[2604.17843] Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research

-->

Computer Science > Human-Computer Interaction

arXiv:2604.17843 (cs)

[Submitted on 20 Apr 2026]

Title:Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research

Authors:Nimisha Karnatak, Mohamad Chatila, Daniel Alejandro Pinzón Hernández, Reza Yazdanfar, Michelle Dugas, Renos Vakis<br>View a PDF of the paper titled Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research, by Nimisha Karnatak and 5 other authors

View PDF<br>HTML (experimental)

Abstract:General-purpose LLMs pose misinformation risks for development and policy experts, lacking epistemic humility for verifiable outputs. We present AVA (AI + Verified Analysis), a GenAI platform built on a curated library of over 4,000 World Bank Reports with multilingual capabilities. AVA's multi-agent pipeline enables users to query and receive evidence-based syntheses. It operationalizes epistemic humility through two mechanisms: citation verifiability (tracing claims to sources) and reasoned abstention (declining unsupported queries with justification and redirection). We conducted an in-the-wild evaluation with over 2,200 individuals from heterogeneous organisations and roles in 116 countries, via log analysis, surveys, and 20 interviews. Difference-in-Differences estimates associate sustained engagement with 2.4-3.9 hours saved weekly. Qualitatively, participants used AVA as a specialized "evidence engine"; reasoned abstention clarified scope boundaries, and trust was calibrated through institutional provenance and page-anchored citations. We contribute design guidelines for specialized AI and articulate a vision for "ecosystem-aware" Humble AI.

Comments:<br>Accepted at ACM CHI'26

Subjects:

Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)

ACM classes:<br>H.5.2; I.2.11

Cite as:<br>arXiv:2604.17843 [cs.HC]

(or<br>arXiv:2604.17843v1 [cs.HC] for this version)

https://doi.org/10.48550/arXiv.2604.17843

Focus to learn more

arXiv-issued DOI via DataCite

Related DOI:

https://doi.org/10.1145/3772318.3791062

Focus to learn more

DOI(s) linking to related resources

Submission history<br>From: Nimisha Karnatak [view email]<br>[v1]<br>Mon, 20 Apr 2026 05:53:52 UTC (3,513 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research, by Nimisha Karnatak and 5 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.HC

next >

new<br>recent<br>| 2026-04

Change to browse by:

cs<br>cs.AI

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)