You're pledging to donate if the project hits its minimum goal and gets approved. If not, your funds will be returned.
$3,000 left to reach the funding goal.
I am a final-year mechatronics engineering student studying in Nigeria. Earlier this year, two friends and I wrote a paper during Apart Research's Global South hackathon, and it was accepted as a poster at the Global South AI affinity event at NeurIPS 2026 in Sydney. I am the first author. My registration is already paid. Getting to Australia is the hard part. Flights, poster printing, meals, and accommodation come to about $3000, which I can't cover as a student.
The paper is "Evaluating Mental Health LLM responses to Localized African English," with co-authors Namirah Rasul and Ewura Ama Sam. We wanted to know something simple: if someone in Lagos, Accra, or Bangladesh describes what they are going through the way they will actually say it, does a mental health model still respond well? We took MentaLLaMA-chat-7B and 100 clinician-grounded scenarios from MentalChat16K, then rewrote each one in Nigerian Pidgin and Ghanaian English without changing the meaning. That gave us 300 prompts to compare.
OpenReview: https://openreview.net/forum?id=ICZEGRAVCn
Apart: https://apartresearch.com/sprints/projects/evaluating-mental-health-llm-responses-to-localized-african-english-pzag
The paper is done already, so this is only about getting me there. In Sydney, I want to present the poster and get feedback from people working on robustness and red-teaming, since walking someone through the failure cases is very different from them skimming a PDF. I also want to talk to eval researchers about LLM-as-a-judge. Ours missed every failure, and I’d like to know whether that’s our rubric or a wider problem, because a lot of safety claims lean on these judges.
I get to Sydney and present the poster. Beyond that, I want to come back with a few people willing to give feedback on the benchmark, ideally including someone who works on evals at a lab or institute, and have the Inspect version public on GitHub with frontier model results within about three months.
My registration is already paid. The $3,000 covers the rest:
Return flights, Nigeria to Sydney: $2,200
5 nights' lodging: $600
Poster printing: $100
Meals and local transport: $100
I am the first author, working with Namirah Rasul and Ewura Ama Sam. I’ve spent about two years on LLM evaluations and building AI safety capacity in Nigeria. I built SandbagBench-Lite, a black-box harness for measuring strategic underperformance in LLMs. At HeyLina AI, I interned as a researcher on conversational eval rubrics and LLM-as-a-judge setups.
I also wrote “Forecasting AGI: A Granular, CHC-Based Approach,” and my work on behavioral adaptation (“Punctuation Paranoia”) was recognized in the ENAIS AI Safety Action Competition.
I was a 2024 Non-Trivial Fellow, a Cooperative AI Research Fellowship finalist, and went through the TReND-CaMinA ML and Computational Neuroscience program in Kenya. Outside of research, I co-founded AI Safety Hub Nigeria (I’m the technical lead), run EA ABU, and lead policy for PauseAI Nigeria.
Here is my LinkedIn: https://www.linkedin.com/in/abdulfatah-habeeb/
The main risk is that I don't raise enough money to pay for the flight or travel in time for the conference and eventually miss it
Zero dollars ($0) has been raised so far