recommendations Articles - Enterprise Knowledge https://enterprise-knowledge.com/tag/recommendations/ Mon, 17 Nov 2025 21:49:23 +0000 en-US hourly 1 https://wordpress.org/?v=6.8.2 https://enterprise-knowledge.com/wp-content/uploads/2022/04/EK_Icon_512x512.svg recommendations Articles - Enterprise Knowledge https://enterprise-knowledge.com/tag/recommendations/ 32 32 Synergizing Knowledge Graphs with Large Language Models (LLMs): A Path to Semantically Enhanced Intelligence https://enterprise-knowledge.com/synergizing-knowledge-graphs-with-large-language-models-llms/ Tue, 02 Apr 2024 16:06:08 +0000 https://enterprise-knowledge.com/?p=20280 Why do Large Language Models (LLMs) sometimes produce unexpected or inaccurate results, often referred to as ‘hallucinations’? What challenges do organizations face when attempting to align the capabilities of LLMs with their specific business contexts? These pressing questions underscore the … Continue reading

The post Synergizing Knowledge Graphs with Large Language Models (LLMs): A Path to Semantically Enhanced Intelligence appeared first on Enterprise Knowledge.

]]>
Why do Large Language Models (LLMs) sometimes produce unexpected or inaccurate results, often referred to as ‘hallucinations’? What challenges do organizations face when attempting to align the capabilities of LLMs with their specific business contexts? These pressing questions underscore the complexities and potential problems of LLMs. Yet, the integration of LLMs with Knowledge Graphs (KGs) offers promising avenues to not only address these concerns but also to revolutionize the landscape of data processing and knowledge extraction. This paper delves into this innovative integration, exploring how it shapes the future of artificial intelligence (AI) and its real-world applications.

 

Introduction

Large Language Models (LLMs) have been trained on diverse and extensive datasets containing billions of words to understand, generate, and interact with human language in a way that is remarkably coherent and contextually relevant. Knowledge Graphs (KGs) are a structured form of information storage that utilizes a graph database format to connect entities and their relationships. KGs translate the relationships between various concepts into a mathematical and logical format that both humans and machines can interpret. The purpose of this paper is to explore the synergetic relationship between LLMs and KGs, showing how their integration can revolutionize data processing, knowledge extraction, and artificial intelligence (AI) capabilities. We explain the complexities of LLMs and KGs, showcase their strengths, and demonstrate how their combination can lead to more efficient and comprehensive knowledge processing and improved performance in AI applications.

 

Understanding Generative Large Language Models

LLMs can generate text that closely mimics human writing. They can compose essays, poems, and technical articles, and even simulate conversation in a remarkably human-like manner. LLMs use deep learning, specifically a form of neural network architecture known as transformers. This architecture allows the model to weigh the importance of different words in a sentence, leading to a better understanding of language context and syntax. One of the key strengths of LLMs is their ability to understand and respond to context within a conversation or a text. This makes them particularly effective for applications like chatbots, content creation, and language translation. However, despite the many capabilities of LLMs, they have limitations. They can generate incorrect or biased information, and their responses are influenced by the data they were trained on. Moreover, they do not possess true understanding or consciousness; they simply simulate this understanding based on patterns in data.

 

Exploring Knowledge Graphs

KGs are a powerful way to represent and store information in a structured format, making it easier for both humans and machines to access and understand complex datasets. They are used extensively in various domains, including search engines, recommendation systems, and data integration platforms. At their core, knowledge graphs are made up of entities (nodes) and relationships (edges) that connect these entities.  This structure allows for the representation of complex relationships between different pieces of data in a way that is both visually intuitive and computationally efficient. KGs are often used to integrate structured and unstructured data from multiple sources. This integration provides a more comprehensive understanding of the data by providing a unified view. One of the strengths of KGs is the ease with which they can be queried. Technologies like SPARQL (a query language for graph databases) enable users to efficiently extract complex information from a knowledge graph. KGs find applications in various fields, including search engines (like Google’s Knowledge Graph), social networks, business intelligence, and artificial intelligence.

