Haiyang Yu

70 papers A* 11A 1B 1Misc 1Journal 42Unranked 14
YearRankTypeTitle / Venue / Authors
2026 J jnl
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs.
CoRR
Xianya Fang, Feiyang Ren, Xiang Chen, Yu Tian, Zhen Bi, Haiyang Yu, Sheng-Jun Huang
2026 J jnl
ExpSeek: Self-Triggered Experience Seeking for Web Agents.
CoRR
Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, Yongbin Li
2026 J jnl
Your One-Stop Solution for AI-Generated Video Detection.
CoRR
Long Ma, Zihao Xue, Yan Wang, Zhiyuan Yan, Jin Xu, Xiaorui Jiang, Haiyang Yu, Yong Liao, Zhen Bi
2025 J jnl
Adaptive Thinking via Mode Policy Optimization for Social Language Agents.
CoRR
Minzheng Wang, Yongbin Li, Haobo Wang, Xinghua Zhang, Nan Xu, Bingli Wu, Fei Huang, Haiyang Yu, Wenji Mao
2025 — conf
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling.
ACL (Findings)
Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, Yongbin Li
2025 — conf
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking.
ACL (1)
Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, Le Sun
2025 J jnl
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking.
CoRR
Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, Le Sun
2025 A conf
Detecting AI-Generated Video via Frame Consistency.
ICME
Long Ma, Zhiyuan Yan, Qinglang Guo, Yong Liao, Haiyang Yu, Pengyuan Zhou
2025 A* conf
EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models.
EMNLP
Tao Zou, Xinghua Zhang, Haiyang Yu, Minzheng Wang, Fei Huang, Yongbin Li
2025 J jnl
EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models.
CoRR
Tao Zou, Xinghua Zhang, Haiyang Yu, Minzheng Wang, Fei Huang, Yongbin Li
2025 — conf
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization.
ACL (1)
Xinghua Zhang, Haiyang Yu, Cheng Fu, Fei Huang, Yongbin Li
2025 A* conf
On the Role of Attention Heads in Large Language Model Safety.
ICLR
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Kun Wang, Yang Liu, Junfeng Fang, Yongbin Li
2025 J jnl
Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns.
CoRR
Xiang Li, Haiyang Yu, Xinghua Zhang, Ziyang Huang, Shizhu He, Kang Liu, Jun Zhao, Fei Huang, Yongbin Li
2025 A* conf
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization.
ICLR
Zhuoqun Li, Xuanang Chen, Haiyang Yu, Hongyu Lin, Yaojie Lu, Qiaoyu Tang, Fei Huang, Xianpei Han, Le Sun, Yongbin Li
2025 — conf
Transferable Post-training via Inverse Value Learning.
NAACL (Long Papers)
Xinyu Lu, Xueru Wen, Yaojie Lu, Bowen Yu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, Yongbin Li
2024 J jnl
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling.
CoRR
Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, Yongbin Li
2024 J jnl
DeCoF: Generated Video Detection via Frame Consistency.
CoRR
Long Ma, Jiajia Zhang, Hongping Deng, Ningyu Zhang, Yong Liao, Haiyang Yu
2024 J jnl
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement.
CoRR
Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li
2024 — conf
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States.
EMNLP (Findings)
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Yongbin Li
2024 J jnl
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States.
CoRR
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Yongbin Li
2024 J jnl
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization.
CoRR
Xinghua Zhang, Haiyang Yu, Cheng Fu, Fei Huang, Yongbin Li
2024 A* conf
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch.
ICML
Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li
2024 A* conf
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA.
EMNLP
Minzheng Wang, Longze Chen, Fu Cheng, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li
2024 J jnl
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA.
CoRR
Minzheng Wang, Longze Chen, Cheng Fu, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li
2024 J jnl
On the Role of Attention Heads in Large Language Model Safety.
CoRR
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Kun Wang, Yang Liu, Junfeng Fang, Yongbin Li
2024 A* conf
Preference Ranking Optimization for Human Alignment.
AAAI
Feifan Song, Bowen Yu, Minghao Li, Haiyang Yu, Fei Huang, Yongbin Li, Houfeng Wang
2024 — conf
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment.
LREC/COLING
Feifan Song, Bowen Yu, Hao Lang, Haiyang Yu, Fei Huang, Houfeng Wang, Yongbin Li
2024 J jnl
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment.
CoRR
Feifan Song, Bowen Yu, Hao Lang, Haiyang Yu, Fei Huang, Houfeng Wang, Yongbin Li
2024 J jnl
Self-Retrieval: Building an Information Retrieval System with One Large Language Model.
