Alert button
Picture for Xiaoying Zhang

Xiaoying Zhang

Alert button

Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards

Mar 14, 2024
Wei Shen, Xiaoying Zhang, Yuanshun Yao, Rui Zheng, Hongyi Guo, Yang Liu

Viaarxiv icon

Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation

Mar 08, 2024
Xiaoying Zhang, Jean-Francois Ton, Wei Shen, Hongning Wang, Yang Liu

Figure 1 for Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
Figure 2 for Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
Figure 3 for Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
Viaarxiv icon

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation

Feb 14, 2024
Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Lifeng Jin, Linfeng Song, Haitao Mi, Helen Meng

Viaarxiv icon

Human-Instruction-Free LLM Self-Alignment with Limited Samples

Jan 06, 2024
Hongyi Guo, Yuanshun Yao, Wei Shen, Jiaheng Wei, Xiaoying Zhang, Zhaoran Wang, Yang Liu

Viaarxiv icon

Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?

Aug 29, 2023
Jingyan Zhou, Minda Hu, Junan Li, Xiaoying Zhang, Xixin Wu, Irwin King, Helen Meng

Figure 1 for Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
Figure 2 for Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
Figure 3 for Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
Figure 4 for Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
Viaarxiv icon

Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

Aug 10, 2023
Yang Liu, Yuanshun Yao, Jean-Francois Ton, Xiaoying Zhang, Ruocheng Guo Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, Hang Li

Figure 1 for Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Figure 2 for Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Figure 3 for Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Figure 4 for Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Viaarxiv icon

SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting

May 15, 2023
Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, Helen Meng

Figure 1 for SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
Figure 2 for SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
Figure 3 for SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
Figure 4 for SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
Viaarxiv icon

Uncertainty-Aware Off-Policy Learning

Mar 11, 2023
Xiaoying Zhang, Junpu Chen, Hongning Wang, Hong Xie, Hang Li

Figure 1 for Uncertainty-Aware Off-Policy Learning
Figure 2 for Uncertainty-Aware Off-Policy Learning
Figure 3 for Uncertainty-Aware Off-Policy Learning
Figure 4 for Uncertainty-Aware Off-Policy Learning
Viaarxiv icon

Debiasing Recommendation by Learning Identifiable Latent Confounders

Feb 10, 2023
Qing Zhang, Xiaoying Zhang, Yang Liu, Hongning Wang, Min Gao, Jiheng Zhang, Ruocheng Guo

Figure 1 for Debiasing Recommendation by Learning Identifiable Latent Confounders
Figure 2 for Debiasing Recommendation by Learning Identifiable Latent Confounders
Figure 3 for Debiasing Recommendation by Learning Identifiable Latent Confounders
Figure 4 for Debiasing Recommendation by Learning Identifiable Latent Confounders
Viaarxiv icon

Disentangled Representation for Diversified Recommendations

Jan 13, 2023
Xiaoying Zhang, Hongning Wang, Hang Li

Figure 1 for Disentangled Representation for Diversified Recommendations
Figure 2 for Disentangled Representation for Diversified Recommendations
Figure 3 for Disentangled Representation for Diversified Recommendations
Figure 4 for Disentangled Representation for Diversified Recommendations
Viaarxiv icon