 

Enhancing Knowledge Graph Creation with LLMs

KGs make implicit human knowledge explicit and allow inferences to be drawn from the information they are provided. The ontology, or graph model, serves as anchors or constraints to these inferences. Once created and validated, KGs can be trusted as a source of truth, they make inferences based on the semantics and structure of their model (ontology). Because of this element of human intervention, humans can ensure that the interpretation of information is correct for the given context, in particular alleviating the ‘garbage in – garbage out’ phenomenon. However, because of this human intervention, they can also be fairly labor-intensive to create. KGs are created using one of a couple types of graph database frameworks, they are generally dependent on some form of human intervention and are generated by individuals with a specialized skill set and/or specialized software. To access the information in a Knowledge Graph they must be stored in an appropriate graph database platform and require the use of specialized query languages to query the graph. Because of these specialized skills and a high degree of human intervention, knowledge graphs can be time-consuming and labor-intensive to create. 

Enhancing KG Creation with LLMs through Ontology Prompting

There is an established process for creating a complete knowledge graph. After data collection, LLM processing and structuring for the knowledge graph make up the bulk of the work.

Through a technique known as ontology prompting, LLMs can effectively parse through vast amounts of unstructured text, accurately identify and extract pertinent entities, and discern the intricate relationships between these entities. By understanding and leveraging the context in which data appears, these models are not only capable of recognizing diverse entity types (such as people, places, organizations, etc.) but can also delineate the nuanced relationships that connect these entities. This process significantly streamlines the creation and enrichment of KGs, transforming raw, unstructured data into a structured, interconnected web of knowledge that is both accessible and actionable. The integration of LLMs into KG construction not only enriches the data but also significantly augments the utility and accuracy of the knowledge graphs in various applications, ranging from semantic search and content recommendation to advanced analytics and decision-making support.

 

Improving LLM Performance with Knowledge Graphs

The integration of KGs into LLMs offers substantial performance improvements, particularly in enhancing contextual understanding, reducing biases, and boosting accuracy. KGs inject a semantic layer of contextual depth into LLMs, enabling these models to grasp and process language with a more nuanced understanding of the subject matter. This interaction significantly enhances the comprehension capabilities of LLMs, as they become more adept at interpreting and responding to complex queries with enhanced precision. Moreover, the structured nature of KGs aids in mitigating biases inherent in LLMs. By providing a balanced and factual representation of information, KGs help neutralize skewed perspectives and promote a more objective and informed generation of content. Finally, the incorporation of KGs into LLMs has been instrumental in enhancing the accuracy and reliability of the output generated by LLMs.

A contextual framework for enhancing large language models with knowledge graphs. Knowledge Graphs boost accuracy & reliability, reduce bias, improve comprehension, inject contextual depth, and provide a semantic layer of context for LLMs.

The validated data from KGs serve as a solid foundation, and reduce ambiguities and errors in the information processed by LLMs, thereby ensuring a higher quality of output that is trustworthy, traceable, and contextually coherent.

 

Case Studies and Applications

The integration of LLMs and KGs is making significant advances across various industries and transforming how we process and leverage information. For instance, in the finance sector, LLMs combined with KGs are used for risk assessment and fraud detection. These systems analyze transaction patterns, detect anomalies, and understand the relationships between different entities, helping financial institutions mitigate risks and prevent fraudulent activities.  Another example is personalized recommendation systems. E-commerce platforms like Amazon utilize KGs and LLMs to understand customer preferences, search histories, and purchase behaviors. This integration allows for highly personalized product and content recommendations, improving customer experience and increasing sales and engagement. In the legal industry LLMs and KGs are used to analyze legal documents, case laws, and statutes. They help in summarizing legal documents, extracting relevant clauses, and conducting research, thereby saving time for legal professionals and improving the accuracy of legal advice. The potential of LLM and KG integrations is unlimited, promising transformative advancements across sectors. For example, leveraging LLMs and KGs can transform educational platforms, guiding learners through tailored and personalized educational journeys. In healthcare, the innovation in sophisticated virtual assistants is revolutionizing telemedicine, offering preventive care and preliminary diagnoses. Urban planning and management stand to gain immensely from this technology, enabling smarter city planning through the analysis of diverse data sources, from traffic patterns to social media sentiments. Moreover, the research and development are set to accelerate, with LLMs and KGs synergizing to automate literature reviews, foster novel research ideas, and predict experimental outcomes. 