CoRR
Qiaoyu Tang, Jiawei Chen, Bowen Yu, Yaojie Lu, Cheng Fu, Haiyang Yu, Hongyu Lin, Fei Huang, Ben He, Xianpei Han, Le Sun, Yongbin Li
2024 A* conf
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model.
NeurIPS
Qiaoyu Tang, Jiawei Chen, Zhuoqun Li, Bowen Yu, Yaojie Lu, Cheng Fu, Haiyang Yu, Hongyu Lin, Fei Huang, Ben He, Xianpei Han, Le Sun, Yongbin Li
2024 — conf
SoFA: Shielded On-the-fly Alignment via Priority Rule Following.
ACL (Findings)
Xinyu Lu, Bowen Yu, Yaojie Lu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, Yongbin Li
2024 J jnl
SoFA: Shielded On-the-fly Alignment via Priority Rule Following.
CoRR
Xinyu Lu, Bowen Yu, Yaojie Lu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, Yongbin Li
2024 J jnl
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization.
CoRR
Zhuoqun Li, Xuanang Chen, Haiyang Yu, Hongyu Lin, Yaojie Lu, Qiaoyu Tang, Fei Huang, Xianpei Han, Le Sun, Yongbin Li
2024 J jnl
The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends.
CoRR
Xinghua Zhang, Haiyang Yu, Yongbin Li, Minzheng Wang, Longze Chen, Fei Huang
2024 J jnl
Transferable Post-training via Inverse Value Learning.
CoRR
Xinyu Lu, Xueru Wen, Yaojie Lu, Bowen Yu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, Yongbin Li
2024 — conf
Tree-Instruct: A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment.
LREC/COLING
Yingxiu Zhao, Bowen Yu, Binyuan Hui, Haiyang Yu, Minghao Li, Fei Huang, Nevin L. Zhang, Yongbin Li
2023 J jnl
A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment.
CoRR
Yingxiu Zhao, Bowen Yu, Binyuan Hui, Haiyang Yu, Fei Huang, Yongbin Li, Nevin L. Zhang
2023 J jnl
API-Bank: A Benchmark for Tool-Augmented LLMs.
CoRR
Minghao Li, Feifan Song, Bowen Yu, Haiyang Yu, Zhoujun Li, Fei Huang, Yongbin Li
2023 A* conf
API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs.
EMNLP
Minghao Li, Yingxiu Zhao, Bowen Yu, Feifan Song, Hangyu Li, Haiyang Yu, Zhoujun Li, Fei Huang, Yongbin Li
2023 A* conf
Causal Document-Grounded Dialogue Pre-training.
EMNLP
Yingxiu Zhao, Bowen Yu, Bowen Li, Haiyang Yu, Jinyang Li, Chao Wang, Fei Huang, Yongbin Li, Nevin L. Zhang
2023 J jnl
Causal Document-Grounded Dialogue Pre-training.
CoRR
Yingxiu Zhao, Bowen Yu, Haiyang Yu, Bowen Li, Jinyang Li, Chao Wang, Fei Huang, Yongbin Li, Nevin L. Zhang
2023 Misc conf
Coarse-To-Fine Knowledge Selection for Document Grounded Dialogs.
ICASSP
Yeqin Zhang, Haomin Fu, Cheng Fu, Haiyang Yu, Yongbin Li, Cam-Tu Nguyen
2023 J jnl
Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs.
CoRR
Yeqin Zhang, Haomin Fu, Cheng Fu, Haiyang Yu, Yongbin Li, Cam-Tu Nguyen
2023 A* conf
Diversify Question Generation with Retrieval-Augmented Style Transfer.
EMNLP
Qi Gou, Zehua Xia, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li, Cam-Tu Nguyen
2023 J jnl
Diversify Question Generation with Retrieval-Augmented Style Transfer.
CoRR
Qi Gou, Zehua Xia, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li, Cam-Tu Nguyen
2023 — conf
Improving Question Generation with Multi-level Content Planning.
EMNLP (Findings)
Zehua Xia, Qi Gou, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li, Cam-Tu Nguyen
2023 J jnl
Improving Question Generation with Multi-level Content Planning.
CoRR
Zehua Xia, Qi Gou, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li, Cam-Tu Nguyen
2023 J jnl
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch.
CoRR
Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li
2023 J jnl
Preference Ranking Optimization for Human Alignment.
CoRR
Feifan Song, Bowen Yu, Minghao Li, Haiyang Yu, Fei Huang, Yongbin Li, Houfeng Wang
2023 — conf
Unified Language Representation for Question Answering over Text, Tables, and Images.
ACL (Findings)
Bowen Yu, Cheng Fu, Haiyang Yu, Fei Huang, Yongbin Li
2023 J jnl
Unified Language Representation for Question Answering over Text, Tables, and Images.
