Speaker
Abstract
Assessment of the validity of climate finance claims requires a system that can handle significant variation in language, format, and structure present in climate and financial reporting documentation, and knowledge of the domain-specific language of climate science and finance. In this talk we will go through our process of engineering a software platform based around retrieval augmented generation (RAG) with large language models (LLMs) to accelerate this assessment, from initial prototype to first live product, through the context of our startup growth, and assess the challenges and impacts of engineering a solution with LLMs in the Climate Finance space.
Interview
Evaluation of LLM model quality in the time and resource-constrained environment of an early-stage startup, where LLMs are primarily being used for zero-shot question answering (as opposed to chat). How do we assess what is good vs what is valuable to users?
Applying AI to real-world problems is hard, and the approach of the big players in the industry is obviously not the right fit for small, domain-focused work. I would love to build dialogue around what a strong technical approach with a small team looks like and how to balance deep technical efforts with proving value to users, which is so vital to startups.
I would love to spark discussions with other technical people using LLMs in a startup context, especially those who are looking to solve problems outside the AI toolchain ecosystem. I would also love to engage with anyone applying a tech lens to climate problems. I hope that these kinds of people find my talk engaging.
I would hope that anyone listening walks away with enough of a baseline understanding of how we are using LLMs to answer domain-specific questions, to come up to me afterward and discuss the similarities and differences with their domain, company, and approach.
Topics
QCon London 2024 is a three day conference for senior software engineers, architects and team leads. An international program committee of working engineers selects every session. Patterns and practices, not products and pitches.
From the same track
Monday 8 April
10:35 Windsor (5th Fl.) Session AI/ML Retrieval-Augmented Generation (RAG) Patterns and Best Practices Jay Alammar Director & Engineering Fellow @Cohere & Co-Author of "Hands-On Large Language Models" The rise of LLMs that coherently use language has led to an appetite to ground the generation of these models in facts and private collections of data. 11:45 Mountbatten (6th Fl.) Session AI/ML Navigating LLM Deployment: Tips, Tricks, and Techniques Meryem Arik Co-Founder and CEO @Doubleword (Previously TitanML), Recognized as a Technology Leader in Forbes 30 Under 30, Recovering Physicist Self-hosted Language Models are going to power the next generation of applications in critical industries like financial services, healthcare, and defence. 13:35 Mountbatten (6th Fl.) Session AI/ML Reach Next-Level Autonomy with LLM-Based AI Agents Tingyi Li Enterprise Solutions Architect @AWS Generative AI has emerged rapidly since the release of ChatGPT, yet the industry is still at its very early stage with unclear prospects and potential. 14:45 Mountbatten (6th Fl.) Session AI/ML LLM and Generative AI for Sensitive Data - Navigating Security, Responsibility, and Pitfalls in Highly Regulated Industries Stefania Chaplin, Azhir Mahmood As large language models (LLM) become more prevalent in highly regulated industries, dealing with sensitive data and ensuring the security and ethical design of machine learning (ML) models is paramount. 15:55 Whittle (3rd Fl.) Session AI/ML The AI Revolution Will Not Be Monopolized: How Open-Source Beats Economies of Scale, Even for LLMs Ines Montani Co-Founder & CEO @Explosion, Core Developer of spaCy With the latest advancements in Natural Language Processing and Large Language Models (LLMs), and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big… 17:05 Fleming (3rd Fl.) Session AI/ML How Green is Green: LLMs to Understand Climate Disclosure at Scale Leo Browning First ML Engineer @ClimateAligned Assessment of the validity of climate finance claims requires a system that can handle significant variation in language, format, and structure present in climate and financial reporting documentation, and knowledge of the domain-specific language of climate science and finance.