Skip to content
View pillowsofwind's full-sized avatar
🎯
Focusing
🎯
Focusing
55 followers · 30 following

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Block or report pillowsofwind

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
pillowsofwind/README.md

Hello World! I am Rongwu Xu (许融武) 👋

🤖 I am currently a Master's student focus on various topics regarding NLP and AI. I am particularly interested in naturally arised Safety and Alignment Problems in NLP Systems. Besides, I study evaluation and application of NLP technologies.

🤗 Always Seeking Collaborators: If you are interested in my work (refer to rongwuxu.com) or see potential for collaboration, please do not hesitate to contact me via this Email!

Pinned Loading

  1. llms-believe-the-earth-is-flat llms-believe-the-earth-is-flat Public

    [ACL 2024] The official GitHub repo for the paper "The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation"

    Python 76 5

  2. Knowledge-Conflicts-Survey Knowledge-Conflicts-Survey Public

    [EMNLP 2024] The official GitHub repo for the survey paper "Knowledge Conflicts for LLMs: A Survey"

    107 5

  3. LLM-CBRN-Risks LLM-CBRN-Risks Public

    The official GitHub repo for the paper ""Nuclear Deployed!": Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents"

    Python 13

  4. CoT-Attack CoT-Attack Public

    [ACL 2024 Findings] The official GitHub repo for the paper "Preemptive Answer" Attacks" on Chain-of-Thought Reasoning"

    Python 3

  5. Course-Correction Course-Correction Public

    [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"

    Python 19 1

  6. DebateQA DebateQA Public

    The official GitHub repo for the paper "DebateQA: Evaluating Question Answering on Debatable Knowledge"

    Python 9