Ningyu Zhang@ZJU
@zxlzr
Followers
1,571
Following
1,384
Media
123
Statuses
541
Associate Professor @ZJU_China . Research interests include NLP, KG, Knowledge Editing.
Hangzhou, China
Joined February 2009
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Cheney
• 352089 Tweets
Colombia
• 227368 Tweets
Packers
• 129498 Tweets
श्री गणेश
• 84928 Tweets
ENGFA ACTRESS 100M
• 82030 Tweets
Perú
• 73869 Tweets
1 Day Left For Avataran Diwas
• 71886 Tweets
Saquon
• 71462 Tweets
गणपति बप्पा
• 63373 Tweets
#GaneshChaturthi
• 55859 Tweets
Hope Love
• 55775 Tweets
Jalen
• 55322 Tweets
#ATIPASHOPxCHARLOTTESNACK
• 50187 Tweets
Giants
• 50176 Tweets
Green Bay
• 37328 Tweets
Philly
• 33073 Tweets
भगवान गणेश
• 29280 Tweets
Jordan Love
• 27735 Tweets
Duke
• 25989 Tweets
Lord Ganesha
• 24569 Tweets
#二度と撮れない画像を貼れ
• 21852 Tweets
#GanpatiBappaMorya
• 20846 Tweets
Fritz
• 16838 Tweets
Durán
• 16640 Tweets
Lucho
• 14548 Tweets
Tiafoe
• 13627 Tweets
Jayden Reed
• 13614 Tweets
ビッグラン
• 12914 Tweets
イコラブ
• 12093 Tweets
Pinned Tweet
🌟 Introducing KnowUnDo! A new benchmark designed
for knowledge unlearning in LLMs, focusing on copyrighted content and user privacy.
Our paper "To Forget or Not? Towards Practical Knowledge Unlearning for LLMs" shows existing methods often erase too much crucial knowledge.
1
7
43
Curious about how large language models store and utilize knowledge? What do the neurons actually learn?
🎉 Exciting insights from our latest research on "Knowledge Circuits in Pretrained Transformers"! Discover how pretrained transformers store and use knowledge, enhancing
7
50
257
How to inform the LLM about the 2022 World Cup champ? 🤔 Ever wondered how to perform surgery on a LLM? 🤖✂️🔪
Our
#EMNLP2023
paper reviews the tech to edit LLMs. Empirical studies on batch & sequential settings are in! 📊 Introducing a new metric: Portability, measuring the
3
8
118
Super excited to announce the open-sourcing of our ICLR 2024 Spotlight work "Tool-Augmented Reward Modeling" in collaboration with Baidu! 🚀 Check out the code here: .
🔥 For more details, feel free to dive into our paper: .
Our
3
18
92
Can we tweak the toxic bits to make LLMs safer? 🤔
Excited to share our new work "Detoxifying Large Language Models via Knowledge Editing" collaborated with
@linyi_yang
@jd92wang
@yyzTodd
@dsmall2apple1
and friends...，accepted at ACL 2024
@aclmeeting
! We introduce SafeEdit, a
2
18
82
Introducing our latest work, KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents 🚀. Explore strategy for boosting the planning capabilities of LLM-based agents by leveraging external action knowledge base.
#NLP
#LLMs
#Agent
#KnowAgent
#Planning
#Knowledge
📌Project
3
15
76
🔬 Just dropped the 🔥 updated MolGen paper! 🧬 New results on molecular docking are in.
#ChemAI
#AI
#NLP
#LLM
#DataScience
#Bioinformatics
Paper:
GitHub:
Model:
1
12
68
Welcome to attend the tutorial on "Knowledge Editing for Large Language Models" at IJCAI 2024
@IJCAIconf
. Here are the details
#NLP
#AI
#KnowledgeEditing
#LLMs
:
Tutorial: Knowledge Editing for Large Language Models
Location: Room 1F-Yeongju B
Time: 9:00-12:30, August 3, 2024
1
13
70
🚀 Our latest paper, "AutoAct: Automatic Agent Learning from Scratch via Self-Planning," introduces an automatic agent learning framework that's independent of large-scale annotated data and synthetic trajectories from LLMs like GPT-4. It's all about precise task specificity and
1
13
61
We will present EasyEdit tomorrow at
#ACL24
@aclmeeting
.
