CN117236410B - 一种可信的电子文件大语言模型训练、推理方法和装置 - Google Patents
一种可信的电子文件大语言模型训练、推理方法和装置 Download PDFInfo
- Publication number
- CN117236410B CN117236410B CN202311500582.5A CN202311500582A CN117236410B CN 117236410 B CN117236410 B CN 117236410B CN 202311500582 A CN202311500582 A CN 202311500582A CN 117236410 B CN117236410 B CN 117236410B
- Authority
- CN
- China
- Prior art keywords
- trusted
- language model
- training
- evaluation index
- sample data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012549 training Methods 0.000 title claims abstract description 181
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000011156 evaluation Methods 0.000 claims abstract description 111
- 238000010276 construction Methods 0.000 claims description 27
- 230000002787 reinforcement Effects 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 16
- 238000009825 accumulation Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000003860 storage Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000004547 Hallucinations Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Machine Translation (AREA)
Abstract
Description
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311500582.5A CN117236410B (zh) | 2023-11-13 | 2023-11-13 | 一种可信的电子文件大语言模型训练、推理方法和装置 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311500582.5A CN117236410B (zh) | 2023-11-13 | 2023-11-13 | 一种可信的电子文件大语言模型训练、推理方法和装置 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117236410A CN117236410A (zh) | 2023-12-15 |
CN117236410B true CN117236410B (zh) | 2024-01-23 |
Family
ID=89086498
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311500582.5A Active CN117236410B (zh) | 2023-11-13 | 2023-11-13 | 一种可信的电子文件大语言模型训练、推理方法和装置 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117236410B (zh) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117910449A (zh) * | 2024-01-19 | 2024-04-19 | 上海算法创新研究院 | 一种基于引证校正的大语言模型幻觉缓解方案 |
CN117852616B (zh) * | 2024-02-29 | 2024-05-31 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | 基于增强拒绝采样训练的大语言模型对齐微调方法和系统 |
CN118094105A (zh) * | 2024-03-25 | 2024-05-28 | 广州探域科技有限公司 | 基于动态信息的模型增量微调方法、系统、设备及介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116127020A (zh) * | 2023-03-03 | 2023-05-16 | 北京百度网讯科技有限公司 | 生成式大语言模型训练方法以及基于模型的搜索方法 |
CN116226334A (zh) * | 2023-03-03 | 2023-06-06 | 北京百度网讯科技有限公司 | 生成式大语言模型训练方法以及基于模型的搜索方法 |
CN116244416A (zh) * | 2023-03-03 | 2023-06-09 | 北京百度网讯科技有限公司 | 生成式大语言模型训练方法、基于模型的人机语音交互方法 |
CN116564330A (zh) * | 2023-05-24 | 2023-08-08 | 思必驰科技股份有限公司 | 弱监督语音预训练方法、电子设备和存储介质 |
CN116611110A (zh) * | 2023-05-31 | 2023-08-18 | 山东浪潮科学研究院有限公司 | 一种数据隐私脱敏方法、装置、设备及存储介质 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11593556B2 (en) * | 2020-05-26 | 2023-02-28 | Mastercard International Incorporated | Methods and systems for generating domain-specific text summarizations |
-
2023
- 2023-11-13 CN CN202311500582.5A patent/CN117236410B/zh active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116127020A (zh) * | 2023-03-03 | 2023-05-16 | 北京百度网讯科技有限公司 | 生成式大语言模型训练方法以及基于模型的搜索方法 |
CN116226334A (zh) * | 2023-03-03 | 2023-06-06 | 北京百度网讯科技有限公司 | 生成式大语言模型训练方法以及基于模型的搜索方法 |
CN116244416A (zh) * | 2023-03-03 | 2023-06-09 | 北京百度网讯科技有限公司 | 生成式大语言模型训练方法、基于模型的人机语音交互方法 |
CN116564330A (zh) * | 2023-05-24 | 2023-08-08 | 思必驰科技股份有限公司 | 弱监督语音预训练方法、电子设备和存储介质 |
CN116611110A (zh) * | 2023-05-31 | 2023-08-18 | 山东浪潮科学研究院有限公司 | 一种数据隐私脱敏方法、装置、设备及存储介质 |
Non-Patent Citations (1)
Title |
---|
语言结构词性流量的冲量过程;徐;熊健;范金宇;;数理统计与管理(第04期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117236410A (zh) | 2023-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111368996B (zh) | 可传递自然语言表示的重新训练投影网络 | |
CN117236410B (zh) | 一种可信的电子文件大语言模型训练、推理方法和装置 | |
CN112131350B (zh) | 文本标签确定方法、装置、终端及可读存储介质 | |
CN112069302B (zh) | 会话意图识别模型的训练方法、会话意图识别方法及装置 | |
CN109376222B (zh) | 问答匹配度计算方法、问答自动匹配方法及装置 | |
AU2022269916A1 (en) | Systems and methods for active curriculum learning | |
CN113704393A (zh) | 关键词提取方法、装置、设备及介质 | |
KR20230117716A (ko) | 검색어 추천 장치, 방법 및 기록매체 | |
CN117494815A (zh) | 面向档案的可信大语言模型训练、推理方法和装置 | |
CN112989024B (zh) | 文本内容的关系提取方法、装置、设备及存储介质 | |
CN117609444B (zh) | 一种基于大模型的搜索问答方法 | |
US20220198149A1 (en) | Method and system for machine reading comprehension | |
CN111507108B (zh) | 别名生成方法、装置、电子设备及计算机可读存储介质 | |
Bachrach et al. | An attention mechanism for neural answer selection using a combined global and local view | |
CN111666375A (zh) | 文本相似度的匹配方法、电子设备和计算机可读介质 | |
CN116186220A (zh) | 信息检索方法、问答处理方法、信息检索装置及系统 | |
Kandi | Language Modelling for Handling Out-of-Vocabulary Words in Natural Language Processing | |
CN115455152A (zh) | 写作素材的推荐方法、装置、电子设备及存储介质 | |
CN111444338A (zh) | 文本处理、装置、存储介质及设备 | |
CN118228718B (zh) | 编码器处理方法、文本处理方法及相关设备 | |
CN110929527B (zh) | 一种确定语义相似度方法及装置 | |
CN118171648B (zh) | 文本提取方法、装置、电子设备及存储介质 | |
CN117521674B (zh) | 对抗信息的生成方法、装置、计算机设备和存储介质 | |
Ziolkowski | Vox populism: Analysis of the anti-elite content of presidential candidates’ speeches | |
US20240144049A1 (en) | Computerized question answering based on evidence chains |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CB03 | Change of inventor or designer information |
Inventor after: Qian Minghui Inventor after: Yang Guancan Inventor after: Gou Jiajie Inventor after: Sun Ke Inventor after: Yang Jianliang Inventor after: Pan Fei Inventor after: Ju Xiang Inventor after: Li Hurong Inventor after: Kuang Fu Inventor after: Xu Jiayuan Inventor after: Xu Zhixuan Inventor after: Fan Anyi Inventor before: Qian Minghui Inventor before: Yang Guancan Inventor before: Gou Jiajie Inventor before: Sun Ke Inventor before: Yang Jianliang Inventor before: Pan Fei Inventor before: Ju Xiang Inventor before: Li Hurong Inventor before: Kuang Fu Inventor before: Xu Jiayuan Inventor before: Xu Zhixuan Inventor before: Fan Anyi |
|
CB03 | Change of inventor or designer information |