Xiaoyuan Yi

Researcher

Publications

View by:

- Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs
  
  JianKui Zhou, Jing Yao, Xiaoyuan Yi, Peng Zhang, Ning Gu, Zhan Hu, Xing Xie, Tun Lu
  
  ICML 2026 | June 2026
  
  Publication
- Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
  
  Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Roy Ka-Wei Lee
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
  
  Xiangxu Zhang, Jiaming Wang, Qinlin Zhao, Hanze Guo, Linzhuo Li, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
  
  Jaehyeok Lee, Xiaoyuan Yi, Jingtao Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie, Jinyeong Bak
  
  March 2026
  
  arXiv | March 2026
  
  Publication
- Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
  
  Zhaowei Zhang, Xiaohan Liu, Xue-Peng Zhu, Junchao Huang, Ceyao Zhang, Zhiyuan Feng, Yaodong Yang, Xiaoyuan Yi, Xing Xie
  
  March 2026
  
  arXiv | March 2026
  
  Publication
- CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization
  
  Jing Yao, Xiaoyuan Yi, Jindong Wang, Zhicheng Dou, Xing Xie
  
  ICML 2026 | March 2026
  
  Publication
- Contextualized Privacy Defense for LLM Agents
  
  Yule Wen, Yanzhe Zhang, Jianxun Lian, Xiaoyuan Yi, Xing Xie, Diyi Yang
  
  March 2026
  
  arXiv | March 2026
  
  Preprint
  
  Publication
- AI Evaluation Should Require Standardized Item-Level Data Releases
  
  Hang Jiang, Susu Zhang, Dongyao Zhu, Yuzhuo Bai, Sang Truong, Xiaoyuan Yi, Sanmi Koyejo, Xing Xie, Ziang Xiao
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- Position: Science of AI Evaluation Requires Item-level Benchmark Data
  
  Hang Jiang, Susu Zhang, Xiaoyuan Yi, Xing Xie, Ziang Xiao
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
  
  Muhua Huang, Qinlin Zhao, Xiaoyuan Yi, Xing Xie
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
  
  Hanze Guo, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
  
  NeurIPS 2025 | October 2025
  
  Publication
- The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
  
  Eoin O’Doherty, Nicole Weinrauch, Andrew Talone, Uri Klempner, Xiaoyuan Yi, Xing Xie, Yi Zeng
  
  September 2025
  
  arXiv | September 2025
  
  Publication
- LegalΔ: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
  
  Xin Dai, Buqiang Xu, Zhenghao Liu, Yukun Yan, Huiyuan Xie, Xiaoyuan Yi, Shuo Wang, Ge Yu
  
  August 2025
  
  arXiv | August 2025
  
  DOI Publication
- PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
  
  Han Jiang, Dongyao Zhu, Zhihua Wei, Xiaoyuan Yi, Ziang Xiao, Xing Xie
  
  ICML 2026 | July 2025
  
  Publication
- AdAEM: An Adaptively and Automated Extensible Measurement of LLMs’ Value Difference
  
  Shitong Duan, Xiaoyuan Yi, Peng Zhang, Dongkuan Xu, Jing Yao, Tun Lu, Ning Gu, Xing Xie
  
  ICLR 2026 | May 2025
  
  DOI Publication
- ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
  
  Pengcheng Huang, Zhenghao Liu, Yukun Yan, Xiaoyuan Yi, Hao Chen, Zhiyuan Liu, Maosong Sun, Tong Xiao, Ge Yu, Chenyan Xiong
  
  NeurIPS 2025 | February 2025
  
  Publication
- CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
  
  Jing Yao, Xiaoyuan Yi, Xing Xie
  
  NeurIPS 2024 | July 2024
  
  DOI Publication Publication
- Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
  
  Han Jiang, Xiaoyuan Yi, Zhihua Wei, Shu Wang, Xing Xie
  
  ICML 2025 | June 2024
  
  DOI Publication Publication
- On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
  
  Xinpeng Wang, Shitong Duan, Xiaoyuan Yi, Jing Yao, Shanlin Zhou, Zhihua Wei, Peng Zhang, Dongkuan Xu, Maosong Sun, Xing Xie
  
  IJCAI 2024 | March 2024
  
  DOI Publication
- Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
  
  Shitong Duan, Xiaoyuan Yi, Peng Zhang, T. Lu, Xing Xie, Ning Gu
  
  ICLR 2024 | October 2023
  
  DOI Publication
- Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation
  
  Jinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun, Xing Xie (xingx)
  
  Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) | July 2022
  
  Publication
- Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora
  
  Changyu Chen, Xiting Wang, Xiaoyuan Yi, Fangzhao Wu, Xing Xie, Rui Yan
  
  ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM SIGKDD) | May 2022
  
  Applied Data Science Track
  
  PDF
- Clickbait Detection via Contrastive Variational Modelling of Text and Label
  
  Xiaoyuan Yi, Jiarui Zhang, Wenhao Li, Xiting Wang, Xing Xie
  
  International Joint Conference on Artificial Intelligence (IJCAI) | March 2022
  
  Publication

- Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs
  
  JianKui Zhou, Jing Yao, Xiaoyuan Yi, Peng Zhang, Ning Gu, Zhan Hu, Xing Xie, Tun Lu
  
  ICML 2026 | June 2026
  
  Publication
- Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
  
  Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Roy Ka-Wei Lee
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
  
  Xiangxu Zhang, Jiaming Wang, Qinlin Zhao, Hanze Guo, Linzhuo Li, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
  
  Zhaowei Zhang, Xiaohan Liu, Xue-Peng Zhu, Junchao Huang, Ceyao Zhang, Zhiyuan Feng, Yaodong Yang, Xiaoyuan Yi, Xing Xie
  
  March 2026
  
  arXiv | March 2026
  
  Publication
- CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization
  
  Jing Yao, Xiaoyuan Yi, Jindong Wang, Zhicheng Dou, Xing Xie
  
  ICML 2026 | March 2026
  
  Publication
- Contextualized Privacy Defense for LLM Agents
  
  Yule Wen, Yanzhe Zhang, Jianxun Lian, Xiaoyuan Yi, Xing Xie, Diyi Yang
  
  March 2026
  
  arXiv | March 2026
  
  Preprint
  
  Publication
- AI Evaluation Should Require Standardized Item-Level Data Releases
  
  Hang Jiang, Susu Zhang, Dongyao Zhu, Yuzhuo Bai, Sang Truong, Xiaoyuan Yi, Sanmi Koyejo, Xing Xie, Ziang Xiao
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- Position: Science of AI Evaluation Requires Item-level Benchmark Data
  
  Hang Jiang, Susu Zhang, Xiaoyuan Yi, Xing Xie, Ziang Xiao
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
  
  Muhua Huang, Qinlin Zhao, Xiaoyuan Yi, Xing Xie
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
  
  Hanze Guo, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
  
  NeurIPS 2025 | October 2025
  
  Publication
- The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
  
  Eoin O’Doherty, Nicole Weinrauch, Andrew Talone, Uri Klempner, Xiaoyuan Yi, Xing Xie, Yi Zeng
  
  September 2025
  
  arXiv | September 2025
  
  Publication
- LegalΔ: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
  
  Xin Dai, Buqiang Xu, Zhenghao Liu, Yukun Yan, Huiyuan Xie, Xiaoyuan Yi, Shuo Wang, Ge Yu
  
  August 2025
  
  arXiv | August 2025
  
  DOI Publication
- PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
  
  Han Jiang, Dongyao Zhu, Zhihua Wei, Xiaoyuan Yi, Ziang Xiao, Xing Xie
  
  ICML 2026 | July 2025
  
  Publication
- AdAEM: An Adaptively and Automated Extensible Measurement of LLMs’ Value Difference
  
  Shitong Duan, Xiaoyuan Yi, Peng Zhang, Dongkuan Xu, Jing Yao, Tun Lu, Ning Gu, Xing Xie
  
  ICLR 2026 | May 2025
  
  DOI Publication
- ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
  
  Pengcheng Huang, Zhenghao Liu, Yukun Yan, Xiaoyuan Yi, Hao Chen, Zhiyuan Liu, Maosong Sun, Tong Xiao, Ge Yu, Chenyan Xiong
  
  NeurIPS 2025 | February 2025
  
  Publication
- CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
  
  Jing Yao, Xiaoyuan Yi, Xing Xie
  
  NeurIPS 2024 | July 2024
  
  DOI Publication Publication
- Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
  
  Han Jiang, Xiaoyuan Yi, Zhihua Wei, Shu Wang, Xing Xie
  
  ICML 2025 | June 2024
  
  DOI Publication Publication
- On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
  
  Xinpeng Wang, Shitong Duan, Xiaoyuan Yi, Jing Yao, Shanlin Zhou, Zhihua Wei, Peng Zhang, Dongkuan Xu, Maosong Sun, Xing Xie
  
