Latticethe structure behind the noise

Papers Digest Topics Selected Labs Collections FAQ

Created by Flynn Lachendro

Papers Digest Topics Labs Saved

Search

Search papers, labs, and topics across Lattice.

Built by Flynn Lachendro·𝕏 / Twitter·RSS··FAQ·Glossary·Privacy

Ahmed Y. Radwan | Lattice

Ahmed Y. Radwan

Vector Institute for Artificial Intelligence, Toronto, Canada

Papers on Lattice

1

Total citations

2

Topics

3

h-index

2

Research focus

Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)RLHF & Preference Learning (1)

Frequent co-authors

Sindhuja Chaduvula (1)Azib Farooq (1)Yani Ioannou (1)Shaina Raza (1)

Papers (1)

Jan 6, 2026

Jan 6, 2026·also Independent Researcher

Reducing Hallucinations in LLMs via Factuality-Aware Preference Learning

LLMs can be five times more truthful with a simple tweak to DPO that prioritizes factual correctness over fluency.

Sindhuja Chaduvula, Ahmed Y. Radwan, Azib Farooq +2

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks RLHF & Preference Learning