Happy to share that our book "Retrieval-Augmented Generation for LLM Applications" is now available for early access at https://lnkd.in/gYm78aAJ. This book is the result of a great collaboration and hard work with Wendy Ran Wei and Ling Huang. In this book, - You'll learn how to leverage large language models (LLMs) and external databases to build powerful retrieval systems for various domains. - You'll also explore the fundamentals of LLMs, information retrieval, and retrieval-augmented generation (RAG), as well as the latest advances and challenges in LLM evaluation and integration with enterprise data. We hope you enjoy reading the book and find it useful for your own projects. We would love to hear your feedback and suggestions. Please feel free to share your thoughts with us on LinkedIn or private message. Thank you for your support and interest!
Jay (Jianqiang) Wang’s Post
More Relevant Posts
-
Feminist, grassroots political strategist, federal health policy analyst. Pro-immigrant advocate, pro-union advocate. Voracious reader.
#A #Guide #to #Investigating #the #Datafied #State #Through #Documents #JennaBurrell #Professor #UCBerkeley #Director #Data & #SocietyResearchInstitute "As a way to redirect attention to #who #holds #power, and to understand #how #they #wield #it, it is worth our time to treat #document #analysis #as #a #method. #Where #research #calls #the #accounts #of #those #in #power #into #question, #it #helps #to #come #with #receipts."
To view or add a comment, sign in
-
GenAI Leadership @ AWS • Stanford AI • Ex-, Amazon Alexa, Nvidia, Qualcomm • EB-1 "Einstein Visa" Recipient/Mentor • EMNLP 2023 Outstanding Paper Award
📝 Announcing our new paper that proposes a framework to enhance causal reasoning and explainability in LLMs 🔹 "Cause and Effect: Can Large Language Models Truly Understand Causality?" 🔹 In collaboration with Carnegie Mellon University, University of North Texas, Rensselaer Polytechnic Institute, and University of Massachusetts Amherst 🔹 We introduce the Context-Aware Reasoning Enhancement with Counterfactual Analysis (CARE-CA) framework to enhance causal reasoning and explainability in LLMs. It integrates explicit causal detection using ConceptNet and counterfactual statements, alongside implicit causal detection through LLMs, and introduces CausalNet, a new dataset for further research in causal reasoning. 🔹 PDF: https://lnkd.in/gcXuFBgH ✍🏼 Authors: Swagata Ashwani, Kshiteesh Hegde, Nishith Reddy Mannuru, Mayank Jindal, Dushyant Singh Sengar, Krishna Chaitanya Rao, Dishant Banga, Vinija Jain, Aman Chadha #artificialintelligence #research
To view or add a comment, sign in
-
-
AI Expert, Full Professor & Head of AIML lab @UniBw-M/CODE Munich, ex @FU_Berlin, @UniHannover, @LMU_Muenchen
Great news 🎉 Congrats S.Siamak Ghodsi for the accepted paper on fair graph clustering at PAKDD24. While there are a lot of works on tabular data fairness, graph data fairness has been less explored. In this work, we adopt the idea of individual graph fairness, i.e., the proportion of a node's 1-hop neighbors in its own cluster should be similar to the proportion of 1-hop neighbors belonging to the entire population. For details on the motivation, method and the link to the pre-print, see Siamak's post. The work is funded by the ITN NoBIAS project and is also related to multi-modal fairness addressed in the MAMMOth project. #responsibleAI, #fairness #graphfairness #noniidfairness #fairgraphclustering
Announcement 📢: I am super excited to announce that: our latest work entitled "Towards Cohesion-Fairness Harmony: Contrastive Regularization in Individual Fair Graph Clustering" has been accepted in the main research track of the PAKDD 2024 (https://pakdd2024.org/). This is a joint work with my friend and colleague Amjad Seyedi with helpful insights and close collaboration from my supervisor prof.Eirini Ntoutsi. In this work, we shed light on the importance of individual fairness and prejudice-free partitioning of people in social networks and after formalizing the problem we propose an interpretable algebraic model based on non-negative matrix factorization. Suppose a teacher in a classroom intends to divide students into smaller groups to pursue course assignments. What is the best practice to cluster these students? diversifying clusters based on gender and/or ethnicity to comply with inclusivity practices for example? bravo, but what about individual rights for simply keeping their friendship networks? The epistemology of individual fairness suggests respecting the existing connections among people instead of forcing them into mandatory groups of which they might have no interest in. This and similar examples exist in many social networks. That's why establishing fairness in graph clustering is a real-world challenge with no unique answer. We propose a flexible model of graph clustering that tends to maximize fairness while preserving existing individual connections. Read more about our work and our findings here: https://lnkd.in/d8kYgdhH. Also, stay tuned for more news in this direction 😉 #aiml #responsibleAI #fair_graph_clustering #NMF #FairNMF #fairness #graphfairness #non_iid_fairness
Towards Cohesion-Fairness Harmony: Contrastive Regularization in Individual Fair Graph Clustering
arxiv.org
To view or add a comment, sign in
-
New year, new blog post: https://lnkd.in/dadWHrZa . Taking a step back to think about two approaches to managing academic quality and standards (quant data; periodic review) and how they can (or perhaps should) dovetail together.
