What we’re about
This Meetup group supports the SF Bay ACM Chapter. You can join the actual SF Bay Chapter by coming to a meeting - most meetings are free, and our membership is only $20/year !
The chapter has both educational and scientific purposes:
- the science, design, development, construction, languages, management and applications of modern computing.
- communication between persons interested in computing.
- cooperation with other professional groups
Our official bylaws will be available soon at the About Us page on our web site. See below for out Code of Conduct.
Videos of past meetings can be found at http://www.youtube.com/user/sfbayacm
Official web site of SF Bay ACM:
http://www.sfbayacm.org/
Click here to Join or Renew
Article IX: Code of Conduct - from the ACM Professional Chapter Code of Conduct
Harassment or hostile behavior is unwelcome, including speech that intimidates,creates discomfort, or interferes with a person’s participation or opportunity for participation, in a Chapter meeting or Chapter event.Harassment in any form, including but not limited to harassment based on alienage or citizenship, age, color, creed, disability, marital status, military status, national origin, pregnancy, childbirth- and pregnancy-related medical conditions, race, religion, sex, gender,veteran status, sexual orientation or any other status protected by laws in which the Chapter meeting or Chapter event is being held, will not be tolerated. Harassment includes the use of abusive or degrading language, intimidation, stalking, harassing photography or recording,inappropriate physical contact, sexual imagery and unwelcome sexualattention. A response that the participant was “just joking,” or “teasing,”or being “playful,” will not be accepted.2. Anyone witnessing or subject to unacceptable behavior should notify a chapter officer or ACM Headquarters.3. Individuals violating these standards may be sanctioned or excluded from further participation at the discretion of the Chapter officers or responsible committee members.
Upcoming events (2)
See all- How to Build Personalization into LLM RecommendationsHacker Dojo, Mountain View, CA
LOCATION ADDRESS
Hacker Dojo
855 Maude Ave,
Mountain View, CA 94043This is a hybrid meeting, you can join remotely and submit questions via Zoom QnA. The zoom link will be provided (TBD).
AGENDA
6:30 Door opens, Food
7:00 SFBayACM upcoming events, introduce the speaker
7:20 presentation starts (~90 min with Q&A)ABSTRACT
We enable Large Language Models (LLM) with personalization capability. This is not specific to the LLM (Open AI's ChatGPT, Athropic's Claude, Meta's Llama 2, Googles,...)Today, LLMs are not good at personalization and providing recommendations. They may advise physicians and financial advisors to "ask professionals" in their respective fields for help, even having user information available. When answering questions for software professionals, the LLM may need to deliver in-depth answers with code or algorithms, whereas for professionals in other fields would need definitions and main concepts.
The intent of this project is to make LLMs provide answers tailored to the needs of a specific user, taking into account available information about that individual. To do that, we need to generalize available documents about a person. Based on the needs of the application and with the permission of the individual being served, information used could include: their LinkedIn profile, visited web pages, investment history extracted from tax documents, and health forms (while maintaining the privacy of this person). We rely on meta-learning techniques to design an LLM prompt to produce a personalization prompt to obtain suitable relevant information. Such a “meta-prompt” is produced by a generalization operation applied to available documents for the user. These documents need to be de-identified so that they are sufficient for personalization, on one hand, and will maintain user privacy on the other hand.
A personalization profile is built from the link provided by the user.
Then, given a user question, this system will use the LLM to generate a set of queries. The URLs from search results are stored internally in a self.urls. A check is performed for any new URLs that haven't been processed yet (not in self.url_database). Only these new URLs are loaded, transformed, and added to the vector store. The vector store is queried for relevant documents based on the questions generated by the LLM. Only unique documents are returned as the final result.
This project build is in https://github.com/bgalitsky/LLM-personalization
SPEAKER BIO
Boris is working at the stealth mode startup, Cybernator.Boris Galitsky contributed linguistic and machine learning technologies to Silicon Valley startups as well as companies like eBay and Oracle for over 25 years. Boris’ information extraction and sentiment analysis techniques assisted a number of acquisitions, such as Xoopit by Yahoo, Uptake by Groupon, Loglogic by Tibco and Zvents by eBay. His security-related technologies of document analysis contributed to acquisition of Elastica by Semantec. https://github.com/bgalitsky/relevance-based-on-parse-trees
As an architect of the Intelligent Bots project at Oracle, Boris developed a discourse analysis technique user for dialogue management and published in the book "Developing Enterprise Chatbots”. He also published a two-volume monograph “AI for CRM”, based on his experience developing Oracle Digital Assistant. Boris is Apache committer to OpenNLP where he created OpenNLP.Similarity component which is a basis for a semantically-enriched search engine and chatbot development.
Galitsky’s exploration and formalization of human seasoning culminated in the book “Computational Autism” broadly used by parents of children with autistic reasoning and rehabilitation personnel. Boris focus on medical domain led to another research monograph, “AI for Health Applications and Management”.
https://www.amazon.com/Books-Boris-Galitsky/s?rh=n%3A283155%2Cp_27%3ABoris+GalitskyAn Author of 150+ publications, 50+ patents and 6 books, Boris’s focus now is on improving content generation quality.
https://www.linkedin.com/in/boris-galitsky-342109204/
