Shayoni Dutta

👉🏼 Potential roles of large language models in production of systematic reviews and meta-analyses 🤓 Xufei Luo 👇🏻 https://lnkd.in/eVTxQ6Ce 🔍 Focus on data insights: - Large language models (LLMs) like ChatGPT are increasingly utilized in medical research. - LLMs can expedite steps in systematic reviews such as defining clinical questions, literature search, and information extraction. - Attention to transparent reporting and avoiding academic misconduct is crucial when using LLMs. 💡 Main outcomes and implications: - Enhanced efficiency and resource conservation in systematic reviews with the use of LLMs. - Need for clear differentiation between genuine and false content generated by LLMs. - Future research directions to maximize the benefits of LLMs in systematic reviews. 📚 Field significance: - Advancements in utilizing LLMs for systematic reviews and meta-analyses. - Importance of ethical considerations and quality control when integrating LLMs in research processes. 🗄️: [#medicalresearch #systematicreviews #LLMs #efficiency #ethics]

1

1 Comment

Large language models (LLMs) are evolving beyond answering questions to excelling in agentic workflows, where they reflect, plan, and collaborate to achieve tasks. Andrew Ng highlights how features like function calling, retrieval-augmented generation, and even computer use (e.g., Anthropic’s recent innovations) are driving this shift. Key takeaways: • Developers are exploring agentic behaviors using prompts and fine-tuning for critical applications. • LLMs now natively integrate tools, improving reliability and efficiency for workflows. • Expect major advancements as models increasingly support agentic tasks by design. This trend promises significant performance gains for AI agents in the coming years. Learn more in Andrew Ng’s article: bit.ly/3QEsQfh #AIWorkflows #AgenticAI #FutureOfLLMs

34

1 Comment

**Introducing GraphRAG by Microsoft Research!** GraphRAG, now available on GitHub, is a tool for complex data discovery. It leverages a large language model to create rich knowledge graphs from text documents, enabling precise question-answering over private datasets. This approach outperforms naive retrieval-augmented generation (RAG) by providing structured information retrieval and comprehensive response generation. Ideal for answering global questions, GraphRAG supports informed decision-making with higher comprehensiveness and diversity. 🔗 [Read more](https://lnkd.in/eEcukH_A)

56

Mathematic legend Terence Tao is playing with OpenAI latest model 🍓: 📌 “[it is] more capable tool than previous iterations, though still struggling with the most advanced research mathematical tasks” 📌 “the new model could work its way to a correct (and well-written) solution *if* provided a lot of hints and prodding, but did not generate the key conceptual ideas on its own, and did make some non-trivial mistakes.” 📌 “The experience seemed roughly on par with trying to advise a mediocre, but not completely incompetent, graduate student.” 🤣 📌 Here is the interesting one: “It may only take one or two further iterations of improved capability […] until the level of "competent graduate student" is reached, at which point I could see this tool being of significant use in research level tasks” 📌 “I could imagine a model of this capability that was specifically finetuned on Lean and Mathlib, and integrated into an IDE, being extremely useful in formalization projects” Even if Terence Tao is not saying “it’s revolutionary” or “I used 🍓 and solved the riemann hypothesis” … I think his review is quite posititve. Remember, we started in Dec 2022 with a “kindergarten model” #GPT3 … who became a mediocre grad student in less than 2 years. To me it sounds almost like “Sheldon Cooper” precocity (#BigBangTheory) 🤩😎 PS1 - Marcel Salathé : thank you for sharing the source material! PS2- Picture below is not of Terence Tao but of “a mediocre grad student holding a strawberry” accroding to ChatGPT 🤣 Link in the comments section 👇