The impact of large language models and knowledge graph integration is far reaching. It affects a wide range of industries, including healthcare, urban planning, research & development, finance, law, education, and e-commerce.

Challenges and Considerations

While the integration of LLMs and KGs is promising, it is accompanied by a set of significant challenges and considerations. From a technical perspective, merging LLMs with KGs needs sophisticated algorithms capable of handling the complexity of KG structures and the nuances of natural language processed by LLMs. For example, ensuring data compatibility, maintaining real-time data synchronization, and managing the computational load are difficult tasks that require advanced solutions and ongoing innovation. Moreover, ethical and privacy concerns are one of the top challenges of this integration. The use of LLMs and KGs involves processing vast amounts of data some of which may be sensitive or personal. Ensuring that these technologies adhere to privacy laws and regulations, maintain data confidentiality, and make ethically sound decisions is a continuous challenge.  There’s also the risk of perpetuating biases present in the training data of LLM that require meticulous oversight and implementation of bias-mitigation strategies. Furthermore, the sustainability of these advanced technologies cannot be overlooked. The energy consumption associated with training and running large-scale LLMs and maintaining extensive KGs poses significant environmental concerns. As the demand for these technologies grows, finding ways to minimize their carbon footprint and developing more energy-efficient models is important. Addressing these technical, ethical, and sustainability challenges is crucial for the responsible and effective implementation of LLM and KG integrations.

 

Conclusion

In this white paper, we explored the dynamic interplay between LLMs and KGs, unraveling the profound impact of their integration on various industries. We delved into the transformative capabilities of LLMs in enhancing the creation and enrichment of KGs, highlighting automated data extraction, contextual understanding, and data enrichment. Conversely, we discussed how KGs can improve LLM performance by imparting contextual depth, mitigating biases, enabling source traceability, and increasing accuracy and reliability. We also showcased the practical benefits and revolutionary potential of this synergy. In conclusion, the combination of LLMs and KGs stands at the forefront of technological advancement and directs us toward an era of enhanced intelligence and informed decision-making. However, fostering continued research, encouraging interdisciplinary collaboration, and nurturing an ecosystem that prioritizes ethical considerations and sustainability is important.

Want to jumpstart your organization’s use of LLMs? Check out our Enterprise LLM Accelerator and contact us at info@enterprise-knowledge.com for more information! 

 

About this article

This is an article within a linked series written to provide a straightforward introduction to getting started with language models (LLMs) and knowledge graphs (KGs). You can find the next article in the series here.

The post Synergizing Knowledge Graphs with Large Language Models (LLMs): A Path to Semantically Enhanced Intelligence appeared first on Enterprise Knowledge.

]]>
KM Strategy for a Multinational Software Company https://enterprise-knowledge.com/km-strategy-for-a-creative-software-company/ Fri, 15 Jul 2022 15:11:50 +0000 https://enterprise-knowledge.com/?p=15695 The Challenge A multinational software company partnered with EK to conduct a four-month enterprise Knowledge Management (KM) Strategy Assessment of its organization to identify and analyze KM practices and technologies currently in place and to provide actionable recommendations on opportunities … Continue reading

The post KM Strategy for a Multinational Software Company appeared first on Enterprise Knowledge.

]]>

The Challenge

A multinational software company partnered with EK to conduct a four-month enterprise Knowledge Management (KM) Strategy Assessment of its organization to identify and analyze KM practices and technologies currently in place and to provide actionable recommendations on opportunities for improvement, specifically focusing on product teams and their respective needs.

In looking to mature their KM capabilities, this organization desired to ensure that its knowledge resources were easily findable, accessible, timely, clear, accurate, complete, and trusted to support their globally distributed employees as they continue to grow, drive innovation, and deliver seamless digital experiences to their customers. More specifically, this organization brought on EK to conduct an enterprise KM Strategy because it was looking to achieve the following solutions:

  • Shape their Future of Work effort and increase accessibility to content across platforms that support remote work. The decentralized nature of the organization enables individual teams to acquire and use different communication and collaboration platforms, and often results in duplicative work and diverging approaches to KM processes across the company.
  • Expand the overall understanding of the importance of KM on an enterprise level with an emphasis on integration into product teams.
  • Centralize search engines and results and implement KM Strategy to optimize the available technologies. Employees must currently navigate a landscape of fragmented knowledge bases and limited search capabilities across multiple, sometimes overlapping, tools.
  • Explore Knowledge Graphs and Artificial Intelligence within the context of KM to drive advanced search features and dynamic search results.

