CASIA OpenIR

浏览/检索结果: 共21条,第1-10条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
Training Large Language Models to Follow System Prompt with Self-Supervised Fine-Tuning 会议论文
, YOKOHAMA, JAPAN, 2024-07
作者:  Junyan Qiu;  Haitao Wang;  Yiping Yang
Adobe PDF(1596Kb)  |  收藏  |  浏览/下载:5/2  |  提交时间:2024/06/17
large language models  supervised fine-tuning  instruct tuning  stylized generation  
Learning to Deliberate: Multi-Pass Decoding for Document-Grounded Conversations 会议论文
, YOKOHAMA, JAPAN, 2024-07
作者:  Junyan Qiu;  Haitao Wang;  Yiping Yang
Adobe PDF(1033Kb)  |  收藏  |  浏览/下载:8/2  |  提交时间:2024/06/17
dialogue system  document-grounded conversations  deliberation network  sequence-to-sequence framework  
Bridging the Gap between Different Vocabularies for LLM Ensemble 会议论文
, Mexico City, Mexico, June 16–21, 2024
作者:  徐杨一帆;  Lu JL(陆金梁);  Zhang JJ(张家俊)
Adobe PDF(1982Kb)  |  收藏  |  浏览/下载:25/5  |  提交时间:2024/06/13
Stream: social data and knowledge collective intelligence platform for TRaining Ethical AI Models 期刊论文
AI & SOCIETY, 2024, 页码: 1
作者:  Yuwei Wang;  Enmeng Lu;  Zizhe Ruan;  Yao Liang;  Yi Zeng
Adobe PDF(2282Kb)  |  收藏  |  浏览/下载:9/1  |  提交时间:2024/06/11
基于预训练模型的决策序列化建模研究 学位论文
, 2024
作者:  林润基
Adobe PDF(7811Kb)  |  收藏  |  浏览/下载:36/0  |  提交时间:2024/06/07
预训练模型  决策序列化  序列模型  
Token-level Direct Preference Optimization 会议论文
, Vienna, Austria, 2024/7/21-27
作者:  Zeng,Yongcheng;  Liu,Guoqing;  Ma,Weiyu;  Yang,Ning;  Zhang,Haifeng;  Wang,Jun
Adobe PDF(883Kb)  |  收藏  |  浏览/下载:31/10  |  提交时间:2024/06/05
Seq2Set2Seq: A Two-stage Disentangled Method for Reply Keyword Generation in Social Media 期刊论文
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2024, 卷号: 23, 期号: 3, 页码: 20
作者:  Liu, Jie;  Li, Yaguang;  He, Shizhu;  Wu, Shun;  Liu, Kang;  Liu, Shenping;  Wang, Jiong;  Zhang, Qing
收藏  |  浏览/下载:11/0  |  提交时间:2024/05/30
Social media reply  keyword prediction  text generation  multi-label classification  determinantal point processes  
基于序列展开模型的多智能体方法研究 学位论文
, 2024
作者:  Luo ZX(罗正昕)
Adobe PDF(13451Kb)  |  收藏  |  浏览/下载:36/1  |  提交时间:2024/05/30
多智能体  强化学习  序列展开模型  信度分配  非平稳性  
T-Agent: A Term-Aware Agent for Medical Dialogue Generation 会议论文
, Yokohama, Japan, 2024-6-30 - 2023-7-5
作者:  Zefa Hu;  Haozhi Zhao;  Yuanyuan Zhao;  Shuang Xu;  Bo Xu
Adobe PDF(483Kb)  |  收藏  |  浏览/下载:23/5  |  提交时间:2024/05/29
SA-MPF: A Status-Aware Mask Prediction Framework for Online Disease Diagnosis 会议论文
, Yokohama, Japan, 2024-6-30 - 2023-7-5
作者:  Zefa Hu;  Linghui Meng;  Yunlong Zhao;  Yuanyuan Zhao;  Shuang Xu;  Bo Xu
Adobe PDF(307Kb)  |  收藏  |  浏览/下载:27/6  |  提交时间:2024/05/29