Framing Few Shot Knowledge Graph Completion with Large Language Models

MODUL Technology GmbH
MODUL Technology GmbHInnovation in Data and Media Extraction, Annotation and Analysis en MODUL Technology GmbH
FRAMING FEW-SHOT
KNOWLEDGE GRAPH
COMPLETION WITH LARGE
LANGUAGE MODELS
Adrian M.P. Brașoveanu
Lyndon J.B. Nixon
Albert Weichselbraun
Arno Scharl
NLP4KGC@SEMANTICS 2023
LLMs 2020-2023
LARGE LANGUAGE MODELS
Generative AI
ChatGPT 3.5/4.0
Claude 2
Cohere Chat
Falcon
LLaMa2
Flan-T5
Core Innovation:
Ecosystems
Agents
LangChain
KGs
Tools
Problem Solving
Mixture of
Experts (MoE)?
Image Copyright © Language Models are Few-Shot Learners (2020) by Tom
B. Brown et al. NeurIPS 2020.
LLM Reasoning Strategies(1): CoT
LARGE LANGUAGE MODELS
Relation
Extraction with
CoT
Explanation is All
You Need!
Step-by-step
reasoning
Augmented Text
leads to better
results!
Image Copyright © Revisiting Relation Extraction in the era of Large Language
Models by Wadhwa et al. ACL(1) 2023.
LLM Reasoning Strategies (2): ToT
LARGE LANGUAGE MODELS
CoT contains
explanations
ToT extends CoT
Multiple paths
towards an answer
CoT-SC – Majority
voting mechanism
ToT – more similar
to the human
selection process
ToT allows for
parallel exploration
of ideas as
opposed to linear
exploration (CoT).
Image Copyright © Tree of Thoughts: Deliberate Problem Solving with Large
Language Models (2023) by Yao et al.
Knowledge Graphs (KG)
LARGE LANGUAGE MODELS
Sustainability
KG
Built with Wikidata.
Missing relations:
- country-specific
- region-specific
KG Completion
(KGC)
Can we fill the
missing relations
using LLMs?
Evaluating Large Language Models
LARGE LANGUAGE MODELS
Single interface
nat.dev/chat
Includes
ChatGPT3.5/4
(with 32k cw)
Claude1/2
(with 100k cw)
Cohere Chat
MPT30B
Falcon40B
LLaMa2
Functionality
Playground
Compare
Chat
Metrics
Evaluating Large Language Models
LARGE LANGUAGE MODELS
Relations
Only Relations
Explanations
CoT
Completions
Restricted CoT
Self-Scoring
Truthfulness Proxy
Evaluating Large Language Models
LARGE LANGUAGE MODELS
Tools
GPT-3.5
GPT-4.0
Claude2
MPT-30B
Few-Shot
Input: 12-14
annotated texts
Output: 50
annotated texts
We want all the
texts annotated in
a large batch if
possible
Evaluating Large Language Models
LARGE LANGUAGE MODELS
Taxonomy of
Errors
These are only the
most frequent
errors!
And the Winner
Is?
ChatGPT and
Claude2 have
similar
performance
Conclusion?
LARGE LANGUAGE MODELS
Self-Scoring
Consecutive runs
Huge differences
And the Winner
Is?
ChatGPT and
Claude2 have
similar
performance
Acknowledgments
PROJECTS
DWBI Vienna - Vienna Science and Technology Fund (WWTF) [10.47379/ICT20096]
SDG-HUB – FFG (GA No. 892212)
CONTACT
adrian.brasoveanu@modul.ac.at
THANK YOU!
1 de 11

Recomendados

ijeter35852020.pdf por
ijeter35852020.pdfijeter35852020.pdf
ijeter35852020.pdfSatishBhalshankar
7 vistas7 diapositivas
Landscape of AI/ML in 2023 por
Landscape of AI/ML in 2023Landscape of AI/ML in 2023
Landscape of AI/ML in 2023HyunJoon Jung
2.4K vistas67 diapositivas
1808.10245v1 (1).pdf por
1808.10245v1 (1).pdf1808.10245v1 (1).pdf
1808.10245v1 (1).pdfKSHITIJCHAUDHARY20
60 vistas6 diapositivas
How to supervise a thesis in NLP in the ChatGPT era? By Laure Soulier por
How to supervise a thesis in NLP in the ChatGPT era? By Laure SoulierHow to supervise a thesis in NLP in the ChatGPT era? By Laure Soulier
How to supervise a thesis in NLP in the ChatGPT era? By Laure SoulierParis Women in Machine Learning and Data Science
22 vistas25 diapositivas
Natural language processing and transformer models por
Natural language processing and transformer modelsNatural language processing and transformer models
Natural language processing and transformer modelsDing Li
658 vistas31 diapositivas
ICAME 2010 por
ICAME 2010ICAME 2010
ICAME 2010nottyknight
304 vistas27 diapositivas

