Search Results for author: Sadat Shahriar

Found 6 papers, 4 papers with code

Inference time LLM alignment in single and multidomain preference spectrum

no code implementations24 Oct 2024 Sadat Shahriar, Zheng Qi, Nikolaos Pappas, Srikanth Doss, Monica Sunkara, Kishaloy Halder, Manuel Mager, Yassine Benajiba

Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure.

Model Editing Prompt Engineering

Seeing Through AI's Lens: Enhancing Human Skepticism Towards LLM-Generated Fake News

1 code implementation20 Jun 2024 Navid Ayoobi, Sadat Shahriar, Arjun Mukherjee

By providing cues in human-written and LLM-generated news, we can help individuals increase their skepticism towards fake LLM-generated news.

POS POS Tagging

HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?

1 code implementation19 Feb 2024 Shubhashis Roy Dipta, Sadat Shahriar

This paper describes our system developed for SemEval-2024 Task 8, ``Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection'' Machine-generated texts have been one of the main concerns due to the use of large language models (LLM) in fake text generation, phishing, cheating in exams, or even plagiarizing copyright materials.

Contrastive Learning Data Augmentation +2

The Looming Threat of Fake and LLM-generated LinkedIn Profiles: Challenges and Opportunities for Detection and Prevention

1 code implementation21 Jul 2023 Navid Ayoobi, Sadat Shahriar, Arjun Mukherjee

We show that the suggested method can distinguish between legitimate and fake profiles with an accuracy of about 95% across all word embeddings.

Language Modelling Large Language Model +2

SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation

1 code implementation1 May 2023 Sadat Shahriar, Thamar Solorio

Subjectivity and difference of opinion are key social phenomena, and it is crucial to take these into account in the annotation and detection process of derogatory textual content.

Deception Detection with Feature-Augmentation by soft Domain Transfer

no code implementations1 May 2023 Sadat Shahriar, Arjun Mukherjee, Omprakash Gnawali

In this era of information explosion, deceivers use different domains or mediums of information to exploit the users, such as News, Emails, and Tweets.

Deception Detection Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.