Skip to content
View juminsuh's full-sized avatar
🏠
Working from home
🏠
Working from home
15 followers · 20 following

Block or report juminsuh

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
juminsuh/README.md

Hi, I'm Minsuh Joo 👋

I'm an undergraduate student majoring in Artificial Intelligence at Ewha Womans University, South Korea. My research interests focus on large language models (LLMs), particularly LLM evaluation, uncertainty estimation, and reliable AI. Currently, I'm an undergraduate research assistant at LKI Lab, where I work on understanding and improving the reliability of LLMs. Please see my CV for more information about me 😊.

🔬 Research Interests

  • Abstention Learning
  • Trustworthy of AI
  • Uncertainty Estimation and Hallucination Detection
  • LLM Evaluation and Benchmarking

📚 Research

  • MAPLE: A multi-axis evaluation framework for knowledge extraction enhancement in LLMs. (arXiv preprint 2026)[paper]
  • Cleanse: Clustering-based semantic consistency for LLM uncertainty estimation. (ACL 2025 GEM Workshop)[paper]

📫 Contact

Email LinkedIn

Pinned Loading

  1. MAPLE MAPLE Public

    Datasets and Evaluation Metrics for MAPLE

    Python

  2. Cleanse Cleanse Public

    Accepted to ACL 2025 GEM orkshop (Oral Presentation)

    Python

  3. CORDE_FashionCoordinator CORDE_FashionCoordinator Public

    CORDE: Outfit Recommendation Chatbot

    2

  4. Option-Specific-RAG-for-LLM-QA Option-Specific-RAG-for-LLM-QA Public

    Designed an option-specific RAG pipeline with question-type-aware prompting and majority-voting ensembles to improve evidence retrieval and answer reliability.

    Python 2

  5. PuBao PuBao Public

    Forked from mgusdn/chatbot

    PuBaO: Psychological Counseling Voiceover System

    TypeScript

  6. LGAimers_Model_Compression LGAimers_Model_Compression Public

    8th LGAimers Model Compression Task. (3rd place)

    Python