Weiyan Shi

Venues

Frequent coauthors

Papers

1. Distilling an End-to-End Voice Assistant Without Instruction Training Data
   ACL 2025 ·

   William Barr Held

   DBLP profile ↗ORCID search ↗
2. LLMs Encode Harmfulness and Refusal Separately
   NeurIPS 2025 ·

   Jiachen Zhao

   DBLP profile ↗ORCID search ↗
3. NewsInterview: a Dataset and a Playground to Evaluate LLMs' Grounding Gap via Informational Interviews
   ACL 2025 ·

   Alexander Spangher

   DBLP profile ↗ORCID search ↗
4. Persuasion for Social Good: How to Build and Break AI
   AAAI 2025 · Weiyan Shi
5. Proactive Conversational Agents with Inner Thoughts
   CHI 2025 ·

   Xingyu Bruce Liu

   DBLP profile ↗ORCID search ↗
6. CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies
   EMNLP 2024 · Weiyan Shi
7. Dialoging Resonance in Human-Chatbot Conversation: How Users Perceive and Reciprocate Recommendation Chatbot's Self-Disclosure Strategy
   CSCW 2024 ·

   Kaihui Liang

   DBLP profile ↗ORCID search ↗
8. How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
   ACL 2024 ·

   Yi Zeng

   DBLP profile ↗ORCID search ↗
9. Position: A Safe Harbor for AI Evaluation and Red Teaming
   ICML 2024 ·

   Shayne Longpre

   DBLP profile ↗ORCID search ↗
10. PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
    NeurIPS 2024 ·

    Yijia Shao

    DBLP profile ↗ORCID search ↗
11. Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future
    ACL 2024 ·

    Minzhi Li

    DBLP profile ↗ORCID search ↗
12. The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
    ACL 2024 ·

    Rongwu Xu

    DBLP profile ↗ORCID search ↗
13. The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes
    CVPR 2024 ·

    Myeongseob Ko

    DBLP profile ↗ORCID search ↗
14. When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels
    NAACL 2024 · Weiyan Shi
15. Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval
    EMNLP 2024 ·

    Kazuaki Furumai

    DBLP profile ↗ORCID search ↗