Location: Mon 11:00-12:30
@Convention
Center A1, Poster Session A
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models (Demo)
Can't wait to connect and chat with everyone there! 🌟
#ACL2024
1
10
56
Exciting news! 🎉 We've just open-sourced EasyEdit, a versatile tool for editing Large Language Models. Supports various methods (e.g., SERAC, IKE, MEND, KN, ROME, MEMIT) and it's available now on
@github
! Committed to keeping it updated with new models. Dive into the world of
1
8
55
🚀 Exciting update! EasyEdit now supports editing Mistral-7B.
You need manually update transformers==4.34.0🔄.
Plus, we have fixed some bugs in MEND evaluation, further refining performance. Stay ahead with the latest enhancements!
#AI
#EasyEdit
#LLMs
#NLP
#ModelEditing
2
13
49
Excited to announce that our knowledge editing tool EasyEdit now supports llama3-8b! 🚀 Currently rocking ROME editing method. We'll keep it fresh with updates and more editing methods, but remember: Transformers gotta level up to 4.40.0. Got questions or requests? Hit us up with
1
5
49
Excited to announce that our paper “Neighboring Perturbations of Knowledge Editing on Large Language Models” cooperated with Jia-Chen Gu
@Jiachen_Gu
, Jun-Yu Ma and Zhen-Hua Ling got accepted to
#icml2024
@iclr_conf
! 🎉 We delve into whether updating new knowledge in LLMs
1
11
48
#IJCAItutorial
We’re excited to announce a tutorial at
@IJCAIconf
on Jeju Island, South Korea, on August 3 (morning), 2024
#IJCAI2024
.
T07: Knowledge Editing for Large Language Models.
Something new:
1) Introducing knowledge mechanisms in large language models such as
1
8
48
Still worried that continuously editing large language models will severely harm their general performance? Concerned about their generalization ability?
Introducing our latest work, "WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of LLMs" 🥳.
Explore a
1
13
47
Thrilled to announce our paper "Reasoning with Language Model Prompting: A Survey" has been accepted by ACL2023
@aclmeeting
!
#ACL2023
#NLP
#AIResearch
arXiv:
Github:
0
18
46
Want to keep your AI agent up-to-date and aligned with your ideas? Try cutting-edge knowledge editing methods!🤖📷<✂️🔪
In
#EMNLP2023
, we presented the prior work “Editing Large Language Models: Problems, Methods, and Opportunities” for a review of LLMs editing techniques. After
3
6
43
Introducing a new task: editing LLM personalities based on Social Psychology! 🚀 Adjust model responses to reflect varied traits and watch it reshape opinions on specific topics. Think of it as giving your AI a personality makeover! 💡✨
#LLM
#NLP
#AI
#InnovativeAI
1
12
42
Curious about how knowledge in LLMs is acquired, stored, utilized, and subsequently evolves in individuals and groups?
New Paper:
Our latest research on "Knowledge Mechanisms in Large Language Models: A Survey and Perspective" provides a novel
1
9
41
Our EasyEdit now supports editing multi-modal LLMs. Currently, you can edit MiniGPT-4 and Blip2. Check out the details here: . Feel free to follow us for updates.
Related paper: . 🚀📚
#EasyEdit
#ModelEditing
#KnowledgeEditing
0
9
39
Can editing LLMs cause a 'butterfly effect'? 🦋 Our new paper dives into:
1️⃣ Knowledge Conflict: Multiple edits with logical conflict might amplify LLM inconsistencies.
2️⃣ Knowledge Distortion: Changing parameters might disrupt LLM's implicit knowledge structure.
Hoping this
0
10
40
🤔Can NLP systems mirror human-esque collaborative intelligence, in a multi-agent society consisting of multiple large language models?