Más contenido relacionado

Similar a Framing Few Shot Knowledge Graph Completion with Large Language Models

A Deep Learning Model to Predict Congressional Roll Call Votes from Legislati... por
A Deep Learning Model to Predict Congressional Roll Call Votes from Legislati...A Deep Learning Model to Predict Congressional Roll Call Votes from Legislati...
A Deep Learning Model to Predict Congressional Roll Call Votes from Legislati...mlaij
12 vistas13 diapositivas
Analysis of the evolution of advanced transformer-based language models: Expe... por
Analysis of the evolution of advanced transformer-based language models: Expe...Analysis of the evolution of advanced transformer-based language models: Expe...
Analysis of the evolution of advanced transformer-based language models: Expe...IAESIJAI
8 vistas16 diapositivas
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR... por
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...mathsjournal
5 vistas10 diapositivas
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR... por
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...mathsjournal
5 vistas10 diapositivas
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015 por
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015RIILP
231 vistas21 diapositivas
BERT Explained_ State of the art language model for NLP.pdf por
BERT Explained_ State of the art language model for NLP.pdfBERT Explained_ State of the art language model for NLP.pdf
BERT Explained_ State of the art language model for NLP.pdfsudeshnakundu10
11 vistas13 diapositivas

Similar a Framing Few Shot Knowledge Graph Completion with Large Language Models(20)

A Deep Learning Model to Predict Congressional Roll Call Votes from Legislati... por mlaij
A Deep Learning Model to Predict Congressional Roll Call Votes from Legislati...A Deep Learning Model to Predict Congressional Roll Call Votes from Legislati...
A Deep Learning Model to Predict Congressional Roll Call Votes from Legislati...
mlaij12 vistas
Analysis of the evolution of advanced transformer-based language models: Expe... por IAESIJAI
Analysis of the evolution of advanced transformer-based language models: Expe...Analysis of the evolution of advanced transformer-based language models: Expe...
Analysis of the evolution of advanced transformer-based language models: Expe...
IAESIJAI8 vistas
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR... por mathsjournal
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...
mathsjournal5 vistas
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR... por mathsjournal
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...
OPTIMIZING SIMILARITY THRESHOLD FOR ABSTRACT SIMILARITY METRIC IN SPEECH DIAR...
mathsjournal5 vistas
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015 por RIILP
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
RIILP231 vistas
BERT Explained_ State of the art language model for NLP.pdf por sudeshnakundu10
BERT Explained_ State of the art language model for NLP.pdfBERT Explained_ State of the art language model for NLP.pdf
BERT Explained_ State of the art language model for NLP.pdf
sudeshnakundu1011 vistas
Topicmodels por Ajay Ohri
TopicmodelsTopicmodels
Topicmodels
Ajay Ohri2.8K vistas
Fine grained irony classification through transfer learning approach por CSITiaesprime
Fine grained irony classification through transfer learning approachFine grained irony classification through transfer learning approach
Fine grained irony classification through transfer learning approach
CSITiaesprime2 vistas
Language Models for Information Retrieval por Dustin Smith
Language Models for Information RetrievalLanguage Models for Information Retrieval
Language Models for Information Retrieval
Dustin Smith3.2K vistas
Deep Learning | Speaker Indentification por Sai Kiran Kadam
Deep Learning | Speaker IndentificationDeep Learning | Speaker Indentification
Deep Learning | Speaker Indentification
Sai Kiran Kadam43 vistas
AUTOMATIC DETECTION AND LANGUAGE IDENTIFICATION OF MULTILINGUAL DOCUMENTS por IRJET Journal
AUTOMATIC DETECTION AND LANGUAGE IDENTIFICATION OF MULTILINGUAL DOCUMENTSAUTOMATIC DETECTION AND LANGUAGE IDENTIFICATION OF MULTILINGUAL DOCUMENTS
AUTOMATIC DETECTION AND LANGUAGE IDENTIFICATION OF MULTILINGUAL DOCUMENTS
IRJET Journal9 vistas
2010 INTERSPEECH por WarNik Chow
2010 INTERSPEECH 2010 INTERSPEECH
2010 INTERSPEECH
WarNik Chow75 vistas
Texts Classification with the usage of Neural Network based on the Word2vec’s... por ijsc
Texts Classification with the usage of Neural Network based on the Word2vec’s...Texts Classification with the usage of Neural Network based on the Word2vec’s...
Texts Classification with the usage of Neural Network based on the Word2vec’s...
ijsc6 vistas
Natural Language Processing - Research and Application Trends por Shreyas Suresh Rao
Natural Language Processing - Research and Application TrendsNatural Language Processing - Research and Application Trends
Natural Language Processing - Research and Application Trends
Shreyas Suresh Rao74 vistas
Artificial intelligence markup language: a Brief tutorial por ijcses
Artificial intelligence markup language: a Brief tutorialArtificial intelligence markup language: a Brief tutorial
Artificial intelligence markup language: a Brief tutorial
ijcses6.2K vistas
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE por ijmpict
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE
VIDEO OBJECTS DESCRIPTION IN HINDI TEXT LANGUAGE
ijmpict152 vistas

