
Knowledge Computation Group@HKUST, led by Prof. Yangqiu Song @yqsong. Maintained by @ZhaoweiWang4
Hong Kong
Joined May 2023
- Tweets69
- Following526
- Followers452
- Likes175
KnowComp HKUST retweeted
What kind of research should I do in the era of LLMs? Nowadays, some people get so excited to work on LLMs and the other feel so suffering as they don't have GPU cards to work on LLMs. IMHO, there are two ways to think about this: (1) What LLMs cannot do and (2) What LLMs have enabled. In this post, I will focus on the second problem, what they have enabled.
If you browse recent arxiv papers, many are working on Agent, Tool use, RAG. I agree they are very interesting and important problems. But at university, we'd better think of something one step further. For example, for RAG, it would be better for us to think about what if the external resource can also make predictions. Particularly, with LLMs, we can improve many semantic matching results in traditional database queries with free text attributes. Nowadays, we are in the era of "neuralizing everything", compared to what we were doing to "digitalize everything". With those neuralized models, agents, agent-tools, tool-tool's interactions can be all memory interactions, which naturally fit Yann LeCun's world model. In this regard, instead of worrying about having no machines to train LLMs, we can focus on improving the predictability of tools. Now it's time for us to leverage LLMs to improve the prediction power of DBs/KBs.
In particular, I love the idea of neural graph databases (ngdb.org/), which not only do DB/KB embeddings, but are also equipped with logical query power. I believe this is one of the most important developments in the field of data mining! In this year's KDD, we will present our work on Privacy-Preserved Neural Graph Databases(arxiv.org/abs/2312.15591). This could be particularly useful for the next generation of RAG systems. You are welcome to attend our talk and have more discussions with us then.
KnowComp HKUST retweeted
Check out our ACL 2024 paper Complex Commonsense Reasoning over Logical Queries on Commonsense Knowledge Graphs (arxiv.org/pdf/2403.07398). The poster session will be 13 August (Tuesday) 4pm! Come and say Hi #NLProc #ACL2024
KnowComp HKUST retweeted
This is one of the best ACL conferences that I have attended. Many reflections, kind people, open-minded people, interesting topics, etc. Particularly for my research on new kinds of knowledge graph/base construction on events/states/intentions/beliefs, this is the only conference that I can find people to discuss. One thing that I found potentially hurt us is that, there is a voice from the Chair saying “ACL is not an AI conference”. Time to think if we should have a new knowledge-oriented conference given that AKBC is no longer active… @aclmeeting @akbc_conf
KnowComp HKUST retweeted
🚀 Thrilled to announce our paper "Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?" has been accepted at #ACL2024!
🎉 We explored whether multi-agent discussions truly outperform single agents in LLM reasoning, an area largely unexamined.
KnowComp HKUST retweeted
I have just got my abductive knowledge graph reasoning paper accept by acl24, and I really have some sights to share.
In this paper, we try to explain observations by using a complex logical expression formed by the knowledge inside a knowledge graph. Seems very abstract? Here is an example: suppose someone follows five people, Grant Heslov, Jason Segel, Robert Towne, Ronald Bass,
Rashida Jones, in social networks, and we have a kg about these people, then we want to explain like: they are the Screenwriters and Actors that are born in California.
KnowComp HKUST retweeted
It’s getting started😄
COLING is just a couple of days from now. Come to our workshop on Tuesday. We will have four great invited talks! Looking forward to learning from @pascalefung, Juanzi Li, @AlexLenci1966 and @vtresp @LrecColing
KnowComp HKUST retweeted
COLING is just a couple of days from now. Come to our workshop on Tuesday. We will have four great invited talks! Looking forward to learning from @pascalefung, Juanzi Li, @AlexLenci1966 and @vtresp @LrecColing
Workshop: Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning @ LREC-COLING 2024 =====================================
Co-located with LREC-COLING in Turin, Italy 21st May 2024 @LrecColing #LREC #COLING
Workshop webpage:neusymbridge.github.io/
Call for Papers
--------------------
The 1st Workshop on Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning — to be held at LREC-COLING
2024 — will promote two directions for exploring neural reasoning:
starting from existing neural networks to enhance the reasoning performance with the target of symbolic-level reasoning, and starting from symbolic reasoning to explore its novel neural implementation.
These two directions will ideally meet somewhere in the middle and will lead to representations that can act as a bridge for novel neural computing, which qualitatively differs from traditional neural networks, and for novel symbolic computing, which inherits the good features of neural computing. Hence the name of our workshop, with a focus on Natural Language Processing and Knowledge Graph reasoning.