14

1 Comment

👉🏼 RDguru: A Conversational Intelligent Agent for Rare Diseases 🤓 Jian Yang 👇🏻 https://lnkd.in/eSCm_MkQ 🔍 Focus on data insights: - 📈 RDguru outperforms ChatGPT in generating authoritative descriptions, highlighting its enhanced accuracy in knowledge Q&A tasks. - 🔍 A novel multi-source fusion diagnostic model shows a significant 5.47% improvement in diagnostic recall compared to PheLR. - 🧬 The use of advanced algorithms facilitates more effective automated phenotype annotation and differential diagnosis in rare diseases. 💡 Main outcomes and implications: - 🏥 RDguru demonstrates the potential to significantly improve clinical decision-making processes in rare disease diagnostics. - 💬 The conversational agent can enhance patient interactions through evidence-based Q&A, leading to better-informed medical consultations. - ⚙️ Integration of multi-source diagnostic strategies could pave the way for the development of more robust AI tools in healthcare settings. 📚 Field significance: - 🚀 This study positions RDguru as a promising solution for addressing the challenges of diagnosing rare diseases, particularly given the limitations of traditional methods. - 🌍 The findings may inspire further research into the implementation of LLMs in clinical environments, promoting wider acceptance and use of AI technologies in healthcare. - 🔒 Ensuring accuracy and reliability in AI outputs is crucial for safeguarding patient safety and enhancing trust in AI applications within medicine. 🗄️: [#RareDiseases #AIAssistedDiagnosis #ClinicalDecisionSupport #MachineLearning #HealthTech #NaturalLanguageProcessing #DiagnosticAccuracy]

1

DISRUPT-DS industry roundtable IV - Large Language Models 🔨 Following up on my previous posts on the DISRUPT-DS roundatable, there is a benchmark on the potential of LLMs on R&D. Unlike the overall potential of Data Science which is considered disruptive, surprisingly the conclusion around LLMs is that they will only have a moderate impact via efficiency gains. And even more more suprisingly, the most impacted R&D area is ... 🔫 ... Data Science itself and purportedly areas where one writes computer code. However, given the fact that most LLMs can write and execute decent code only in Python, it leaves many statistical sciences in the lurch. 🔍 The next major area of impact is insight generation via searching and summarising. Whether it be searching internal regulatory documents via custom-built RAG pipelines or being able to query *both* data and documents systems simultaneously through agentic-applications. The ability to browse multiple systems, both internal and external to generate insightful and (hopefully) factual summaries remains the most sought-after use-case. ✍ Document-writing by summarizing larger reports or data from disparate sources, which might seem the most intuitive use-case for Generative AI, fails to get sufficient traction in R&D and lands only on the third spot. The reasons are the constraints imposed by regulatory writing, fact heavy document-authoring requiring complex agentic-designs which are often unstable and a work-in-progress. 🏭 Automating some of the R&D workflows by combining the above mentioned agents which can write and execute code, search multiple systems and summarise information in factual content is the most complex use-case. Consequently, only a quarter of Pharma companies from the benchmark consider it as realistic prospect. LLMs remain one of the most exciting area in AI and the potential is immense. However, in Pharma R&D the current state-of-implementation is still in its infancy. I plan to dedicate a series of posts in the future on this topic about my experiences of building solutions in this space.

17

2 Comments

🚨New Publication Alert : Qwen2 Technial Report The Qwen2 Technical Report introduces a new series of large language models, with sizes ranging from 0.5 to 72 billion parameters. The flagship model, Qwen2-72B, achieves high scores across various benchmarks, demonstrating strong capabilities in language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The instruction-tuned variant, Qwen2-72B-Instruct, also excels in specific benchmarks. Qwen2 supports about 30 languages and is openly available for community use, with resources for quantization, fine-tuning, and deployment on Hugging Face and ModelScope. For more details, you can view the [full report](https://lnkd.in/dhiXhE_r).