  IJCAI 2024 | March 2024
  
  DOI Publication
- Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
  
  Shitong Duan, Xiaoyuan Yi, Peng Zhang, T. Lu, Xing Xie, Ning Gu
  
  ICLR 2024 | October 2023
  
  DOI Publication
- Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora
  
  Changyu Chen, Xiting Wang, Xiaoyuan Yi, Fangzhao Wu, Xing Xie, Rui Yan
  
  ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM SIGKDD) | May 2022
  
  Applied Data Science Track
  
  PDF
- Clickbait Detection via Contrastive Variational Modelling of Text and Label
  
  Xiaoyuan Yi, Jiarui Zhang, Wenhao Li, Xiting Wang, Xing Xie
  
  International Joint Conference on Artificial Intelligence (IJCAI) | March 2022
  
  Publication
- Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
  
  Xiangxu Zhang, Jiaming Wang, Qinlin Zhao, Hanze Guo, Linzhuo Li, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
  
  Jaehyeok Lee, Xiaoyuan Yi, Jingtao Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie, Jinyeong Bak
  
  March 2026
  
  arXiv | March 2026
  
  Publication
- CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization
  
  Jing Yao, Xiaoyuan Yi, Jindong Wang, Zhicheng Dou, Xing Xie
  
  ICML 2026 | March 2026
  
  Publication
- On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
  
  Xinpeng Wang, Shitong Duan, Xiaoyuan Yi, Jing Yao, Shanlin Zhou, Zhihua Wei, Peng Zhang, Dongkuan Xu, Maosong Sun, Xing Xie
  
  IJCAI 2024 | March 2024
  
  DOI Publication
- Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation
  
  Jinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun, Xing Xie (xingx)
  
  Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) | July 2022
  
  Publication
- Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
  
  Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Roy Ka-Wei Lee
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
  
  Han Jiang, Dongyao Zhu, Zhihua Wei, Xiaoyuan Yi, Ziang Xiao, Xing Xie
  
  ICML 2026 | July 2025
  
  Publication
- Position: Science of AI Evaluation Requires Item-level Benchmark Data
  
  Hang Jiang, Susu Zhang, Xiaoyuan Yi, Xing Xie, Ziang Xiao
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- Contextualized Privacy Defense for LLM Agents
  
  Yule Wen, Yanzhe Zhang, Jianxun Lian, Xiaoyuan Yi, Xing Xie, Diyi Yang
  
  March 2026
  
  arXiv | March 2026
  
  Preprint
  
  Publication
- The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
  
  Eoin O’Doherty, Nicole Weinrauch, Andrew Talone, Uri Klempner, Xiaoyuan Yi, Xing Xie, Yi Zeng
  
  September 2025
  
  arXiv | September 2025
  
  Publication

- Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs
  
  JianKui Zhou, Jing Yao, Xiaoyuan Yi, Peng Zhang, Ning Gu, Zhan Hu, Xing Xie, Tun Lu
  
  ICML 2026 | June 2026
  
  Publication
- CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization
  
  Jing Yao, Xiaoyuan Yi, Jindong Wang, Zhicheng Dou, Xing Xie
  
  ICML 2026 | March 2026
  
  Publication
- Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
  
  Hanze Guo, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
  
  NeurIPS 2025 | October 2025
  
  Publication
- PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
  
  Han Jiang, Dongyao Zhu, Zhihua Wei, Xiaoyuan Yi, Ziang Xiao, Xing Xie
  
  ICML 2026 | July 2025
  
  Publication
- AdAEM: An Adaptively and Automated Extensible Measurement of LLMs’ Value Difference
  
  Shitong Duan, Xiaoyuan Yi, Peng Zhang, Dongkuan Xu, Jing Yao, Tun Lu, Ning Gu, Xing Xie
  
  ICLR 2026 | May 2025
  
  DOI Publication
- ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
  
  Pengcheng Huang, Zhenghao Liu, Yukun Yan, Xiaoyuan Yi, Hao Chen, Zhiyuan Liu, Maosong Sun, Tong Xiao, Ge Yu, Chenyan Xiong
  
  NeurIPS 2025 | February 2025
  
  Publication
- CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
  
  Jing Yao, Xiaoyuan Yi, Xing Xie
  
  NeurIPS 2024 | July 2024
  
  DOI Publication Publication
- Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
  
  Han Jiang, Xiaoyuan Yi, Zhihua Wei, Shu Wang, Xing Xie
  
  ICML 2025 | June 2024
  
  DOI Publication Publication
- On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
  
