Researcher — paper.dinq.me

2026 顶会论文

作者位次 #6/6ICML 2026Poster· Social Aspects / Alignment

Reliability-Aware LLM Alignment from Inconsistent Human Feedback

Jingyi Huang · Ruohan Zong · Yujun Feng · Liran Ma · Lanyu Shang · Yang Zhang

社会与人本对齐与偏好OpenReview

作者位次 #2/3ICML 2026Poster· Social Aspects / Alignment

Conflict-Aware Adaptive Alignment for LLM Hallucination Mitigation

Ruohan Zong · Yang Zhang · Wang

对齐与偏好安全社会与人本OpenReview

作者位次 #6/7SIGIR 2026Oral· Information Retrieval (Full)

Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation

Yifan Liu · Yaokun Liu · Zelin Li · Zhenrui Yue · Ruichen Yao · Yang Zhang · Dong Wang

摘要

Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via sequence-to-sequence modeling. However, these two stages are optimized f...

数据与预训练检索与知识对齐与偏好OpenReview

Yang Zhang

获取完整研究档案

联系方式

2026 顶会论文

Reliability-Aware LLM Alignment from Inconsistent Human Feedback

Conflict-Aware Adaptive Alignment for LLM Hallucination Mitigation

Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation

常见合作者