Jinhu Qi

Jinhu Qi

Jinhu Qi is a visiting researcher at the HUMANS LAB at the University of Southern California, under the mentorship of Professor Emilio Ferrara. His research centers on Large Language Models (LLMs) applications, particularly in Retrieval-Augmented Generation (RAG) using vector databases and knowledge graphs. Jinhu also explores Chain of Thought (CoT) reasoning, language translation, and misinformation detection. With a Master's in Analytics from USC and a Bachelor's in Computer and Information Science from the University of Oregon, he is currently pursuing a PhD for 2025 to further advance his research in these areas.

👋Hello there, I’m Jinhu Qi!

🔬 PhD Aspirant | AI & LLM Enthusiast | Researcher in Language Translation & Misinformation Detection Machine Translation in AI by geeksforgeeks

Welcome to my academic profile. I am Jinhu Qi, an aspiring PhD researcher with a deep focus on Large Language Models (LLMs), Chain of Thought (CoT) reasoning, and Retrieval-Augmented Generation (RAG) techniques. My research addresses key challenges in multilingual communication and misinformation detection across social media platforms.

Research Interests

As a visiting researcher at the HUMANS LAB at the University of Southern California (USC), led by Professor Emilio Ferrara, I have explored the impact of misinformation on platforms such as YouTube and 4chan. These experiences have been formative in shaping my PhD research trajectory, which will commence in 2025. My research interests include:

  • Misinformation detection and mitigation on social media
  • Leveraging LLMs and RAG to facilitate cross-linguistic communication
  • Improving AI transparency and governance by addressing hallucination challenges in large models

PhD Research Objectives

I am currently applying for PhD programs for Fall 2025, with the objective of advancing research in AI, specifically within:

  • LLMs, RAG, and knowledge graphs for enhanced reasoning and interpretability
  • AI governance to improve transparency and prevent hallucinations in LLMs
  • Utilizing AI and LLMs for societal impact, particularly in cross-cultural communication

Academic Background

  • Master of Science in Analytics, University of Southern California (USC)
  • Bachelor of Science in Computer & Information Science, University of Oregon (minor in Korean Studies)

Research Focus

  • Development of Large Language Models with Retrieval-Augmented Generation and Chain of Thought techniques
  • Misinformation detection and classification of offensive content on social media
  • Knowledge graph and vector database integration to enhance AI reasoning and transparency

Selected Projects

  • Graph-RAG: Employing knowledge graphs to enhance transparency and interpretability in AI
  • Tibetan Tourism Recommender: Addressing LLM hallucinations in smart tourism systems
  • Misinformation Detection: Identifying and mitigating false information on YouTube and 4chan

Publications

Technical Skills

  • Python, Machine Learning, Neo4j, Graph RAG, Vector Databases, Chain of Thought, LangChain
  • Expertise in Pre-training and Fine-tuning LLMs through SFT/ORPO

Contact

I welcome opportunities for research collaboration and discussions. Please feel free to email me or explore my publications for more details.

“Pursuing cutting-edge AI research to enhance cross-linguistic communication and build more transparent, reliable systems.”