Throughout the engagement, it became clear that this organization’s goal was not just to manage, but to thrive, in the hybrid work environment; EK aimed to align with and support other focused initiatives at the company, improving findability across all of their technologies and ensuring that every employee had the same access to these resources, regardless of their physical location.

The Solution

Over the course of four months, EK facilitated focus groups and interviews with team members from across various business units at the organization to gather a diverse array of perspectives and establish a reference point upon which to analyze their current state and measure future success. The baseline scores for each workstream (People, Process, Content, Culture, Technology) within EK’s proprietary KM Maturity Benchmark were provided to the organization to allow them to gain an understanding of which factors were the most impactful on KM across the organization, as well as strengths they could leverage and areas where they could improve. Through these activities and a review of pertinent systems and documentation, EK identified critical business needs surrounding KM and the challenges that team members faced.

After a thorough analysis of their present capabilities, EK again utilized our KM Maturity Benchmark and collaborated with the company to prioritize three areas of focus:

  • Enterprise Search: Implement a universal enterprise search tool to locate and pull content from all integrated systems and repositories across the enterprise, and present action-oriented search results in an intuitive manner to enable employees to find the answer to their query before or at the time of need.
  • Content Strategy: Develop an enterprise content strategy to address current and future processes for content management, with the intent of mitigating unstructured content that is duplicative, obsolete, or outdated.
  • KM Leadership: Establish an enterprise-wide approach to KM leadership, and formalize responsibilities for securing and procuring KM resources.

These recommendations, among others, were leveraged to create a fully customized, actionable KM Roadmap spanning three years, outlining activities, their estimated duration, and the order in which to approach them to guide the development of current KM practices at the organization.

The EK Difference

In EK’s conversations with the organization’s core team and stakeholders, we observed a keen interest in implementing Artificial Intelligence (AI) within the organization, but no enterprise-level guidance to do so. We dug deeper to understand and learn more about their desires for AI concurrent to our assessment of their organization. To help educate and support the organization in their journey to Enterprise AI, EK held an AI Knowledge Share for approximately 50+ employees. EK also outlined three pilots that could be pursued to achieve more advanced Artificial Intelligence (AI) capabilities, providing staff with powerful tools to find and discover information at the time of need.

A key element of our assessment was the usage of EK’s proprietary KM Maturity Benchmark to analyze the strengths and weaknesses of the five KM workstreams within the organization – People, Process, Content, Culture, and Technology. Each factor in the benchmark is based on proven KM best practices and denotes measurable practices and characteristics within an organization which are then evaluated by our team of impartial experts, reducing bias in defining the current state of KM at the organization and providing them with an industry-relevant, quantifiable measurement of their KM maturity. This analysis allowed EK to provide a practical baseline for context-based recommendations and ensured that we delivered a highly detailed and actionable plan for solving the organization’s KM needs.

EK approached this project with a unique combination of “soft” and “hard” recommendations and techniques, bridging the gap between KM concepts (people, process, content, culture) and practical KM solutions (technology, integrations). By combining employee focus groups and interviews with a quantifiable benchmark, EK was able to address each type of challenge in the organization, from search and content difficulties to a desire for greater KM expertise and leadership.

The Results

Over the course of this engagement, EK provided the organization with the following:

  • Current State Assessment and Benchmark that assessed KM practices and tools throughout the organization, providing them with a deeper understanding of their KM maturity level and identifying high-impact areas for improvement;
  • Target State Assessment and Benchmark that defined the future state of KM at the company, focusing on the improvements that will yield the greatest impact and business value. The Target State represents a realistic vision for what the organization can achieve upon improvement beyond the current baseline; and
  • A fully customized, iterative, task-based KM Roadmap and Recommendations that addressed this organization’s KM needs and gaps to help the organization enhance its overall KM maturity and achieve its strategic objectives. The Roadmap included 14 recommended activities focused on Enterprise Search, Content Strategy, and KM Leadership, as well as provided metrics upon which to measure the organization’s success to help emphasize the business value of knowledge management to stakeholders and leadership.

