# GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search

arXiv: https://arxiv.org/abs/2602.08945 · HTML: https://mlsanity.com/paper/2602.08945/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 15 of 15)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [The science of fake news](https://mlsanity.com/paper/2307.07903/) (2023)
- [Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate](https://mlsanity.com/paper/2402.07401/) (2024)
- [The Role of the Crowd in Countering Misinformation: A Case Study of the COVID-19 Infodemic](https://mlsanity.com/paper/2011.05773/) (2020)
- [Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking](https://mlsanity.com/paper/2411.06116/) (2024)
- [Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors](https://mlsanity.com/paper/2403.09747/) (2024)
- [Community notes reduce engagement with and diffusion of false information online](https://mlsanity.com/paper/2502.13322/) (2025)
- [Did the Roll-Out of Community Notes Reduce Engagement With Misinformation on X/Twitter?](https://mlsanity.com/paper/2307.07960/) (2023)
- [Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation](https://mlsanity.com/paper/2510.11423/) (2025)
- [COMMUNITYNOTES: A Dataset for Exploring the Helpfulness of Fact-Checking Explanations](https://mlsanity.com/paper/2510.24810/) (2025)
- [Timeliness, Consensus, and Composition of the Crowd: Community Notes on X](https://mlsanity.com/paper/2510.12559/) (2025)
- [Fact-Checking Comments Precede Community Notes to Misleading Posts on X](https://mlsanity.com/paper/2509.11052/) (2025)
- [Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search](https://mlsanity.com/paper/2511.18749/) (2025)
- [AI Feedback Enhances Community-Based Content Moderation through Engagement with Counterarguments](https://mlsanity.com/paper/2507.08110/) (2025)

## Built on by (most cited first, 2 of 2)

- [CommunityFact: A Dynamic, Multilingual, Multi-domain Benchmark for Misinformation Detection in the Wild](https://mlsanity.com/paper/2605.30241/) (2026)
- [Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes](https://mlsanity.com/paper/2606.02215/) (2026)

## Abstract (arXiv)

Community-based moderation offers a scalable alternative to centralized fact-checking, yet it faces significant structural challenges, and existing AI-based methods fail in "cold start" scenarios. To tackle these challenges, we introduce GitSearch (Gap-Informed Targeted Search), a framework that treats human-perceived quality gaps, such as missing context, etc., as first-class signals. GitSearch has a three-stage pipeline: identifying information deficits, executing real-time targeted web-retrieval to resolve them, and synthesizing platform-compliant notes. To facilitate evaluation, we present PolBench, a benchmark of 78,698 U.S. political tweets with their associated Community Notes. We find GitSearch achieves 99% coverage, almost doubling coverage over the state-of-the-art. GitSearch surpasses human-authored helpful notes with a 69% win rate and superior helpfulness scores (3.87 vs. 3.36), demonstrating retrieval effectiveness that balanced the trade-off between scale and quality.