4

1 Comment

In my previous article on Retrieval-Augmented Generation (https://lnkd.in/gV5XfJkC), we discussed how AI models enhance their responses by retrieving relevant external data. Microsoft’s GraphRAG takes this concept a step further by leveraging knowledge graphs. For us in the pharmaceutical industry, every piece of the puzzle that can and will reduce hallucinations and thus increase accuracy when it comes to GenAI is another corner stone implementing GenAI products that will benefit our industry. How Does GraphRAG Work? 👉 Graph-Based Retrieval: Instead of traditional keyword-based searches, GraphRAG represents information as nodes in a graph, with relationships between them forming the edges. This means the system can connect different pieces of data more intelligently, leading to more insightful and contextually rich answers, especially useful for complex pharmaceutical queries like drug interactions and clinical trial data​. 👉 Enhanced Context Understanding: By understanding how data points are related, GraphRAG offers more accurate responses, which is critical in fields like healthcare, where decisions rely on understanding the full picture, not just isolated facts​. 👉 Auto-Tuning for New Domains: One of GraphRAG’s key advantages is its ability to automatically adapt to new datasets. In pharmaceuticals, where new research and regulations are constantly evolving, this ensures that the model stays current without needing extensive retraining​. Why Does GraphRAG Reduce Hallucinations? 👉 Grounded in Verified Data: Traditional AI models sometimes suffer from "hallucinations," where they generate plausible but inaccurate information. GraphRAG addresses this by grounding responses in factual relationships within the knowledge graph. Each answer is linked to verified data points, ensuring greater accuracy​. 👉 Provenance and Transparency: GraphRAG includes a clear trail of evidence for every response, making it easier to verify the accuracy of the AI’s answers. In the pharmaceutical industry, this transparency is crucial for ensuring regulatory compliance and safety. 👉 Handling Complex Queries: GraphRAG is particularly good at dealing with queries that span multiple data points—like understanding how a new drug interacts with various conditions. This capability is critical in pharma, where precision and context are key​. While specific figures on hallucination reduction aren't available, GraphRAG’s structured approach significantly minimizes the risk of incorrect or misleading information. https://lnkd.in/g376XwBS #AI #GraphRAG #DataAccuracy #MicrosoftAI #LLMs #ReducedHallucinations

19

👉🏼 Expansive data, extensive model: Investigating discussion topics around LLM through unsupervised machine learning in academic papers and news 🤓 Hae Sun Jung 👇🏻 https://lnkd.in/ef_MF54v 🔍 Focus on data insights: - Utilized data from Web of Science and LexisNexis to explore topic modeling methods for Large Language Models (LLMs). - Evaluated various topic modeling approaches such as LDA, NMF, CTM, and BERTopic based on diversity and coherence metrics. - BERTopic demonstrated superior performance in diversity and coherence across both platforms. 💡 Main outcomes and implications: - News articles covered a wide range of topics related to LLM applications, focusing on specialized domains. - Research papers concentrated on technical aspects of LLM technology. - Insights gained can help understand future challenges and opportunities for LLMs in different sectors. 📚 Field significance: - Enhances understanding of how LLMs are utilized in academic and news contexts. - Provides insights for enterprises leveraging LLMs for service delivery. 🗄️: #topicmodeling #unsupervisedlearning #machinelearning #datainsights

1

Kolmogorov–Arnold Networks seem like a paradigm shift in ML architectures. Curious to see how they evolve. "While MLPs have fixed activation functions on nodes ("neurons"), KANs have learnable activation functions on edges ("weights"). KANs have no linear weights at all -- every weight parameter is replaced by a univariate function parametrized as a spline. " https://lnkd.in/gdPk_qCQ

29

𝗙𝗿𝗼𝗺 𝗣𝗿𝗶𝘃𝗮𝗰𝘆 𝘁𝗼 𝗘𝘅𝗽𝗹𝗮𝗶𝗻𝗮𝗯𝗶𝗹𝗶𝘁𝘆: 𝗧𝗮𝗰𝗸𝗹𝗶𝗻𝗴 𝗔𝗜 𝗖𝗵𝗮𝗹𝗹𝗲𝗻𝗴𝗲𝘀 𝗮𝘁 𝗡𝗛𝗦 𝗘𝗻𝗴𝗹𝗮𝗻𝗱 I’ve recently written two articles for the NHS England Data Science Website based on some of the really interesting work I’ve been doing! The first: Investigating Annotation Tools for Named Entity Recognition (1). If you like Generative AI, entity extraction and identifying privacy risks - this is for you. The second: The RISE Tool (2) - An Easy Way for Testers and Assurers to Evaluate AI Classifiers. This covers AI evaluation, assurance, image classifiers and explainability. The NHS England Data Science team have a whole host of interesting projects, you can read about them all on our website (3). 1 - https://lnkd.in/dNaUXsgv 2 - https://lnkd.in/dEjp88ra 3 - https://lnkd.in/dYg53A4j

15