Excited to collaborate with
@zjuzjt
@dsmall2apple1
@BryanHooi1
@RuiboLiu
@IreneXuPiano
! 🚀 We've updated our paper "Exploring Collaboration
2
7
36
Just released new information extraction models: lora weights trained on Meta-Llama-3-8B-Instruct with IEPile corpus, and a full-parameter fine-tuned information extraction model, OneKE, based on Chinese-Alpaca-2-13B for the community! 🚀
#OpenSource
#ModelWeights
#IEPile
#NLP
4
5
34
🚀 Knowledge Graphs meet LLMs in a grand rendezvous! 🧠 Dive into the future of KGs x LLMs with us at
#IJCAI23
@IJCAIconf
. Get insights on knowledge extraction, editing & interactive agents. Be there, be informed! 🌟
#AI
#KnowledgeGraph
#NLP
#LLM
#TechTalks
🤖🔍📚
📌 Topic:
3
6
32
Excited to share that our team will be at ACL 2024 in Bangkok from August 11-16! We'll be presenting our latest work on knowledge editing, agent learning, and information extraction at both the main conference and workshops
@aclmeeting
. Can't wait to connect and chat with
0
5
29
🚀 Excited to announce our
#EMNLP2023
work: "Knowledge Rumination"! 🧠 By extracting implicit parametric knowledge from PLM via prompting "as far as I know", and feeding it back, we've seen a boost in
#NLP
tasks, especially commonsense reasoning. 📈 See you in Singapore! 🔥
#AI
0
8
28
Meet MOLGEN - our novel pre-trained molecule-generating language model. MOLGEN harnesses inherent structural and grammatical nuances by rebuilding 100M+ molecular SELFIES.
#ChemAI
#AI
#NLP
#LLM
#DataScience
#Bioinformatics
Paper:
GitHub:
1
6
28
Thrilled to announce that our paper "IEPile: Unearthing Large-Scale Schema-Based Information Extraction Corpus" has been accepted by ACL 2024! Massive thanks to my amazing collaborators! 🚀🚀🚀
#ACL2024
#NLP
#LLMs
Github:
Paper:
Just released new information extraction models: lora weights trained on Meta-Llama-3-8B-Instruct with IEPile corpus, and a full-parameter fine-tuned information extraction model, OneKE, based on Chinese-Alpaca-2-13B for the community! 🚀
#OpenSource
#ModelWeights
#IEPile
#NLP
4
5
34
1
3
28
🚀 EasyEdit, our knowledge editing framework for LLMs, now seamlessly integrates with LlaMA2! Edit LLMs in under 5 seconds. 🕐 Dive in now at !
#EasyEdit
#LLMediting
#NLP
#LLM
#ArtificialIntelligence
1
4
27
Excited to share our latest open-source dataset, InstructIE, a bilingual information extraction dataset based on topic schemas! 🌍🔍 Spanning 12 topics: Person, Geographic_Location, Building, Works, Creature, Artificial_Object, Natural_Science, Organization, Transport, Event,
1
0
27
Our group has 5 papers accepted to
#EMNLP2023
(3 main conference + 2 findings)! Stay tuned for more details. See you in Singapore!
@emnlpmeeting
#NLP
#AI
0
1
27
The code for AutoAct is now open source at .
