Automating Knowledge Extraction for Training Content Generation with LLMs @ SquadStack

Dec 2023

4 Mon

5 Tue

6 Wed

7 Thu

8 Fri 09:00 AM – 04:15 PM IST

9 Sat

10 Sun

Make a submission

Accepting submissions till 15 Nov 2023, 11:59 PM

Bangalore International Centre (BIC), Bengaluru

Why Large Language Models are important in AI

In 2020, OpenAI released a Large Language Model (LLM) called GPT3 which has a billion parameters. With a minimal and intuitive user interface which was released to go with GPT3, it caught the imagination and attention of AI communities and researchers all over the world.
One by one, the domain use cases such as co-pilots for coding, creative AI, and other downstream tasks were shown to be fast-tracked by GenerativeAI models and LLMs. As such, there is a wide-ranging interest in large language models and applications around them for various domains and use cases in the AI space. Experiments which aim to find optimal hyperparameters, and those dealing with underfitting and overfitting models are being carried out regularly; more and more barriers are being broken down every day.

The Fifth Elephant 2023 Winter edition will cover topics on the research, engineering, and business aspects of AI, exploring the practical implementation and economic implications of these systems.

Themes

The winter edition of The Fifth Elephant will showcase talks, discussions and demos across generative and multimodal AI, and other classic AI/ML/DL applications on the below themes.

Share approaches and case studies covering the following use cases:

Products and platforms using LLMs, GenerativeAI, ML, and Deep Learning techniques, and business formulation around AI engineering.

Conversational AI and search, automatic speech recognition, healthcare, e-commerce, fintech, media and OTT, and other verticals.

Multilingual needs in India in digital products/platforms - features discussions, models training, finetuning, RLHF, RAGs, quantization techniques, dataset curation and augmentations, challenges faced in pipelines, evaluation metrics, future roadmaps, applications such as multilingual voice bots using ASR/STT, text to speech for accessibility.

Share case studies and experiential talks on handling the operations for data science such as scaling challenges and fine-tuning challenges, and lessons learned, and best practices for incorporating ethics, safety, and bias.

Show demos on features/products which leverage AI and LLM-based APIs and models. It can be from creative AI, generative AI space, and various verticals with relevant use cases.

The Fifth Elephant membership

The December edition will be held in-person. Attendance is open to The Fifth Elephant members only. Pick a membership to attend the in-person conference, and to support The Fifth Elephant’s community activities.

AI/ML/Data Science Ops engineers who want to learn about state-of-the-art tools and techniques, especially from domains such as health care, e-commerce, automobile, agri-tech and industrial verticals

Data scientists who want a deeper understanding of model deployment/governance.

Architects who are building ML workflows that scale.

Tech founders and CTOs who are building products and platforms that leverage AI, ML and LLMs

Product managers, who want to learn about the process of building AI/ML products.

Directors, VPs and senior tech leadership who are building AI/ML teams.

Sponsorship

Sponsorship slots are open for:

Infrastructure (GPU, CPU and cloud providers) and developer productivity tool makers who want to evangelise their offering to developers and decision-makers.

Companies who want to do tech branding among AI and ML developers.

Venture Capital (VC) firms and investors who want to scan the landscape of innovations and innovators in AI and who want to source leads for investment in the AI and ML space.
If you are interested in sponsoring The Fifth Elephant, email sales@hasgeek.com.

Automating Knowledge Extraction for Training Content Generation with LLMs @ SquadStack

Submitted Nov 13, 2023

Abstract

In traditional BPOs, training sales representatives is challenging, primarily due to limited visibility into the universe of knowledge that the representatives have to stay on top of. This limitation often results in suboptimal sales interactions with customers. Furthermore, the creation of thorough and timely training materials is a time-consuming endeavor, even before the actual training can commence. Consequently, this extended preparatory phase delays sales representatives from promptly engaging in customer calls on behalf of the business, resulting in missed opportunities.

As a solution to this problem, SquadStack is in the process of creating an in-house tool, we call Intel Assist, to streamline the extraction of content, for faster and accurate generation and querying of training material for a variety of businesses at a very low cost. This as a result, is empowering our sales representatives to access and utilize this information seamlessly during customer calls.

At its core, we aim for source-agnostic knowledge integration, gathering information from a wide range of sources to enhance documentation and streamline the process of querying this knowledge. While we have initially applied this approach to enhance our internal business processes at SquadStack, it can also benefit other enterprises seeking to bolster their own knowledge management capabilities.

Features

Step 1 - Knowledge Onboarding

Extracting asked Questions, Questions & Answers (QnAs), and Summaries from a variety of raw data sources, including Call Recordings, Word Documents, PDFs, Spreadsheets, and Presentations.
Our comprehensive logging of each question and objection during calls has resulted in a valuable data repository, opening the door to a multitude of analytical insights.
By identifying frequently asked questions and objections, we equip our representatives with the means to improve their preparedness and performance.

Step 2 - Knowledge Sufficiency

Automatically generate a report assessing the alignment of the extracted knowledge with periodic changes and new requirements.
We can precisely discern which of the current questions being posed can be addressed using our existing knowledge base and which ones cannot.
Subsequently, we can present these specific questions to our customers, gather their responses, and incorporate the newfound insights back into our knowledge repository.

Step 3 - Knowledge Search

Swiftly interrogate an extensive knowledge database spanning multiple businesses.
This proves highly effective when sales representatives require real-time access to information that transcends conventional keyword matching.

Technology

In-House ASR for Transcription (Presented at Fifth Elephant Monsoon ‘23)
LLMs
Sentence Transformers for generating embeddings

Impact

Reduction in time required to acquire knowledge
Reduction in the expenses to qcquire knowledge
Accelerated onboarding for new customers, leading to quicker Return on Investment (ROI) delivery for our clients.

Flow of Presentation

SquadStack’s Introduction (1-2 mins)
Product Introduction (5-8 mins)
- Industrial Problems (3-5 mins)
- Overview of our solution - Intel Assist (2-3 mins)
- Introduce ASR as previously showcased in Fifth Elephant Monsoon ‘23 (2-3 mins)
Features (7-12 mins)
- Knowledge Onboarding (3-5 mins)
- Knowledge Sufficiency (3-5 mins)
- Knowledge Search (1-2 mins)
Application’s Lifecycle (3-5 mins)
- What is the direct output of Intel Assist? (Streamlit App)
- How do we provide training?
- Impact (1-2 mins)
- Time Saved
- How can people make use of a tool like this
Audience QnA

Speakers

Sumit Saha

The Fifth Elephant 2023 Winter

Why Large Language Models are important in AI

Themes

AI engineering Track

Data Science operations track

Demo track

The Fifth Elephant membership

Who will benefit from participating in The Fifth Elephant community:

Sponsorship

Contact information