{
  "docId": "019dd923-5e88-73ef-bd59-174b7f7da09c",
  "docSlug": "d9ee2fdc0bd7b0ec",
  "documentTitle": "enhaced data extraction using gen ai ey collaboration with wlastic",
  "authorId": "MorganStanley",
  "authorName": "EY",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "equity_research",
  "sourceTypeLabel": "Equity research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.778,
  "pageNumber": 3,
  "pageCount": 16,
  "prevPage": 2,
  "nextPage": 4,
  "slideType": "problem_statement",
  "function": "frame_problem",
  "density": "overcrowded",
  "nDataPoints": 0,
  "notes": null,
  "elementsJson": [
    "paragraph",
    "icon_grid",
    "photo"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/3",
  "deckHref": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-3",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Let's take a look at varying retrieval and language model strategies that can offer innovative information retrieval methods for the financial services sector.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-340f-723f-8a12-acec86f426b7",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 1,
        "w": 0.3,
        "x": 0.33,
        "y": 0
      },
      "kind": "image",
      "text": null,
      "attrs": null,
      "subkind": "photo",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "e01240c0-1775-44b2-a5a8-bc0c3da1cd39",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.08,
        "w": 0.23,
        "x": 0.715,
        "y": 0.28
      },
      "kind": "list",
      "text": "Large language models (LLMs) may generate hallucinations – responses that are out of context – that result in unreliable outcomes.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "1051dcd9-e998-40c6-b081-df46434a3f5a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.23,
        "x": 0.715,
        "y": 0.46
      },
      "kind": "list",
      "text": "Cost and speed constraints can result in limited scalability across extensive source databases.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "17d15d7b-e89d-4ceb-b67a-3fd9f54d114f",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.23,
        "x": 0.715,
        "y": 0.63
      },
      "kind": "list",
      "text": "Out-of-the-box LLMs and search engines are difficult to set up for the most suitable parameters",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "77421fd7-adfb-4719-bdab-4fece332a088",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.3,
        "x": 0.648,
        "y": 0.77
      },
      "kind": "paragraph",
      "text": "Let's take a look at varying retrieval and language model strategies that can offer innovative information retrieval methods for the financial services sector.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "0570b29c-90f6-4063-8e28-8023a27062c8",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.3,
        "x": 0.648,
        "y": 0.18
      },
      "kind": "paragraph",
      "text": "Organizations that have attempted to implement gen AI solutions have quickly encountered new challenges, including:",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "05c733c8-269f-4834-8d19-7f7d2fda7c13",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.28,
        "x": 0.048,
        "y": 0.33
      },
      "kind": "paragraph",
      "text": "Alternatively, organizations had to build their own extraction pipelines, an endeavour that came with its own challenges. But with the advent of gen AI, the entire financial services industry has been disrupted, resulting in a lasting change in the field of data extraction.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "509e7518-9c91-4976-bb38-808c047aefb4",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.28,
        "x": 0.048,
        "y": 0.48
      },
      "kind": "paragraph",
      "text": "Gen AI can autonomously analyze and interpret vast amounts of unstructured data with unprecedented accuracy and speed, using natural language processing and machine learning algorithms. These innovative capabilities include contextual understanding, pattern recognition and the generation of coherent data summaries, which significantly reduce the time and resources required to extract data.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7c0b9918-e7f4-4b5d-a1ba-bb6bd07ccb6b",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.28,
        "x": 0.048,
        "y": 0.18
      },
      "kind": "paragraph",
      "text": "Data extraction has always been challenging, particularly when dealing with unstructured, inconsistent, and notably large amounts of data. Organizations have often relied on external data providers, which was not only costly but also not always up-to-date or live.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "e6a9978a-646c-4b44-84a4-dce7c5f8044e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.19,
        "x": 0.048,
        "y": 0.095
      },
      "kind": "title",
      "text": "Introduction",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "bea0df2d-f148-421f-8718-4ebfbad589e0",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 4,
      "from": 3,
      "beatId": "e3077b66-a96d-4be2-9521-145f02396c38",
      "arcName": "The Consultant's Gambit",
      "arcSlug": "consultants-gambit",
      "beatName": "Situation & Context",
      "beatSlug": "consultants-gambit-situation-context",
      "evidence": "The deck provides an introduction to the current state and main challenges of data extraction",
      "position": 0,
      "confidence": 0.8,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    }
  ],
  "loops": [
    {
      "to": 6,
      "from": 3,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "565e85cb-f579-4e65-a33a-b008d293d5f2",
      "evidence": "The deck presents a problem statement and a proposed solution using Gen AI",
      "position": 0,
      "objective": "Identify patterns in current data extraction methods",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 0.6,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}