影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
52.8/100
前 7.2%
全站排名 #4,626
发表论文13 篇
平均评分
年均产出4.3 篇/年
Xiaoyuan Yi
研究方向
Responsible AI · value alignment · LLM evaluation · text generation · poetry generation · natural language processing · natural language generation
20
AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference
ICLR 2026Oral
三作22
CAReDiO: Enhancing Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization
ICLR 2026Rejected
二作21
PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization
ICLR 2026Rejected
三作30
MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally Grounded Evaluation
ICLR 2026Withdrawn
9
Beyond BFI: The CSI for Enhanced Reliability and Validity in Evaluating LLM Personality Traits
ICLR 2026Rejected
三作27
Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
NeurIPS 2025Poster
29
ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
NeurIPS 2025Poster
17
Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
ICML 2025Poster
二作40
Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
ICLR 2025Rejected
二作19
Why Do You Answer Like That? Psychological Analysis on Underlying Connections between LLM's Values and Safety Risks
ICLR 2025Rejected
二作14
Leveraging Implicit Sentiments: Enhancing Reliability and Validity in Psychological Trait Evaluation of LLMs
ICLR 2025Rejected
三作16
Elephant in the Room: Unveiling the Pitfalls of Human Proxies in Alignment
ICLR 2025Rejected
二作