bias mitigation 1logical reasoning 1multilingual evaluation 1multi-objective optimization 1synthetic data generation 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization
Abdullah Shaikh, Zain Naqi, Taha Zahid +2
The paper describes a system for SemEval‑2026 Task 11 that uses synthetic rule‑based training data and a multi‑objective loss to separate formal logical reasoning from content bias…
cs.CL2026
UrduLM: A Resource-Efficient Monolingual Urdu Language Model
Syed Muhammad Ali, Hammad Sajid, Zainab Haider +3
Urdu, spoken by 230 million people worldwide, lacks dedicated transformer-based language models and curated corpora. While multilingual models provide limited Urdu support, they su…