How to facilitate the adoption of Large Language Models in pharma and finance

By altilia on November 24, 2022

After the initial enthusiasm about Large Language Models (LLMs) due to their impressive results that made them SOTA approaches for some new and traditional general purposes NLP tasks (e.g. question answering, text classification, information retrieval, token sequence tagging, entity extraction, sentiment analysis, intent detection, word sense disambiguation, POS-tagging), now it’s the time of reality.

Peraphs, LLMs are contributing more than computervision to the new AI spring. LLMs are powerful tools that can create great value in industry and help organizations to streamline business processes, improve operations, save a lot of money, and improve business performances. But, as a recent neural article optimally points out, they must be carefully adopted, furthemore they need to be fine tuned to solve specific business problems in vertical domains.

For this reason in Altilia we have built a platform that helps users to fine tune LLMs and control their results by human-in-the-loop AI, augmented intelligence, and composite and adaptive AI tools.

Users in highly specialized areas like pharma, health, and finance have to face problems cited in the article. In particular, LLMs cannot be used as they are. These models  are trained over general available data, hence specific data programming and fine-tuning techniques are needed to make them working in a trustworthy, explainable way on highly specific, regulated, privacy and security sensitive tasks.

Altilia Intelligent Automation platform leverages all LLMs available in huggingface and provides users with tools that allow to curate and program data set to fine-tune LLMs and apply them to solve any NLP and document processing task at the highest level of accuracy and trustworthiness needed by the users operating in highly regulated environments.

For more information read the following use cases: improving NPL data tapes management; enhancing credit scoring for lending applications; Extract ESG data from multiple sources; data extraction from notes to balance sheets.

By altilia on November 24, 2022

Explore more stories like this one

How generative AI is revolutionising business + 7 prompts to streamline your daily work

