Xiaoyuan Yi

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment ACL 2026 Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization ACL 2026 Generative Personality Simulation via Theory-Informed Structured Interview EACL 2026 Influence-based Online Experience Selection for Effective RLHF ACL 2026 IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization AAAI 2026 MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation ACL 2026 MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions AAAI 2026 MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models? ACL 2025 MoVa: Towards Generalizable Classification of Human Morals and Values EMNLP 2025 Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing ICML 2025 Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and Enhancement ACL 2025 Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights ACL 2025 Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation ACL 2025 CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models ACL 2024 CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses NeurIPS 2024 DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING ICLR 2024 Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization EMNLP 2024 On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models IJCAI 2024 Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value NAACL 2024 DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation ACL 2023 KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation IJCAI 2023 ToViLaG: Your Visual-Language Generative Model is Also An Evildoer EMNLP 2023 Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization ICLR 2023 Clickbait Detection via Contrastive Variational Modelling of Text and Label IJCAI 2022 Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention EMNLP 2022 Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation NAACL 2022 Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation EMNLP 2022 Self-explaining deep models with logic rule reasoning NeurIPS 2022 Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction NAACL 2021 MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space AAAI 2020 Text Style Transfer via Learning Style Instance Supported Latent Space IJCAI 2020 Jiuge: A Human-Machine Collaborative Chinese Classical Poetry Generation System ACL 2019 Sentiment-Controllable Chinese Poetry Generation IJCAI 2019 Automatic Poetry Generation with Mutual Reinforcement Learning EMNLP 2018 Chinese Poetry Generation with a Salient-Clue Mechanism CoNLL 2018 Chinese Poetry Generation with a Working Memory Model IJCAI 2018 Stylistic Chinese Poetry Generation via Unsupervised Style Disentanglement EMNLP 2018