Más de MODUL Technology GmbH

Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Cl... por
Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Cl...Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Cl...
Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Cl...MODUL Technology GmbH
98 vistas12 diapositivas
Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forec... por
Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forec...Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forec...
Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forec...MODUL Technology GmbH
9 vistas11 diapositivas
New Opportunities for Understanding Tourist Photography.pptx por
New Opportunities for Understanding Tourist Photography.pptxNew Opportunities for Understanding Tourist Photography.pptx
New Opportunities for Understanding Tourist Photography.pptxMODUL Technology GmbH
42 vistas13 diapositivas
How do destinations relate to one another? A study of visual destination bran... por
How do destinations relate to one another? A study of visual destination bran...How do destinations relate to one another? A study of visual destination bran...
How do destinations relate to one another? A study of visual destination bran...MODUL Technology GmbH
19 vistas10 diapositivas
Do DMOs promote the right aspects of the destination? A study of Instagram ph... por
Do DMOs promote the right aspects of the destination? A study of Instagram ph...Do DMOs promote the right aspects of the destination? A study of Instagram ph...
Do DMOs promote the right aspects of the destination? A study of Instagram ph...MODUL Technology GmbH
198 vistas30 diapositivas
The Impact of Social Media on perceived Destination Image: case of Mexico Ci... por
The Impact of Social Media on perceived Destination Image:  case of Mexico Ci...The Impact of Social Media on perceived Destination Image:  case of Mexico Ci...
The Impact of Social Media on perceived Destination Image: case of Mexico Ci...MODUL Technology GmbH
321 vistas16 diapositivas

Más de MODUL Technology GmbH(20)

Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Cl... por MODUL Technology GmbH
Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Cl...Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Cl...
Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Cl...
Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forec... por MODUL Technology GmbH
Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forec...Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forec...
Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forec...
New Opportunities for Understanding Tourist Photography.pptx por MODUL Technology GmbH
New Opportunities for Understanding Tourist Photography.pptxNew Opportunities for Understanding Tourist Photography.pptx
New Opportunities for Understanding Tourist Photography.pptx
How do destinations relate to one another? A study of visual destination bran... por MODUL Technology GmbH
How do destinations relate to one another? A study of visual destination bran...How do destinations relate to one another? A study of visual destination bran...
How do destinations relate to one another? A study of visual destination bran...
Do DMOs promote the right aspects of the destination? A study of Instagram ph... por MODUL Technology GmbH
Do DMOs promote the right aspects of the destination? A study of Instagram ph...Do DMOs promote the right aspects of the destination? A study of Instagram ph...
Do DMOs promote the right aspects of the destination? A study of Instagram ph...
The Impact of Social Media on perceived Destination Image: case of Mexico Ci... por MODUL Technology GmbH
The Impact of Social Media on perceived Destination Image:  case of Mexico Ci...The Impact of Social Media on perceived Destination Image:  case of Mexico Ci...
The Impact of Social Media on perceived Destination Image: case of Mexico Ci...
The Impact of Social Media on perceived Destination Image: the case of Mexico... por MODUL Technology GmbH
The Impact of Social Media on perceived Destination Image:the case of Mexico...The Impact of Social Media on perceived Destination Image:the case of Mexico...
The Impact of Social Media on perceived Destination Image: the case of Mexico...
How Instagram influences Visual Destination Image - a case study of Jordan an... por MODUL Technology GmbH
How Instagram influences Visual Destination Image - a case study of Jordan an...How Instagram influences Visual Destination Image - a case study of Jordan an...
How Instagram influences Visual Destination Image - a case study of Jordan an...
14 no tube dissemination and showcases [compatibility mode] por MODUL Technology GmbH
14 no tube dissemination and showcases [compatibility mode]14 no tube dissemination and showcases [compatibility mode]
14 no tube dissemination and showcases [compatibility mode]