Feel free to check it out and contribute to advancing LLM-based agent development together! 🚀
#AI
#agent
#NLP
#LLM
#AutoAct
🚀 Our latest paper, "AutoAct: Automatic Agent Learning from Scratch via Self-Planning," introduces an automatic agent learning framework that's independent of large-scale annotated data and synthetic trajectories from LLMs like GPT-4. It's all about precise task specificity and
1
13
61
0
2
26
Congratulations to my student Shuofei Qiao
@QSFByte
for his work "Making Language Models Better Tool Learners with Execution Feedback" getting accepted by
#NAACL24
@naaclmeeting
. This paper tries to address the research question: Can we teach language models when and how to use
1
3
25
Thrilled to announce the release of our 7B molecular language model based on SELFIES! 🎉
Download:
Dive in to generate molecules from scratch using the bos_token or input a partial structure for completion. Have a try! 🔬
#MolecularAI
#Innovation
#NLP
#AI
1
3
24
The code of the paper "Agent Planning with World Knowledge Model" has been released:
Unveiling the Power of Knowledge in AI Planning 🚀
Preprint alert! We release a new work "Agent Planning with World Knowledge Model", which boosts agent planning capabilities by training a parameterized world knowledge model. 🌐
#NLP
#LLMs
#AI
#WorldModel
#Knowledge
Paper:
10
6
18
0
2
24
🚀 EasyEdit now supports efficient editing for
#Baichuan2
,
#ChatGLM2
,
#InternLM
,
#Qwen
. Plus, we've fixed some bugs for an even smoother experience! ✨
#Update
#TechNews
#NLP
#ModelEditing
#KnowledgeEditing
#AI
#LLMs
#EasyEdit
#KnowLM
Check it out:
🔥
0
6
23
Thrilled to announce that our paper "AUTOACT: Automatic Agent Learning from Scratch via Self-Planning" has been accepted by ACL 2024! Congrats to Shuofei
@QSFByte
. Massive thanks to my amazing collaborators
@wangchunshu
@eleanorjiang630
! 🚀🚀🚀
#ACL2024
#NLP
#LLMs
Github:
🚀 Our latest paper, "AutoAct: Automatic Agent Learning from Scratch via Self-Planning," introduces an automatic agent learning framework that's independent of large-scale annotated data and synthetic trajectories from LLMs like GPT-4. It's all about precise task specificity and
1
13
61
0
2
23
Thank you to all the speakers and friends who joined us at LKM2024: The First International OpenKG Workshop on Large Knowledge-Enhanced Models
@IJCAIconf
. It was a wonderful day! 🎉
#LKM2024
#OpenKG
#IJCAI2024
#NLP
#KG
#LLMs
#IJCAI24
0
5
22
Unveiling
#Mol
-Instructions, a large-scale biomolecule instruction dataset for LLMs! It's time to level-up your game in molecule gen, protein synthesis, and biomedical NLP.
#AI
#NLP
#LLM
#DataScience
#Bioinformatics
arXiv:
Github:
0
6
22
Ever wondered about the connection between code (Program-of-Thought) and the reasoning ability of LLMs? 🤔 We've delved into this intriguing realm through empirical analysis and uncovered some fascinating insights.
📊 Introducing Complexity-Impacted Reasoning Score (CIRS): a
0
9
21
The tutorial of Knowledge Editing for Large Language Models at LREC-COLING 2024
@LrecColing
is in progress.
#NLP
#LLMs
#KnowledgeEditing
0
1
21
Excited to chat about “Knowledge Editing for Large Language Models" at
#AAAI24
in our tutorial with Jiachen Gu, Yunzhi Yao, Zhen Bi and Shumin Deng! Thanks a lot to the organizer. Dive deeper into the topic with resources on .
@RealAAAI
#LanguageModels
0
5
20
Excited to announce our EasyInstruct paper is out! 🚀 Transforming chat, corpus, and Knowledge Graph into instructions for LLMs. Dive into our project, try the demo, and explore the code. Your feedback is welcome!
#AI
#NLP
#LLMs
#EasyInstruct
#KnowLM
🌐 Project:
0
3
18
We've just open-sourced KnowLM, a knowledgeable large language model framework! It comes with pre-training and instruction fine-tuning code (supports multi-machine multi-GPU setup). Oh, and don't miss our bilingual LLM called ZhiXi (智析) for information extraction!
#opensource
0
5
19
Just published in JCIM: "The Future of Molecular Studies through the Lens of Large Language Models" – a visionary paper exploring the role and potential of large language models in molecular research. We evaluate their capabilities and envision future developments in this
0
2
17
Unveiling the Power of Knowledge in AI Planning 🚀
Preprint alert! We release a new work "Agent Planning with World Knowledge Model", which boosts agent planning capabilities by training a parameterized world knowledge model. 🌐
#NLP
#LLMs
#AI
#WorldModel
#Knowledge
Paper:
10
6
18
#EMNLP2023
Diving deep into editing Multimodal LLMs! 🚀 Introducing MMEdit - our newest benchmark for polishing these beasts. 🧠 While past methods did okay-ish, there's a WHOLE lot more to unravel. Challenges ahead!