  Xinpeng Wang, Shitong Duan, Xiaoyuan Yi, Jing Yao, Shanlin Zhou, Zhihua Wei, Peng Zhang, Dongkuan Xu, Maosong Sun, Xing Xie
  
  IJCAI 2024 | March 2024
  
  DOI Publication
- Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
  
  Shitong Duan, Xiaoyuan Yi, Peng Zhang, T. Lu, Xing Xie, Ning Gu
  
  ICLR 2024 | October 2023
  
  DOI Publication
- Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation
  
  Jinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun, Xing Xie (xingx)
  
  Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) | July 2022
  
  Publication
- Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora
  
  Changyu Chen, Xiting Wang, Xiaoyuan Yi, Fangzhao Wu, Xing Xie, Rui Yan
  
  ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM SIGKDD) | May 2022
  
  Applied Data Science Track
  
  PDF
- Clickbait Detection via Contrastive Variational Modelling of Text and Label
  
  Xiaoyuan Yi, Jiarui Zhang, Wenhao Li, Xiting Wang, Xing Xie
  
  International Joint Conference on Artificial Intelligence (IJCAI) | March 2022
  
  Publication
- Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
  
  Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Roy Ka-Wei Lee
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
  
  Xiangxu Zhang, Jiaming Wang, Qinlin Zhao, Hanze Guo, Linzhuo Li, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
  
  Jaehyeok Lee, Xiaoyuan Yi, Jingtao Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie, Jinyeong Bak
  
  March 2026
  
  arXiv | March 2026
  
  Publication
- Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
  
  Zhaowei Zhang, Xiaohan Liu, Xue-Peng Zhu, Junchao Huang, Ceyao Zhang, Zhiyuan Feng, Yaodong Yang, Xiaoyuan Yi, Xing Xie
  
  March 2026
  
  arXiv | March 2026
  
  Publication
- Contextualized Privacy Defense for LLM Agents
  
  Yule Wen, Yanzhe Zhang, Jianxun Lian, Xiaoyuan Yi, Xing Xie, Diyi Yang
  
  March 2026
  
  arXiv | March 2026
  
  Preprint
  
  Publication
- AI Evaluation Should Require Standardized Item-Level Data Releases
  
  Hang Jiang, Susu Zhang, Dongyao Zhu, Yuzhuo Bai, Sang Truong, Xiaoyuan Yi, Sanmi Koyejo, Xing Xie, Ziang Xiao
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- Position: Science of AI Evaluation Requires Item-level Benchmark Data
  
  Hang Jiang, Susu Zhang, Xiaoyuan Yi, Xing Xie, Ziang Xiao
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
  
  Muhua Huang, Qinlin Zhao, Xiaoyuan Yi, Xing Xie
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
  
  Eoin O’Doherty, Nicole Weinrauch, Andrew Talone, Uri Klempner, Xiaoyuan Yi, Xing Xie, Yi Zeng
  
  September 2025
  
  arXiv | September 2025
  
  Publication
- LegalΔ: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
  
  Xin Dai, Buqiang Xu, Zhenghao Liu, Yukun Yan, Huiyuan Xie, Xiaoyuan Yi, Shuo Wang, Ge Yu
  
  August 2025
  
  arXiv | August 2025
  
  DOI Publication

Xiaoyuan Yi

Publications

Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization

Contextualized Privacy Defense for LLM Agents

AI Evaluation Should Require Standardized Item-Level Data Releases

Position: Science of AI Evaluation Requires Item-level Benchmark Data

On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models

The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis

LegalΔ: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs’ Value Difference

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models

Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning

Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation

Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora

Clickbait Detection via Contrastive Variational Modelling of Text and Label

Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization

Contextualized Privacy Defense for LLM Agents

AI Evaluation Should Require Standardized Item-Level Data Releases

Position: Science of AI Evaluation Requires Item-level Benchmark Data

On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models

The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis

LegalΔ: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs’ Value Difference

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models

Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning

Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora

Clickbait Detection via Contrastive Variational Modelling of Text and Label

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization

On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models

Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization

Position: Science of AI Evaluation Requires Item-level Benchmark Data

Contextualized Privacy Defense for LLM Agents

The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis

Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs

CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs’ Value Difference

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models

Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning

Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation

Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora

Clickbait Detection via Contrastive Variational Modelling of Text and Label

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

Contextualized Privacy Defense for LLM Agents

AI Evaluation Should Require Standardized Item-Level Data Releases

Position: Science of AI Evaluation Requires Item-level Benchmark Data

On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity

The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis

LegalΔ: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain