provided for information purposes only.\n <\/p>\n<\/p><\/div>\n<\/p><\/div>\n