Leveraging these deliverables will allow this organization to increase employee engagement by supporting cross-functional communication, enabling employees to work more efficiently and share knowledge more effectively. This will also boost productivity and increase rates of collaboration, retention, and satisfaction while cultivating innovation and creativity within the organization by building connection and collaboration among employees. The company will also be able to enhance their client reputation by eliminating discrepancies in product documentation and providing their employees the tools to better support customers, drive company performance by increasing exposure to new ideas across the enterprise, and secure information in shared spaces to prevent unintentional disclosures. Finally, these deliverables will ensure alignment across teams to a single set of goals and expectations for Enterprise AI, grounding the company in a future-oriented mindset.

The post KM Strategy for a Multinational Software Company appeared first on Enterprise Knowledge.

]]>
Integrated Change Management Plan for Top Telecommunications Company https://enterprise-knowledge.com/integrated-change-management-plan-for-top-telecommunications-company/ Thu, 17 Jun 2021 13:07:46 +0000 https://enterprise-knowledge.com/?p=13301 The Challenge Their Challenge: One of the top telecommunication companies in the world is pursuing an ambitious corporate strategy that entails a digital transformation of its entire operations, expanding its service offerings, and exploiting new business opportunities to become a … Continue reading

The post Integrated Change Management Plan for Top Telecommunications Company appeared first on Enterprise Knowledge.

]]>

The Challenge

Their Challenge:

One of the top telecommunication companies in the world is pursuing an ambitious corporate strategy that entails a digital transformation of its entire operations, expanding its service offerings, and exploiting new business opportunities to become a global reference point and leader within its industry. They sought a partnership with Enterprise Knowledge (EK) to assess the company’s current knowledge management (KM) maturity and elaborate a vision for future KM capabilities and practice that would support this corporate agenda. 

During the process of defining a KM Strategy and Roadmap to guide the company in increasing its KM maturity, EK surfaced important considerations – based on the company’s culture and staff’s experience with past changes – that would need to be addressed when implementing the KM Strategy and Roadmap and introducing the associated changes:

  • Communication around past initiatives has been either too complex for staff to understand the initiative’s value or hasn’t been sufficiently targeted to specific employee groups. Staff hasn’t had a clear understanding of how a change will benefit them, resulting in reduced engagement. 
  • The company hasn’t typically established two-way communication channels during a change initiative to address concerns, mitigate resistance, correct misinformation, and allow for input that can drive improvements to those overseeing a change.
  • Staff primarily follow vertical lines of communication to share information from senior leadership to non-supervisory employees. As a result, important information doesn’t always trickle down to non-supervisory employees
  • Those in middle management have not been fully “activated” – they aren’t always communicating in a way to help their employees understand the need for and impact of an organizational change, nor are they holding their staff accountable to requested changes.
  • There are many concurrent activities that are requiring staff to take on new projects and responsibilities, adapt to new requirements, and adjust ways of working. Staff are experiencing varying levels of change fatigue, and express uncertainty over how these initiatives are aligned and where to focus their attention.
  • There are groups within the company who are more heavily invested in how things are done today as well as those who are more responsive to change. This reality plays out in the varying degrees to which people are willing to share information with their colleagues. 

The Solution

As part of EK’s nine-month, enterprise-wide effort to assess the company’s current KM maturity and elaborate a vision for future KM capabilities and practices, EK developed an Integrated Change Management Plan to support the implementation of the KM Strategy and Roadmap. To define a bespoke set of change management recommendations and communication practices, EK engaged internal stakeholders to discuss 1) lessons learnt from their past experiences with organizational changes, 2) the critical factors that mean the difference between success and failure on a project or change initiative, and 3) how information gets distributed across the organization and top down. EK disseminated and analyzed results of a KM survey to surface staff perspectives on what motivations (e.g., incentives, rewards, and recognition) could be offered or would be desired to support KM practices. Additionally, EK led interviews and workshops that informed our understanding of the company’s organizational structure, lines of authority, information flow patterns, cultural nuances, and those who could serve as key partners in supporting the KM Strategy and Roadmap. 