CoRR
Bowen Yu, Cheng Fu, Haiyang Yu, Fei Huang, Yongbin Li
2023 — conf
Universal Information Extraction with Meta-Pretrained Self-Retrieval.
ACL (Findings)
Xin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, Bin Wang
2023 J jnl
Universal Information Extraction with Meta-Pretrained Self-Retrieval.
CoRR
Xin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, Bin Wang
2023 J jnl
Wider and Deeper LLM Networks are Fairer LLM Evaluators.
CoRR
Xinghua Zhang, Bowen Yu, Haiyang Yu, Yangyu Lv, Tingwen Liu, Fei Huang, Hongbo Xu, Yongbin Li
2022 — conf
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population.
EMNLP (Demos)
Ningyu Zhang, Xin Xu, Liankuan Tao, Haiyang Yu, Hongbin Ye, Shuofei Qiao, Xin Xie, Xiang Chen, Zhoubo Li, Lei Li
2022 J jnl
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population.
CoRR
Ningyu Zhang, Xin Xu, Liankuan Tao, Haiyang Yu, Hongbin Ye, Xin Xie, Xiang Chen, Zhoubo Li, Lei Li, Xiaozhuan Liang, Yunzhi Yao, Shumin Deng, Wen Zhang, Zhenru Zhang, Chuanqi Tan, Fei Huang, Guozhou Zheng, Huajun Chen
2022 — conf
Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots.
EMNLP (Findings)
Haomin Fu, Yeqin Zhang, Haiyang Yu, Jian Sun, Fei Huang, Luo Si, Yongbin Li, Cam-Tu Nguyen
2022 J jnl
Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots.
CoRR
Haomin Fu, Yeqin Zhang, Haiyang Yu, Jian Sun, Fei Huang, Luo Si, Yongbin Li, Cam-Tu Nguyen
2022 A* conf
Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration.
ACM Multimedia
Zhenyu Zhang, Bowen Yu, Haiyang Yu, Tingwen Liu, Cheng Fu, Jingyang Li, Chengguang Tang, Jian Sun, Yongbin Li
2022 J jnl
Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration.
CoRR
Zhenyu Zhang, Bowen Yu, Haiyang Yu, Tingwen Liu, Cheng Fu, Jingyang Li, Chengguang Tang, Jian Sun, Yongbin Li
2022 J jnl
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue.
CoRR
Yingxiu Zhao, Yinhe Zheng, Zhiliang Tian, Chang Gao, Bowen Yu, Haiyang Yu, Yongbin Li, Jian Sun, Nevin L. Zhang
2022 J jnl
Semi-Supervised Lifelong Language Learning.
CoRR
Yingxiu Zhao, Yinhe Zheng, Bowen Yu, Zhiliang Tian, Dongkyu Lee, Jian Sun, Haiyang Yu, Yongbin Li, Nevin L. Zhang
2022 J jnl
Towards Generalized Open Information Extraction.
CoRR
Bowen Yu, Zhenyu Zhang, Jingyang Li, Haiyang Yu, Tingwen Liu, Jian Sun, Yongbin Li, Bin Wang
2021 J jnl
Interventional Aspect-Based Sentiment Analysis.
CoRR
Zhen Bi, Ningyu Zhang, Ganqiang Ye, Haiyang Yu, Xi Chen, Huajun Chen
2020 J jnl
A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges.
CoRR
Bin Fu, Yunqi Qiu, Chengguang Tang, Yang Li, Haiyang Yu, Jian Sun
2020 B conf
Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction.
COLING
Haiyang Yu, Ningyu Zhang, Shumin Deng, Hongbin Ye, Wei Zhang, Huajun Chen
2020 J jnl
Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction.
CoRR
Haiyang Yu, Ningyu Zhang, Shumin Deng, Hongbin Ye, Wei Zhang, Huajun Chen
2020 J jnl
Can Fine-tuning Pre-trained Models Lead to Perfect NLP? A Study of the Generalizability of Relation Extraction.
CoRR
Ningyu Zhang, Luoqiu Li, Shumin Deng, Haiyang Yu, Xu Cheng, Wei Zhang, Huajun Chen
2020 — conf
OpenUE: An Open Toolkit of Universal Extraction from Text.
EMNLP (Demos)
Ningyu Zhang, Shumin Deng, Zhen Bi, Haiyang Yu, Jiacheng Yang, Mosha Chen, Fei Huang, Wei Zhang, Huajun Chen
2020 J jnl
The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis.
CoRR
Haiyang Yu, Ningyu Zhang, Shumin Deng, Zonggang Yuan, Yantao Jia, Huajun Chen