Último

The Power of Heat Decarbonisation Plans in the Built Environment por
The Power of Heat Decarbonisation Plans in the Built EnvironmentThe Power of Heat Decarbonisation Plans in the Built Environment
The Power of Heat Decarbonisation Plans in the Built EnvironmentIES VE
84 vistas20 diapositivas
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f... por
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...TrustArc
176 vistas29 diapositivas
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue por
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlueCloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlueShapeBlue
137 vistas13 diapositivas
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue por
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlueShapeBlue
152 vistas23 diapositivas
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023 por
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023Redefining the book supply chain: A glimpse into the future - Tech Forum 2023
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023BookNet Canada
44 vistas19 diapositivas
The Role of Patterns in the Era of Large Language Models por
The Role of Patterns in the Era of Large Language ModelsThe Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language ModelsYunyao Li
91 vistas65 diapositivas

Último(20)

The Power of Heat Decarbonisation Plans in the Built Environment por IES VE
The Power of Heat Decarbonisation Plans in the Built EnvironmentThe Power of Heat Decarbonisation Plans in the Built Environment
The Power of Heat Decarbonisation Plans in the Built Environment
IES VE84 vistas
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f... por TrustArc
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc176 vistas
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue por ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlueCloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
ShapeBlue137 vistas
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue por ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
ShapeBlue152 vistas
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023 por BookNet Canada
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023Redefining the book supply chain: A glimpse into the future - Tech Forum 2023
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023
BookNet Canada44 vistas
The Role of Patterns in the Era of Large Language Models por Yunyao Li
The Role of Patterns in the Era of Large Language ModelsThe Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language Models
Yunyao Li91 vistas
Future of AR - Facebook Presentation por Rob McCarty
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
Rob McCarty65 vistas
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit... por ShapeBlue
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
ShapeBlue162 vistas
Digital Personal Data Protection (DPDP) Practical Approach For CISOs por Priyanka Aash
Digital Personal Data Protection (DPDP) Practical Approach For CISOsDigital Personal Data Protection (DPDP) Practical Approach For CISOs
Digital Personal Data Protection (DPDP) Practical Approach For CISOs
Priyanka Aash162 vistas
"Package management in monorepos", Zoltan Kochan por Fwdays
"Package management in monorepos", Zoltan Kochan"Package management in monorepos", Zoltan Kochan
"Package management in monorepos", Zoltan Kochan
Fwdays34 vistas
"Running students' code in isolation. The hard way", Yurii Holiuk por Fwdays
"Running students' code in isolation. The hard way", Yurii Holiuk "Running students' code in isolation. The hard way", Yurii Holiuk
"Running students' code in isolation. The hard way", Yurii Holiuk
Fwdays36 vistas
State of the Union - Rohit Yadav - Apache CloudStack por ShapeBlue
State of the Union - Rohit Yadav - Apache CloudStackState of the Union - Rohit Yadav - Apache CloudStack
State of the Union - Rohit Yadav - Apache CloudStack
ShapeBlue303 vistas
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading... por The Digital Insurer
Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading...
Transcript: Redefining the book supply chain: A glimpse into the future - Tec... por BookNet Canada
Transcript: Redefining the book supply chain: A glimpse into the future - Tec...Transcript: Redefining the book supply chain: A glimpse into the future - Tec...
Transcript: Redefining the book supply chain: A glimpse into the future - Tec...
BookNet Canada41 vistas
"Surviving highload with Node.js", Andrii Shumada por Fwdays
"Surviving highload with Node.js", Andrii Shumada "Surviving highload with Node.js", Andrii Shumada
"Surviving highload with Node.js", Andrii Shumada
Fwdays58 vistas
VNF Integration and Support in CloudStack - Wei Zhou - ShapeBlue por ShapeBlue
VNF Integration and Support in CloudStack - Wei Zhou - ShapeBlueVNF Integration and Support in CloudStack - Wei Zhou - ShapeBlue
VNF Integration and Support in CloudStack - Wei Zhou - ShapeBlue
ShapeBlue207 vistas
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT por ShapeBlue
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITUpdates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
ShapeBlue208 vistas
"Node.js Development in 2024: trends and tools", Nikita Galkin por Fwdays
"Node.js Development in 2024: trends and tools", Nikita Galkin "Node.js Development in 2024: trends and tools", Nikita Galkin
"Node.js Development in 2024: trends and tools", Nikita Galkin
Fwdays33 vistas