one and one make five
http://lefttomyowndevices.blog
To view or add a comment, sign in
-
Professor of Authentic Music Theory & Dean of Infrastructure; National Teaching Fellow (2021) and QAA Reviewer.
A cracking thought piece to kickstart the New Year: here’s a quote from it that will appear (cited) in a forthcoming publication from me for sure: Education is a social process. When we’re dealing with social processes quantitative data can indicate something you probably need to look at and think about, but it frequently can’t explain the thing that it’s highlighted. That requires other, more qualitative approaches together with the application of expertise and practical wisdom.
New year, new blog post: https://lnkd.in/dadWHrZa . Taking a step back to think about two approaches to managing academic quality and standards (quant data; periodic review) and how they can (or perhaps should) dovetail together.
one and one make five
http://lefttomyowndevices.blog
To view or add a comment, sign in
-
An interesting kick off towards self-optimization of LLMs. Exciting times! Just make sure to notice the limitations section at the end ofthe paper to fully comprehend the scope 👾
Improvements in LLM reliability! Researchers from Cornell University just published a paper that introduces a method where an LLM learns to evaluate itself using synthetic data, eliminating the need for human annotations. In high level: LLM is receiving input and is instructed to generate two (or more) responses that are totally different. The output is used again as input but with instructions to perform reasoning on each. The result would then be used for model training. The Medium blog: https://lnkd.in/dyiNj2zY The paper: https://lnkd.in/dgPQfiCC
Self-Taught Evaluators
arxiv.org
To view or add a comment, sign in
-
A complete overview of LLM Agent Applications! 🙏 This is a refreshing survey paper, that goes beyond simply documenting the current landscape. It starts by giving the reasoning behind different approaches and describes how these are implemented by various papers in a very intuitive way. It divides the Large Language Model requirement part into three: - Brain: Acting as the reasoning engine, memory and long term planning - Perception: This section covers all modalities possible - Action: Using Text, External Tools and acting independently Finally the paper covers implementation in single agent, multiple agent and human-agent settings. The paper is really comprehensive and actually reads like a very upto date book on the topic. An amazing 50 page read for your Saturday: https://lnkd.in/dzpQdkDs
To view or add a comment, sign in
-
-
Here is a seminar I gave recently, called "Open Science, reproducible research, and the citation of articles, code and data alike". After touching upon the principles of Open Science and reproducible research, I focus on practical approaches to make research software and data Findable, Accessible, Referenceable and Citable (FARC), as well as good practices to cite others' code and data. I finally make the point that to go further, editors must now actively support code and data citation, evaluation metrics must change to give credit for and reward impactful code and data, and all of that shall require a true cultural shift of researchers' mindset. https://lnkd.in/dZZfmTfp
Open Science, reproducibible research, and the citation of articles,code and data alike - F. MICHEL
https://www.youtube.com/
To view or add a comment, sign in
-
The original article was posted last week, but this is a good follow up by Pascal Biese. The idea that structured context is less efficient through an LLM should really surprise no one. Structure (semantification) costs energy to produce, especially when the primary training data for these LLMs is primarily narrative and conversational. This requires more computational cycles, requires more inference from existing samples, and requires more validation. This is a key argument for knowledge graphs. The semanticification has (largely) been done with a knowledge graph. These means that such structured content is the equivalent of a high carb meal.
To view or add a comment, sign in
Senior Director at Alvarez & Marsal | Software Engineer and FinTech Innovator | CPA, AWS Solutions Architect
2moCongrats Jay (Jianqiang) Wang that’s quite an accomplishment. I look forward to reading it!