Imagine a tool that can create almost anything you ask it to: text, images, music and even programming code. Generative AI (GenAI) has emerged not just as a concept, but as a transformative force in the business landscape.   What is Generative AI and why is it so special? Generative AI acts like a super-assistant that doesn't just perform tasks but does so with a note of creativity. It's an innovation that creates content, designs and solutions, effectively turning ideas into reality with little more than a prompt. What sets Generative AI (GenAI) apart is its ability to be a super-assistant in support of human creativity. Unlike traditional AI, which might suggest the next logical data point in a series, Generative AI could imagine an entirely new series. This is because GenAI works by understanding and replicating the complex patterns that make up human-like creations, from artwork to prose. For example, if you ask it to write a poem in the style of Shakespeare, it doesn't just find existing poems; it generates a new poem that feels like it could have been written by the Bard himself. In business, this means that Generative AI doesn't just optimise existing processes; It's an invaluable tool for streamlining complex tasks and problem solving, unlocking the ability to explore countless scenarios and variations that a human alone could never conceive.   Why AI is a Game-Changer for Businesses? Generative AI is transforming business operations by streamlining tasks and reducing costs. It simplifies knowledge management by using AI to quickly answer employee questions and retrieve information. It automates document creation by using templates to generate contracts and reports with less effort. AI also improves data entry by extracting information from documents and populating databases more accurately and quickly. These improvements enable organisations to do more with fewer resources and less time.   The Value Potential The figures are staggering—generative AI could add between $2.6 and $4.4 trillion to the global economy annually. That's more than the GDP of many countries, and as GenAI technology advances, its impact is set to increase (source: McKinsey 2023)   Which Areas Will Benefit? GenAI will significantly advance areas like finance, procurement, HR, legal, and customer service. It will also boost data analysis, business intelligence, and office support. These areas, often heavy with documents, will benefit. The solutions offered by Altilia, for example, automate tedious tasks, thereby increasing efficiency. The impact will also be felt across sectors, from banking to technology to healthcare.   AI helps complete tasks without replacing jobs GenAI doesn't replace jobs. It transforms and enhances them. In fact, AI is really powerful when it performs specific tasks, not entire jobs. At Altilia, we believe that AI can enhance the skills of workers. This is especially true for knowledge workers. It also increases the quality of work and productivity. AI targets repetitive, low-value manual tasks. These tasks provide little value to the organisation. Altilia's solutions aim to empower employees by streamlining repetitive document-based processing tasks. They free employees from tedious tasks. This leaves more time for creative and social activities.   Looking Ahead The rapid changes brought by GenAI are part of the larger evolution of our world. Companies’ adept at leveraging this technology could gain a considerable edge. However, there are challenges to be addressed, like ensuring responsible AI use and preparing people for the changes it will bring. Generative AI is opening a realm of possibilities for companies, making it easier to accomplish tasks that were once time-consuming or even impossible. With every technological advancement comes challenges, but the potential to enhance how we work and live is immense.   7 Prompts to Streamline Work with AI In the ever-evolving landscape of professional environments, the role of Generative AI (GenAI) is becoming increasingly integral. From automating dull tasks to fostering creativity, GenAI is not just a futuristic concept but a present reality enhancing our working life. Here's a closer look at the practical applications of GenAI that are transforming businesses today, exemplifying its versatility and power across various domains: - Content Creation and Enhancement: GenAI can draft text in any desired style and length. Example prompt: "Generate a blog post draft on the impact of interest rate hikes on the real estate market, including key statistics and industry expert quotes."   - Query Resolution in Business Operations: Find precise answers to specific business questions. Example prompt: "Explain the recent amendments to HR policies regarding hybrid work environments and their implications for employees.”   - Communication Tone Adjustment: Tailor the tone of workplace communications to fit the intended audience. Example prompt: "Revise this performance review email feedback to make it more constructive and motivating, focusing on growth and development opportunities."   - Information Summarization: Distil complex documents into easy-to-digest formats. Example prompt: "Summarise the annual financial report into a concise executive summary for the upcoming board meeting, highlighting the five most significant financial KPIs using bullet points."   - Complex Information Simplification: Break down intricate documents for broader accessibility. Example prompt: "Simplify the complex legal terms in our customer service agreements for non-specialist comprehension, and include a section with bullet points summarising the most common questions about our customer service.”   - Customer Feedback Analysis: Analyse customer interactions for service improvements. Example prompt: "Analyse and classify the latest batch of customer service tickets into categories of complaint types, and identify the top three areas for service enhancement."   - Software Coding: Generate, translate, and verify code. Example prompt: "I need a spending tracker app prototype. Can you generate a basic code that works on both iOS and Android using natural language descriptions?"   Emerging Applications: As Generative AI (GenAI) continues to evolve, it’s opening the door to a host of new and compelling applications. These emerging technologies harness the creative power of GenAI to address complex problems and organise unstructured data. A few of the most promising and impactful applications of GenAI for businesses are: Intelligent Document Processing (IDP): This involves using AI to read and understand documents. Imagine you have a huge pile of Complex documents like contracts, financial statements, reports as well. IDP acts like a super-smart assistant that can quickly sift through all these documents, figure out what's important, and even extract the specific information you need. For example, it can help a bank process loan applications faster by automatically extracting applicant details, saving hours of manual work. Intelligent Process Automation (IPA): This takes the idea of robotic process automation (RPA) a step further. Initially, RPA was like teaching a robot to do repetitive tasks, such as entering data into a system. But IPA adds a layer of intelligence to these robots. Now they can not only perform tasks, but also make intelligent decisions based on the data they encounter. For example, an IPA system can automatically handle customer service requests by understanding the customer's problem and either solving it directly or routing it to the right department. Managing unstructured data: This is about organising and understanding data that doesn't fit neatly into tables or databases - think of it as the messy, handwritten notes scattered across your desk. Most of the information we deal with every day, from emails and PDF documents to images and videos, is unstructured. Managing this type of data means using tools and technologies to sift through the clutter, identify the important information and organise it in a way that makes sense for future use. Consider a scenario where a lawyer needs to find specific evidence in thousands of pages of legal documents. Unstructured data management tools can help by quickly finding relevant information and organising it in an easily accessible way, saving hours of manual searching.   To Conclude: In conclusion, Generative AI represents not just a leap forward in technological capabilities, but a transformative shift in how businesses operate, innovate, and compete. As we navigate this exciting landscape, the potential for GenAI to redefine roles, streamline processes, and unlock new realms of creativity is unparalleled. Whether it's improving customer interactions, streamlining document management, or process automation, the implications for efficiency, productivity, and innovation are vast. However, harnessing the full power of GenAI requires more than just technology; it demands expertise and vision to integrate these capabilities into the business strategy effectively. If you're eager to find a solution for your business to streamline processes, reduce the time spent on tasks, and drive growth, we're here to guide you through every step. Book a free consultation with an Altilia expert today, and let's embark on this transformative journey together, unlocking the potential of GenAI to propel your business into the future.

