GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917260841451520 |
|---|---|
| author | Singh, Sahajpreet Jaidka, Kokil Kan, Min-Yen |
| author_facet | Singh, Sahajpreet Jaidka, Kokil Kan, Min-Yen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08945 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search Singh, Sahajpreet Jaidka, Kokil Kan, Min-Yen Computation and Language Computers and Society 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. |
| title | GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search |
| topic | Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2602.08945 |