Framing Few Shot Knowledge Graph Completion with Large Language Models

  • 1. FRAMING FEW-SHOT KNOWLEDGE GRAPH COMPLETION WITH LARGE LANGUAGE MODELS Adrian M.P. Brașoveanu Lyndon J.B. Nixon Albert Weichselbraun Arno Scharl NLP4KGC@SEMANTICS 2023
  • 2. LLMs 2020-2023 LARGE LANGUAGE MODELS Generative AI ChatGPT 3.5/4.0 Claude 2 Cohere Chat Falcon LLaMa2 Flan-T5 Core Innovation: Ecosystems Agents LangChain KGs Tools Problem Solving Mixture of Experts (MoE)? Image Copyright © Language Models are Few-Shot Learners (2020) by Tom B. Brown et al. NeurIPS 2020.
  • 3. LLM Reasoning Strategies(1): CoT LARGE LANGUAGE MODELS Relation Extraction with CoT Explanation is All You Need! Step-by-step reasoning Augmented Text leads to better results! Image Copyright © Revisiting Relation Extraction in the era of Large Language Models by Wadhwa et al. ACL(1) 2023.
  • 4. LLM Reasoning Strategies (2): ToT LARGE LANGUAGE MODELS CoT contains explanations ToT extends CoT Multiple paths towards an answer CoT-SC – Majority voting mechanism ToT – more similar to the human selection process ToT allows for parallel exploration of ideas as opposed to linear exploration (CoT). Image Copyright © Tree of Thoughts: Deliberate Problem Solving with Large Language Models (2023) by Yao et al.
  • 5. Knowledge Graphs (KG) LARGE LANGUAGE MODELS Sustainability KG Built with Wikidata. Missing relations: - country-specific - region-specific KG Completion (KGC) Can we fill the missing relations using LLMs?
  • 6. Evaluating Large Language Models LARGE LANGUAGE MODELS Single interface nat.dev/chat Includes ChatGPT3.5/4 (with 32k cw) Claude1/2 (with 100k cw) Cohere Chat MPT30B Falcon40B LLaMa2 Functionality Playground Compare Chat Metrics
  • 7. Evaluating Large Language Models LARGE LANGUAGE MODELS Relations Only Relations Explanations CoT Completions Restricted CoT Self-Scoring Truthfulness Proxy
  • 8. Evaluating Large Language Models LARGE LANGUAGE MODELS Tools GPT-3.5 GPT-4.0 Claude2 MPT-30B Few-Shot Input: 12-14 annotated texts Output: 50 annotated texts We want all the texts annotated in a large batch if possible
  • 9. Evaluating Large Language Models LARGE LANGUAGE MODELS Taxonomy of Errors These are only the most frequent errors! And the Winner Is? ChatGPT and Claude2 have similar performance
  • 10. Conclusion? LARGE LANGUAGE MODELS Self-Scoring Consecutive runs Huge differences And the Winner Is? ChatGPT and Claude2 have similar performance
  • 11. Acknowledgments PROJECTS DWBI Vienna - Vienna Science and Technology Fund (WWTF) [10.47379/ICT20096] SDG-HUB – FFG (GA No. 892212) CONTACT adrian.brasoveanu@modul.ac.at THANK YOU!