Topics (include, but are not limited to)
--------------------------------------------------
• Proposing novel knowledge representations that are derived from transdisciplinary research • Using knowledge graphs or other types of symbolic Knowledge to improve the quality of LLMs • Exploring the reasoning mechanism of LLMs • Distilling symbolic knowledge from LLMs • Proposing benchmark datasets and evaluation matrices for neuro-symbolic approaches to NLP tasks • Proposing novel NLP tasks for neuro-symbolic approaches • NLP applications in classification, sense-disambiguation, sentiment analysis, question-answering, knowledge graph reasoning • Critical analysis of traditional deep learning or LLMs • Analysing spatial reasoning of LLMs • Proposing novel neural computing that may reach symbolic-level reasoning • Proposing benchmark datasets and matrices to evaluate the gap between neural reasoning and symbolic reasoning • Addressing efficiency issues in neuro-symbolic systems • Identifying challenges and opportunities of neuro-symbolic systems • Developing retrieval augmented models for combining KG and LLMs • Applying neuro-symbolic approaches to humor generation and other real-life applications
Submissions:
------------------
• The papers should be submitted as a PDF document, conforming to the formatting guidelines provided in the call for papers of LREC-COLING conference (lrec-coling-2024.org/authors…)
• Submissions via Softconf/START Conference Manager athttps://softconf.com/lrec-coling2024/neusymbridge2024/
Important Dates
---------------------
• Submission Deadline: March 03, 2024
• Notification of Acceptance: March 27, 2024 • Submission of final, camera-ready paper (latex version preferred):
April 03, 2024
• Workshop: May 21st
KnowComp HKUST retweeted
🎉Our work is accepted by ACL 2024: AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation.
While previous evaluations show that LLMs lack abstraction ability, do LLMs already own a lot of abstraction knowledge?
The answer is YES!
Arxiv: arxiv.org/pdf/2402.10646
#ACL #NLP #ACL2024 #nlproc
KnowComp HKUST retweeted
Happy to share EventGround got accepted to LREC-COLING 2024 ! #lreccoling
We introduced a framework that grounds free-text to eventuality knowledge graphs, aiming to enhance narrative reasoning.
arxiv.org/abs/2404.00209
KnowComp HKUST retweeted
Check out our new WWW 2024 Tutorial on New Frontiers of Knowledge Graph Reasoning: Recent Advances and Future Trends where we have discussed many interesting new things happening in the field of knowledge graphs #webconf #knowledgegraph #KG @TheWebConf @Zihao_thust @JiaxinBai2 @Lihui00721924 sites.google.com/view/new-fr…
KnowComp HKUST retweeted
In particular, I have discussed the three dimensions of the new development of knowledge graphs
Check out our new WWW 2024 Tutorial on New Frontiers of Knowledge Graph Reasoning: Recent Advances and Future Trends where we have discussed many interesting new things happening in the field of knowledge graphs #webconf #knowledgegraph #KG @TheWebConf @Zihao_thust @JiaxinBai2 @Lihui00721924 sites.google.com/view/new-fr…
KnowComp HKUST retweeted
Love this
* attacker can inject backdoors by issuing very few malicious instructions among thousands of gathered data
* attacker can achieve > 90% success
* instruction attacks show resistance to existing inference-time defense
Any mTurker has control!
arxiv.org/abs/2305.14710
KnowComp HKUST retweeted
Learning from interaction is different from learning from annotations. Today we are excited to share how we are starting to learn from people's interactions to understand and improve Copilot (web) for our consumer customers:
microsoft.com/en-us/research…
#Microsoft #Copilot #Bing
KnowComp HKUST retweeted
🚩Exciting foundational work towards building an ever-improving interactive agent:
- Identifying user intents/tasks and
- Inferencing user satisfaction
Both from unstructured chat logs are necessary first-steps for self-improving.
Esp. found this fig of how ppl are actually using llms intriguing
Learning from interaction is different from learning from annotations. Today we are excited to share how we are starting to learn from people's interactions to understand and improve Copilot (web) for our consumer customers:
microsoft.com/en-us/research…
#Microsoft #Copilot #Bing
KnowComp HKUST retweeted
So far there are quite a few scaling law papers; almost all of them use different function forms for the same loss, yet all the curve fitting look quite well. I'll buy a coffee for someone who writes a blog comparing all the scaling laws and suggesting the most reasonable one 🤔
KnowComp HKUST retweeted
Excited to announce our NeurIPS paper on for querying KGs and improving logical inference! Traditional approaches mainly focus on entity KGs, but in the real world, we need to reason about events, states, and activities too. #NeurIPS2023 #KnowledgeGraphs #LogicalInference – at Central Region, Singapore
KnowComp HKUST retweeted
It's super exciting to meet a lot of my "idols" in EMNLP'23. I even had chances to talk with some of them. What a great event!
KnowComp HKUST retweeted
NAACL 2024 invites the submission of long and short papers
📜Paper submission deadline to ARR: December 15, 2023
🌎Hybrid conference, physically held in: #MexicoCity
More info is here:
2024.naacl.org/calls/papers/
KnowComp HKUST retweeted
🥳New Public Webinars🥳Welcome all!
The School of Engineering of HKUST will host two Info Webinars on HKUST Engineering Research Studies, with the themes of Healthcare and Artificial Intelligence, and Robotics and Sustainability, on 19 and 26 September 2023 (Tue.), respectively.































