6 papers
Position: Sustainable Open-Source AI Requires Tracking the Cumulative Footprint of Derivatives
Shaina Raza, Iuliia Zarubiieva, Ahmed Y. Radwan +4
Open-source AI is scaling rapidly, and model hubs now host millions of artifacts. Each foundation model can spawn large numbers of fine-tunes, adapters, quantizations, merges, and…
SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding
Ahmed Y. Radwan, Christos Emmanouilidis, Hina Tabassum +2
Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, while their ability to process seq…
Reducing Hallucinations in LLMs via Factuality-Aware Preference Learning
Sindhuja Chaduvula, Ahmed Y. Radwan, Azib Farooq +2
Preference alignment methods such as RLHF and Direct Preference Optimization (DPO) improve instruction following, but they can also reinforce hallucinations when preference judgmen…
Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights
Tahniat Khan, Soroor Motie, Sedef Akinli Kocak +1
The rapid adoption of large language models (LLMs) has led to significant energy consumption and carbon emissions, posing a critical challenge to the sustainability of generative A…
Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods
Shaina Raza, Rizwan Qureshi, Azib Farooq +4
Large language models (LLMs) reproduce misinformation not by memorizing false facts alone, but by learning the linguistic patterns that make falsehoods persuasive, such as hedging,…
FairSense-AI: Responsible AI Meets Sustainability
Shaina Raza, Mukund Sayeeganesh Chettiar, Matin Yousefabadi +2
In this paper, we introduce FairSense-AI: a multimodal framework designed to detect and mitigate bias in both text and images. By leveraging Large Language Models (LLMs) and Vision…