Xiaoyuan Yi

Venues

Frequent coauthors

Papers

1. Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
   ACL 2026 ·

   Bryan Chen Zhengyu Tan

   DBLP profile ↗ORCID search ↗
2. Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
   ACL 2026 ·

   Shaohua Duan

   DBLP profile ↗ORCID search ↗
3. Generative Personality Simulation via Theory-Informed Structured Interview
   EACL 2026 ·

   Pengda Wang

   DBLP profile ↗ORCID search ↗
4. IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization
   AAAI 2026 ·

   Yuzhuo Bai

   DBLP profile ↗ORCID search ↗
5. Influence-based Online Experience Selection for Effective RLHF
   ACL 2026 ·

   Yifan Gong

   DBLP profile ↗ORCID search ↗
6. MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation
   ACL 2026 ·

   Weihua Zheng

   DBLP profile ↗ORCID search ↗
7. MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions
   AAAI 2026 ·

   Yanxu Zhu

   DBLP profile ↗ORCID search ↗
8. Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts
   ACM MM 2025 ·

   Zhenghao Liu

   DBLP profile ↗ORCID search ↗
9. Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
   NeurIPS 2025 ·

   Hanze Guo

   DBLP profile ↗ORCID search ↗
10. MoVa: Towards Generalizable Classification of Human Morals and Values
    EMNLP 2025 ·

    Ziyu Chen

    DBLP profile ↗ORCID search ↗
11. MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?
    ACL 2025 ·

    Xixian Yong

    DBLP profile ↗ORCID search ↗
12. ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
    NeurIPS 2025 ·

    Pengcheng Huang

    DBLP profile ↗ORCID search ↗
13. Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
    ICML 2025 ·

    Han Jiang

    DBLP profile ↗ORCID search ↗
14. Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models
    ACM MM 2025 ·

    Xingqi Wang

    DBLP profile ↗ORCID search ↗
15. Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and Enhancement
    ACL 2025 ·

    Bingbing Xu

    DBLP profile ↗ORCID search ↗
16. Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights
    ACL 2025 ·

    Sooyung Choi

    DBLP profile ↗ORCID search ↗
17. Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs' Value Evaluation
    ACL 2025 ·

    Jing Yao

    DBLP profile ↗ORCID search ↗
18. CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
    NeurIPS 2024 ·

    Jing Yao

    DBLP profile ↗ORCID search ↗
19. Denevil: towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
    ICLR 2024 ·

    Shitong Duan

    DBLP profile ↗ORCID search ↗
20. Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization
    ACM MM 2024 ·

    Xingqi Wang

    DBLP profile ↗ORCID search ↗
21. Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
    EMNLP 2024 ·

    Shitong Duan

    DBLP profile ↗ORCID search ↗
22. On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
    IJCAI 2024 ·

    Xinpeng Wang

    DBLP profile ↗ORCID search ↗
23. Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value
    NAACL 2024 ·

    Jing Yao

    DBLP profile ↗ORCID search ↗