Read more

RAG: a transformative approach that overcomes the limitations of traditional LLM systems

In the evolving landscape of AI, the rapid strides made by Large Language Models (LLMs) bring forth the promise of enhanced efficiency and effectiveness. However, a critical query arises: can these models, despite their impressive advancements, truly excel in business settings without tailored training for business-domain specific tasks? The quandary lies in the limitations faced by these generic models, particularly in highly specialized domains like finance or healthcare, where expert knowledge and nuanced understanding of organizational intricacies are paramount. Utilizing LLMs in these environments pose some challenges regarding their functionality, particularly in their generation of text responses to user queries. These models, while impressive, encounter certain undesired behaviours that pose significant issues. One prevalent issue arises when the answer provided by the LLM lacks credibility or stems from outdated sources, ultimately hindering the end-user's ability to discern the accuracy of the response. In fact, conventional LLMs are trained to swiftly produce a response to a user query, based on its internal knowledge, even if its reference sources are unreputable or out of date. Another problem stems from their lack of transparency, which makes it more difficult for end users to verify the answers. This could lead a propagation of misinformation or unreliable content, potentially eroding trust, and credibility of the generative AI application.  In the fast-evolving landscape of natural language processing (NLP), Retrieval-Augmented Generation (RAG) has emerged as a groundbreaking paradigm, redefining the capabilities of Large Language Models. Within many sectors where data-driven insights are critical for decision-making, RAG presents a transformative approach, surpassing the limitations of traditional Large Language Model (LLM) systems.  RAG represents a hybrid architecture that marries the strengths of both retrieval and generative models. Departing from the conventional approach of relying solely on pre-trained patterns, RAG incorporates an explicit retrieval mechanism, enabling the model to access and leverage information from external knowledge repositories. In a business setting, personalized responses to queries are often essential. RAG allows LLMs to pull personalized information from specific sources pertinent to individual queries. For instance, in HR-related questions, RAG can extract and synthesize information from an employee's records, company policies, or other relevant documents to provide tailored and accurate responses. This way any company can easily index its own documents into RAG and get answers that come directly from its own indexed documents. In essence, the key to the RAG effectiveness lies precisely in the fact that it eases the use of LLMs for company-specific documents and data. Key Components of RAG Retrieval Component The Retrieval Component in RAG is a fundamental aspect of the model's architecture, responsible for accessing and incorporating information from external knowledge sources. This component distinguishes RAG from traditional LLMs by allowing the model to dynamically retrieve relevant data during the generation process. The Retrieval Component is designed to access diverse external knowledge sources, that can include databases, knowledge bases, text corpora, or any repository of information that is relevant to the task at hand. Retrieval Component is initiated by an input query or context provided to the model. This query serves as the basis for retrieving information relevant to the specific task or user prompt. Advanced algorithms are employed to determine the most pertinent information related to the input query, thus enabling a more contextually aware retrieval process. Generation Component The Generation Component in RAG is responsible for synthesizing responses based on the information retrieved by the Retrieval Component and the model's internal knowledge. This component utilizes advanced language generation techniques to produce coherent, contextually relevant, and task-specific outputs. The Generation Component is capable of producing creative and diverse language outputs, going beyond mere regurgitation of retrieved information. This capability is particularly beneficial in generating nuanced and informative responses in various applications. In situations where the input query is ambiguous or requires clarification, the Generation Component can leverage its language generation capabilities to provide informative responses, seeking further clarification if needed. Key Benefits of RAG RAG offers several key benefits that make it a powerful and versatile tool in many industries. Here are some of the key advantages of using RAG: Contextual Relevance RAG excels at providing contextually relevant responses by integrating information retrieved from external sources. This contextual awareness is crucial in understanding and addressing specific queries, making RAG highly effective in tasks that require a deep understanding of context. Enhanced Knowledge Integration RAG seamlessly integrates external knowledge sources into the generation process. This feature is especially valuable in industries where regulations, policies, and market trends are dynamic. By incorporating up-to-date information, RAG enhances decision-making processes and ensures a more accurate and comprehensive understanding of complex scenarios. Improved Accuracy in Responses The retrieval mechanism in RAG enables the model to access precise and relevant information from external databases or knowledge bases. This results in more accurate and reliable responses compared to traditional LLMs that rely solely on pre-existing patterns learned during training. Efficient Data Processing RAG optimizes data processing by efficiently retrieving relevant information. This not only accelerates response times but also reduces the computational resources required for exhaustive searches within large datasets. In tasks where timely decision-making is critical, this efficiency is a significant advantage. Tailored Responses to Specific Queries RAG's ability to retrieve and incorporate information specific to a given query allows it to generate responses that are highly tailored to the user's requirements. This, for example, is particularly beneficial in insurance-related tasks such as policy inquiries, claims assessments and customer interactions, where precision is paramount. Improved Decision Support By combining information retrieval with language generation, RAG provides enhanced decision support. You can leverage the model's capabilities to access relevant data, analyze complex scenarios and make more informed decisions. This contributes to the overall effectiveness of decision-making processes within an organization. Facilitation of Complex Workflows RAG's integration of retrieval and generation components streamlines complex workflows by providing a more seamless transition between accessing external knowledge and generating responses. This facilitates smoother interactions in tasks such as document analysis, legal compliance and risk evaluation. Competitive Edge Organizations adopting RAG gain a competitive edge by harnessing advanced natural language processing capabilities. The model's ability to deliver more contextually relevant and accurate information positions companies to make data-driven decisions with greater confidence, ultimately enhancing their market competitiveness. Customer Engagement and Satisfaction In customer-facing applications, such as virtual assistants or chatbots, RAG can provide more accurate and helpful responses to customer queries. This contributes to improved customer satisfaction and a more positive user experience. How Altilia leverages RAG to enhance its IDP capabilities Altilia has been pioneering the use of LLMs for IDP applications, to read and understand documents automatically, with the ultimate goal of automating processes that require manual information extraction from unstructured data and documents (discriminative AI), and to allow customers to “talk” with their internal document knowledge base, through an easy-to-use conversational UI that answers natural language questions (generative AI). With the limitations of LLMs already highlighted in the article, the next step for Altilia is integrating RAG technology to extend its current IDP capabilities and provide a state-of-the-art IDP platform. RAG allows us to obtain more accurate results and up-to-date answers, based on external knowledge sources rather than just on the LLM’s own internal knowledge (in our context an external knowledge source is the customer’s own document knowledge base). This minimizes the "hallucination" problems that are typical of generative AI applications, based on LLM algorithms, leading to a substantial set of benefits to the client, as already highlighted in the article. We are implementing RAG with a plug’n’play and accurate approach in Altilia Intelligent Automation (AIA), our next-generation AI assistant and automator, to improve results and extend the capabilities of Discriminative AI algorithms, retrieve pertinent passages where to find relevant data, let users to talk with documents by prompts and allow users to generate new documents on the base of extracted data and document contents. Novel RAG capabilities extend current Intelligent Document Processing (IDP) features of the AIA Platform and make Altilia a new challenger player in the Generative AI market. For more information on how Altilia can support your business, schedule a demo here.

