collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2024

FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs

Deema Alnuhait, Neeraja Kirtane, Muhammad Khalifa +1

Language models (LMs) hallucinate. We inquire: Can we detect and mitigate hallucinations before they happen? This work answers this research question in the positive, by showing th…

cs.CL2024

AraTrust: An Evaluation of Trustworthiness for LLMs in Arabic

Emad A. Alghamdi, Reem I. Masoud, Deema Alnuhait +3

The swift progress and widespread acceptance of artificial intelligence (AI) systems highlight a pressing requirement to comprehend both the capabilities and potential risks associ…

cs.CL2024

CIDAR: Culturally Relevant Instruction Dataset For Arabic

Zaid Alyafeai, Khalid Almubarak, Ahmed Ashraf +9

Instruction tuning has emerged as a prominent methodology for teaching Large Language Models (LLMs) to follow instructions. However, current instruction datasets predominantly cate…

cs.CL20232 cited

Using Textual Interface to Align External Knowledge for End-to-End Task-Oriented Dialogue Systems

Qingyang Wu, Deema Alnuhait, Derek Chen +1

Traditional end-to-end task-oriented dialogue systems have been built with a modularized design. However, such design often causes misalignment between the agent response and exter…

cs.CL20232 cited

FaceChat: An Emotion-Aware Face-to-face Dialogue Framework

Deema Alnuhait, Qingyang Wu, Zhou Yu

While current dialogue systems like ChatGPT have made significant advancements in text-based interactions, they often overlook the potential of other modalities in enhancing the ov…