@emnlpmeeting
@Arxiv_Daily
@arxiv
@ArXivGPT
🤖🔧
#MMEdit
#NLP
1
4
18
Curious about editing Large Language Models? Drop by our poster on "Can We Edit Multimodal Large Language Models?" at
#EMNLP2023
!
@emnlpmeeting
#NLP
#LLM
#ModelEditing
#KnowledgeEditing
🗓️ Date: Dec 8th 🕚 Time: 16:00 📍 Location: East Foyer
#34
📚 Dive into our research:
🔗
1
1
18
🚀 Knowledge Graphs meet LLMs in a grand rendezvous! 🧠 Dive into the future of KGs x LLMs with us at
#IJCAI23
@IJCAIconf
. Get insights on knowledge extraction, editing & interactive agents. Be there, be informed! 🌟
#AI
#KnowledgeGraph
#NLP
#LLM
#TechTalks
🤖🔍📚
📌 Topic:
3
6
32
0
3
18
Poster alert! We will also present SafeEdit and MHaluBench tomorrow afternoon at
#ACL24
@aclmeeting
Location: Tue 16:00-17:30
@Convention
Center A1, Poster Session E
Detoxifying Large Language Models via Knowledge Editing
Unified Hallucination Detection for Multimodal Large
0
4
17
🚀 Our knowledge editing tool EasyEdit now features:
🆕 Two new editing methods - GRACE’NeurIPS23 & PMET’AAAI24. Discover how they work?:
🔗 Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors()
🔗 PMET: Precise Model Editing in a
0
3
16
Welcome to focus on our new paper in the field of Multimodal Hallucination: "Unified Hallucination Detection for Multimodal Large Language Models." 🤖💡
#AI
#MultimodalAI
#MachineLearning
#NLP
#LLMs
#EasyDetect
#Hallucination
#UniHD
🔍 Our latest paper, "Unified Hallucination
0
3
17
We have released new weights of models trained on Meta-Llama-3-8B with Mol-Instructions for the community
#Mol
-Instructions
#LLMs
#NLP
#LLaMA3
#AI
#Science
#Bioinformatics
.
Models：
Mol-Instructions collections:
Just rolled out fresh quantitative experimental results with the LLaMA-based training on our Mol-Instructions dataset! 🚀 Stay tuned as we continuously update the paper and improve this dataset. 📈🔧
#DataScience
#NLP
#Science
#Bioinformatics
#LLM
#AI
ArXiv:
0
3
10
0
5
17
Just in! We're thrilled to share the hallucination detection performance of GPT-4o on our MHaluBench. 🎉 Additionally, we're excited to release HalDet-LLAVA(7/13B), an open-source hallucination detection model. Check it out!
#NLP
#AI
#LLMs
#MHaluBench
#HalDetLLAVA
Github:
Welcome to focus on our new paper in the field of Multimodal Hallucination: "Unified Hallucination Detection for Multimodal Large Language Models." 🤖💡
#AI
#MultimodalAI
#MachineLearning
#NLP
#LLMs
#EasyDetect
#Hallucination
#UniHD
🔍 Our latest paper, "Unified Hallucination
0
3
17
0
2
16
🚀Excited to share a quick EasyEdit () update! 🎉 We've fixed some bugs and added some cool features for the community:
1️⃣ Introducing a simple baseline FT-M (different from FT-L in ROME) for better performance, thanks to Damien de Mijolla's advice! 🌟
1
4
15
Ever dived into how code prompts like Program-of-Thought impact a language model's reasoning skills? 🤓 Explore with us in our latest
#AAAI24
paper "When Do Program-of-Thoughts Work for Reasoning?", revealing some interesting findings.
