KnowComp HKUST
@HKUSTKnowComp
Followers
451
Following
177
Media
8
Statuses
69
Knowledge Computation Group@HKUST, led by Prof. Yangqiu Song @yqsong. Maintained by @ZhaoweiWang4
Hong Kong
Joined May 2023
RT @yqsong: 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 s….
0
20
0
RT @TFang229: Check out our ACL 2024 paper Complex Commonsense Reasoning over Logical Queries on Commonsense Knowledge Graphs ( https://t.co….
0
4
0
RT @yqsong: This is one of the best ACL conferences that I have attended. Many reflections, kind people, open-minded people, interesting to….
0
3
0
RT @Inevitablevalor: 🚀 Thrilled to announce our paper "Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?" has be….
0
4
0
RT @JiaxinBai2: I have just got my abductive knowledge graph reasoning paper accept by acl24, and I really have some sights to share. In t….
0
3
0
RT @yqsong: COLING is just a couple of days from now. Come to our workshop on Tuesday. We will have four great invited talks! Looking for….
0
6
0
RT @ZhaoweiWang4: 🎉Our work is accepted by ACL 2024: AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with P….
0
3
0
RT @jchengaj: Happy to share EventGround got accepted to LREC-COLING 2024 ! #lreccoling. We introduced a framework that grounds free-text t….
arxiv.org
Narrative reasoning relies on the understanding of eventualities in story contexts, which requires a wealth of background world knowledge. To help machines leverage such knowledge, existing...
0
1
0
RT @yqsong: Check out our new WWW 2024 Tutorial on New Frontiers of Knowledge Graph Reasoning: Recent Advances and Future Trends where we h….
0
4
0
RT @yqsong: In particular, I have discussed the three dimensions of the new development of knowledge graphs
0
4
0
RT @LeonDerczynski: Love this. * attacker can inject backdoors by issuing very few malicious instructions among thousands of gathered data….
arxiv.org
We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies...
0
30
0
RT @ylongqi: Learning from interaction is different from learning from annotations. Today we are excited to share how we are starting to le….
microsoft.com
Microsoft researchers are taking a comprehensive and dynamic approach to help Copilot (web) continuously learn from interaction and feedback, improving the AI system and making it increasingly useful...
0
9
0
RT @peizNLP: 🚩Exciting foundational work towards building an ever-improving interactive agent:.- Identifying user intents/tasks and.- Infer….
0
3
0
RT @Francis_YAO_: So far there are quite a few scaling law papers; almost all of them use different function forms for the same loss, yet a….
0
2
0
Check our new paper.
📢 Glad to share our research accepted at #EACL2024 @eaclmeeting on addressing Large Language Models' (LLMs) ignorance about relational constraints with "ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases"
0
0
8
RT @JiaxinBai2: Excited to announce our NeurIPS paper on for querying KGs and improving logical inference! Traditional approaches mainly f….
0
5
0
RT @Quyet_Azir: 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 eve….
0
1
0