The Integrated Change Management Plans includes:

  • A purpose statement to generate momentum and align on what success is anticipated to look like as a result of implementing the KM Strategy and Roadmap.
  • A list of success indicators and preliminary activities to guide the company’s change management strategy and track whether outcomes are being realized. 
  • The people who will be impacted by and whose involvement will be necessary in the implementation of the KM Strategy and Roadmap.
  • Critical messages to use and considerations to keep in mind when communicating about the KM Strategy and Roadmap.
  • Recommendations for how to address risks that are unique to the company’s culture and organization and that could jeopardize success of the KM Strategy and Roadmap if left unattended. 

The EK Difference

EK engaged the company’s KM project team in helping to define what success will look like for its KM Strategy throughout the implementation of the two-year Roadmap. Through holding a Visioning workshop with the KM project team, EK was able to co-create success indicators – i.e., outcome-based statements that are specific and measurable – that would ultimately support the company in tracking whether it is realizing the outcomes it hopes to achieve with a KM Strategy. This co-creation session was critical to gaining alignment on what success will look like and identifying a “North Star” for the Strategy. By engaging the KM project team as partners in this process, EK was able to understand what meaningful success looks like and develop a process that the company can use to define: corresponding metrics for each success indicator; the critical behaviors that will need to be performed consistently by the company’s workforce to bring about success; and the ways in which the company can provide support for critical behaviors to ensure those behaviors occur at the desired consistency and rate. 

The Results

The company was appreciative of the detail and customization that were evidenced in the Integrated Change Management Plan. The company continues to work with EK to provide training to KM team members focused on strengthening their ability to manage and lead change. With the Integrated Change Management Plan, the company’s KM Leadership Team are well equipped to: 

  • Give the implementation of the KM Strategy and Roadmap high relevance and visibility;
  • Facilitate open communication about the Strategy’s purpose and desired outcomes;
  • Educate employees on how they can expect to benefit from having more robust knowledge capture, storing, and sharing practices in place;
  • Communicate the roles, responsibilities, and expectations of leadership, middle management, and non-supervisory staff in leading and supporting the rollout of the KM Roadmap; and
  • Make data-driven decisions on how to pivot communication and engagement strategies as needed.

The company’s Integrated Change Management Plan provides recommendations that will support the company’s workforce in sustainably adjusting to new ways of creating, managing, storing, and sharing knowledge, information and data. With an Integrated Change Management Plan to accompany its KM Strategy and Roadmap, the company is well positioned to realize its corporate agenda and goals of enabling staff to exchange knowledge, experience, and insights in support of collaborative problem-solving, decision-making, and the development of transformative services and platforms.

The post Integrated Change Management Plan for Top Telecommunications Company appeared first on Enterprise Knowledge.

]]>
What is the Roadmap to Enterprise AI? https://enterprise-knowledge.com/enterprise-ai-in-5-steps/ Wed, 18 Dec 2019 14:00:57 +0000 https://enterprise-knowledge.com/?p=10153 Artificial Intelligence technologies allow organizations to streamline processes, optimize logistics, drive engagement, and enhance predictability as the organizations themselves become more agile, experimental, and adaptable. To demystify the process of incorporating AI capabilities into your own enterprise, we broke it … Continue reading

The post What is the Roadmap to Enterprise AI? appeared first on Enterprise Knowledge.

]]>
Artificial Intelligence technologies allow organizations to streamline processes, optimize logistics, drive engagement, and enhance predictability as the organizations themselves become more agile, experimental, and adaptable. To demystify the process of incorporating AI capabilities into your own enterprise, we broke it down into five key steps in the infographic below.

An infographic about implementing AI (artificial intelligence) capabilities into your enterprise.

If you are exploring ways your own enterprise can benefit from implementing AI capabilities, we can help! EK has deep experience in designing and implementing solutions that optimizes the way you use your knowledge, data, and information, and can produce actionable and personalized recommendations for you. Please feel free to contact us for more information.

The post What is the Roadmap to Enterprise AI? appeared first on Enterprise Knowledge.

]]>