📊 Meet Complexity-Impacted Reasoning Score
0
0
15
We will present MachineSoM and IEPile tomorrow at
#ACL24
@aclmeeting
Location: Tue 10:30-12:00
@Convention
Center A1, Poster Session D
Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
IEPile: Unearthing Large-Scale Schema-Based Information Extraction
0
3
15
🚀 Want to keep your AI agent up-to-date and aligned with your ideas? 🧠 Dive into the cutting-edge methods of editing LLMs with us at
#AACL23
@aaclmeeting
📌 Topic: T4 - Editing Large Language Models.
📍 Catch us at Tabanban, Grand Hyatt Bali.
🕑 Time's ticking: 14:00-17:30.
0
2
13
We will also present OceanGPT tomorrow at
#ACL24
@aclmeeting
Location: Mon 11:00-12:30
@Convention
Center A1, Poster Session A
OceanGPT: A Large Language Model for Ocean Science Tasks
Can't wait to connect and chat with everyone there! 🌟
#ACL2024
#AI
#NLP
#LLMs
0
4
13
Excited to announce our tutorial on knowledge editing for large language models at LREC-COLING 2024
@LrecColing
! Join us in Torino, Italy on Tuesday, May 21st, to explore how we can control LLMs to update knowledge (memory). Let's dive into the power of knowledge editing! 🚀
1
2
13
📄 "Towards A Unified View of Answer Calibration for Multi-Step Reasoning" 🤖 We're diving deep into the world of
#AnswerCalibration
in
#MultiStepReasoning
via prompting
#LLMs
. Discover a unified view to establish connections between different answer calibration strategies
1
3
13
🌊 Introducing
#OceanGPT
: The first LLM expert in ocean science! Leveraging our new DoInstruct framework, we gather vast ocean domain instruction data through multi-agent collaboration. Plus, check out
#OceanBench
, our benchmark for oceanography. Results? OceanGPT excels in
0
3
13
Just updated our Mol-Instructions paper with more quantitative experiment comparisons! 📊 Released a molecular and text model trained on LLaMA-2. Eager for your valuable feedback! 💡
#DataScience
#NLP
#Science
#Bioinformatics
#LLM
#AI
Paper:
GitHub:
0
4
13
Cool idea to serve LLMs as Collaboratively Edited Knowledge Bases using our EasyEdit!
Project here:
EasyEdit:
Algorithms like MEMIT enable us to inject facts into an LLM by editing its parameters 💉🧠.
Could we use fact editing to crowdsource a continually updated neural knowledge base—with no RAG or external documents?
Announcing WikiLLM! Tomorrow's [experimental] free encyclopedia 🧵
5
28
178
0
2
11
We are excited to announce the first International OpenKG Workshop on Large Knowledge-enhanced Models (LKM2024) held in conjunction with IJCAI 2024
@IJCAIconf
🚀. The workshop aims to bring together researchers from academia and industry to discuss the latest advances and
1
2
12
#knowledgeedting
Knowledge editing for API updates!
Knowledge updates for code LLMs: Code LLMs generate calls to libraries like numpy and pandas. What if these libraries change? Can we update LLMs with modified function definitions?
Test this with our new benchmark, CodeUpdateArena. Findings: updating LLMs’ API knowledge is hard!
2
41
131
0
2
12
The slides is available online:
#Tutorial
T07: Knowledge Editing for Large Language Models with Ningyu Zhang, Jia-Chen Gu, Yunzhi Yao, Mengru Wang, Xiang Chen, Shumin Deng.
PPT resources:
Details by
@zxlzr
:
#IJCAI2024
0
1
5
0
3
12
Can we update Knowledge Graph (KG) embeddings without re-training after deployment🤔. In our
#AAAI24
paper, we propose a new task of editing language model-based KG embeddings with new benchmarks and baselines🤖📷🔪
@RealAAAI
.
#NLP
#LLM
#ModelEditing
#KnowledgeEditing
1
1
10
Interesting work on LLM agents!