Read more

How can Intelligent Document Processing serve your organization?

Intelligent Document Processing (IDP) refers to the use of advanced technologies, such as artificial intelligence (AI) and machine learning (ML), to automate the extraction, understanding, and processing of information from various types of documents. IDP aims to streamline and enhance document-centric workflows by leveraging cognitive capabilities to interpret unstructured data found in documents such as invoices, contracts, and forms. Through the application of natural language processing (NLP), advanced computer vision and other intelligent algorithms, IDP systems can recognize patterns, extract relevant data, and even comprehend the context of information within documents. This enables organizations to automate tedious and error-prone manual document processing tasks, improving efficiency, accuracy and overall productivity. The more advanced Intelligent Document Processing (IDP) solutions, utilise a combination of AI technologies, including Computer Vision and Natural Language Processing (NLP). In document capture, computer vision digitizes physical documents and employs Optical Character Recognition (OCR) to extract text from images or scans. Computer vision algorithms also recognize patterns and structures within documents, aiding in context understanding and data extraction from unstructured formats. Natural Language Processing (NLP), on the other hand, breaks down texts for identifying key information and relationships. It enables IDP systems to comprehend natural language, ensuring context-aware interpretation. Additionally, NLP techniques facilitate document summarization, extracting key insights. When combined with rule-based processing, NLP enhances IDP systems' adaptability to various document types and formats. What makes Altilia different from other players in the IDP space? Altilia Intelligent Automation (AIA) is an IDP platform that utilizes cutting-edge technologies to take IDP to the next level, including: Large Language Models (LLMs) with RAG (Retreival Augmmented Generation) to enhance its natural language processing capabilities Models fine-tuning adapt language model to suit specific use case tailored and customer tailored applications Knowledge graphs to represent data and information alongside with the interrelations between them, making the models better understand the documents and simplifying the access to informations Advanced Computer Vision technology, including OCR, HTR (Handwritten Text Recognition) and patented DAR (Document Analysis and Recognition), to better interpret the layout and the spatial information of the documents What can your organization achieve with IDP? Reduce the manual workload and associated costs Speed up operational and decision-making processes (shorter lead time / time to answer) Increase the capability of processes that require documents analysis and data retrieval (more operations managed in a given time-frame) Higher accuracy of extracted data by eliminating human errors in the process Improved accessibility to information contained in large documents datasets / knowledge bases utilized by the organization Real world application examples of Altilia Intelligent Automation Although with a focus in banking and finance industry, AIA is a general-purpose platform that can process any kind of documents for any industry. Here are some examples: Banking and insurance sectors Increase the ability and speed of reading and analyzing financial statements for profiling the bank's corporate customers and selling derivative products Analyze Non-Performing Loans (NPL) file documents to support the evaluation of NPL portfolios and to estimate the likelihood of credit recovery Increase capacity and speed data extraction from documents related to claims and/or court documents for insurance companies. Increase the ability to search for information found within pension regulations and documents related to products offered to clients; the ultimate goal is to provide an AI assistant (similar to ChatGPT) that can respond to personal pension advisors Manufacturing and utilities sectors Automatic reading of documents sent by suppliers to simplify supplier evaluation and selection for the procurement office Reading and analyzing CVs with automatic matching of sought skills to expedite the HR department's recruitment activities Automatic reading and classification of action reports (activations, modifications and plant decommissioning) to simplify asset management operations for companies in the utilities sector Automatic reading of bills, invoices and photos of meter self-readings to simplify the administrative management of energy and gas distribution companies Training of conversational AI assistant (similar to ChatGPT) to provide real-time support regarding technical intervention procedures to support asset management operations for companies in the utilities sector Thanks to its capabilities in 2022 Altilia has been recognized by Gartner a Representative Vendor in Market Guide on Iintelligent Document Processing. In 2023, IDC MarketScape hase recognized Altilia as a “Major Player” in its Worldwide IDP Vendor Assessment. Why not schedule a demo with Altilia to learn more about how we can help transform your organization? Click here to register.   

Read more