🚀Exploring the Mind of LLMs in Multi-Agent Societies!🤖
📑:
📚: , ,
🛠️:
#NLP
#NLProc
#NLPResearch
#Collaboration
#AI
#CollaborativeAI
#LLM
#SocialPsychology
2
15
48
0
2
11
Check out our paper list on Model Editing over at . Here's to shaping the future of large language models!
#AI
#ModelEditing
#LargeLanguageModels
2
0
10
#KnowledgeEditing
#NLP
#LLMs
#AI
#ModelEditing
The slides is available at:
More materials can be found at:
The tutorial of Knowledge Editing for Large Language Models at LREC-COLING 2024
@LrecColing
is in progress.
#NLP
#LLMs
#KnowledgeEditing
0
1
21
0
0
10
We release a library DeltaKG for dynamically editing PLM-based KG embeddings, have fun!
arXiv:
Github:
0
0
10
Just rolled out fresh quantitative experimental results with the LLaMA-based training on our Mol-Instructions dataset! 🚀 Stay tuned as we continuously update the paper and improve this dataset. 📈🔧
#DataScience
#NLP
#Science
#Bioinformatics
#LLM
#AI
ArXiv:
0
3
10
New model alert! Last year, we released OceanGPT (based on LLaMA2) and explored its capabilities in ocean science Q&A, generation, and underwater embodied intelligence
#OceanGPT
#AI
#OceanScience
#LLM
#NLP
.
Paper:
Model:
🌊 Introducing
#OceanGPT
: The first LLM expert in ocean science! Leveraging our new DoInstruct framework, we gather vast ocean domain instruction data through multi-agent collaboration. Plus, check out
#OceanBench
, our benchmark for oceanography. Results? OceanGPT excels in
0
3
13
0
3
9
Thrilled to announce that our paper "Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View" has been accepted by ACL 2024! Massive thanks to my amazing collaborators
@zjuzjt
@dsmall2apple1
@RuiboLiu
@BryanHooi1
@XinXuNLPer
! 🚀📷
#ACL2024
#NLP
#LLMs
🤔Can NLP systems mirror human-esque collaborative intelligence, in a multi-agent society consisting of multiple large language models?
Excited to collaborate with
@zjuzjt
@dsmall2apple1
@BryanHooi1
@RuiboLiu
@IreneXuPiano
! 🚀 We've updated our paper "Exploring Collaboration
2
7
36
0
2
9
great and interesting work
What happens when LLMs encounter information that contradicts their static knowledge? 🤔
Discover our findings, including a new dataset and interpretability method, in our ACL 2024 paper! 🧵👇
📄 Read the paper:
🖥️ Explore more:
2
26
94
0
0
8
Thanks AK for re-posting our work!
Weaver
Foundation Models for Creative Writing
paper page:
most-capable Weaver Ultra model surpasses GPT-4, a state-of-the-art generalist LLM, on various writing scenarios, demonstrating the advantage of training specialized LLMs for writing purposes.
13
76
357
0
0
6
Our ACL2023 work for information extraction, which models complex dependency among event structured components with energy-based modeling
@aclmeeting
@aclanthology
.
Thrilled to share our paper "💬SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres" accepted by ACL2023.
@aclmeeting
#ACL2023
#NLP
#AIResearch
@zxlzr
@BryanHooi1
Preprint:
Project:
2
0
6
0
0
7
We’ll talk about “Open-Environment Knowledge Graph Construction and Reasoning: Challenges, Approaches, and Opportunities” at IJCAI 23 at our tutorial.
Thanks a lot to the organizers.
More resources at .
2
2
5
Great work! Congrats.
New paper on single-cell genomics & regulatory networks for 388 human brains just out in
@ScienceMagazine
. Neat stuff on single-cell QTLs, cell-to-cell communication, & DL models simulating drug effects ()
#PsychENCODE24
13
72
221
1
0
6
Our WWW2023 paper "A Concept Knowledge Graph for User Next Intent Prediction at Alipay" cooperated with Alipay has been online at
1
1
6