Large Language Models | Towards Data Science https://towardsdatascience.com/category/artificial-intelligence/large-language-models/ Publish AI, ML & data-science insights to a global community of data professionals. Sun, 14 Dec 2025 14:28:17 +0000 en-US hourly 1 https://wordpress.org/?v=6.8.3 https://towardsdatascience.com/wp-content/uploads/2025/02/cropped-Favicon-32x32.png Large Language Models | Towards Data Science https://towardsdatascience.com/category/artificial-intelligence/large-language-models/ 32 32 NeurIPS 2025 Best Paper Review: Qwen’s Systematic Exploration of Attention Gating https://towardsdatascience.com/neurips-2025-best-paper-review-qwens-systematic-exploration-of-attention-gating/ Sat, 13 Dec 2025 10:16:00 +0000 https://towardsdatascience.com/?p=607899 This one little trick can bring about enhanced training stability, the use of larger learning rates and improved scaling properties

The post NeurIPS 2025 Best Paper Review: Qwen’s Systematic Exploration of Attention Gating appeared first on Towards Data Science.

]]> GraphRAG in Practice: How to Build Cost-Efficient, High-Recall Retrieval Systems https://towardsdatascience.com/graphrag-in-practice-how-to-build-cost-efficient-high-recall-retrieval-systems/ Tue, 09 Dec 2025 13:30:00 +0000 https://towardsdatascience.com/?p=607859 Smarter retrieval strategies that outperform dense graphs — with hybrid pipelines and lower cost

The post GraphRAG in Practice: How to Build Cost-Efficient, High-Recall Retrieval Systems appeared first on Towards Data Science.

]]> Reading Research Papers in the Age of LLMs https://towardsdatascience.com/reading-research-papers-in-the-age-of-llms/ Sat, 06 Dec 2025 16:00:00 +0000 https://towardsdatascience.com/?p=607833 How I keep up with papers with a mix of manual and AI-assisted reading

The post Reading Research Papers in the Age of LLMs appeared first on Towards Data Science.

]]> Why AI Alignment Starts With Better Evaluation https://towardsdatascience.com/why-ai-alignment-starts-with-better-evaluation/ Mon, 01 Dec 2025 13:00:00 +0000 https://towardsdatascience.com/?p=607771 You can’t align what you don’t evaluate

The post Why AI Alignment Starts With Better Evaluation appeared first on Towards Data Science.

]]> Training Objective That Makes LLM Inference 3X Faster https://towardsdatascience.com/why-weve-been-optimizing-the-wrong-thing-in-llms-for-years/ Fri, 28 Nov 2025 14:00:00 +0000 https://towardsdatascience.com/?p=607748 The simple shift in training that unlocks foresight, faster inference, and better reasoning.

The post Training Objective That Makes LLM Inference 3X Faster appeared first on Towards Data Science.

]]> How I Use AI to Convince Companies to Adopt Sustainability https://towardsdatascience.com/how-i-use-ai-to-convince-companies-to-adopt-sustainability/ Wed, 26 Nov 2025 12:00:00 +0000 https://towardsdatascience.com/?p=607735 Discover how Claude can act as a Supply Chain Sustainability Analyst and guide companies toward greener, more efficient inventory management.

The post How I Use AI to Convince Companies to Adopt Sustainability appeared first on Towards Data Science.

]]> LLM-as-a-Judge: What It Is, Why It Works, and How to Use It to Evaluate AI Models https://towardsdatascience.com/llm-as-a-judge-what-it-is-why-it-works-and-how-to-use-it-to-evaluate-ai-models/ Mon, 24 Nov 2025 19:33:31 +0000 https://towardsdatascience.com/?p=607718 A step-by-step guide to building AI quality control using large language models

The post LLM-as-a-Judge: What It Is, Why It Works, and How to Use It to Evaluate AI Models appeared first on Towards Data Science.

]]> How to Use Gemini 3 Pro Efficiently https://towardsdatascience.com/how-to-use-gemini-3-pro-efficiently/ Thu, 20 Nov 2025 16:30:00 +0000 https://towardsdatascience.com/?p=607692 Learn the pros and cons of Gemini 3 Pro, from testing with both coding and console usage

The post How to Use Gemini 3 Pro Efficiently appeared first on Towards Data Science.

]]> How to Build an Over-Engineered Retrieval System https://towardsdatascience.com/how-to-build-an-overengineered-retrieval-system/ Tue, 18 Nov 2025 17:00:00 +0000 https://towardsdatascience.com/?p=607673 Which is actually how some people do it

The post How to Build an Over-Engineered Retrieval System appeared first on Towards Data Science.

]]> Why LLMs Aren’t a One-Size-Fits-All Solution for Enterprises https://towardsdatascience.com/why-llms-arent-a-one-size-fits-all-solution-for-enterprises/ Tue, 18 Nov 2025 15:30:00 +0000 https://towardsdatascience.com/?p=607670 LLMs are a seamless way to find value in your unstructured data, but the truth is, there is so much more value hidden within your structured data. This post explores what LLMs are (and aren’t) optimized for and how the industry is approaching AI over structured business datasets – including one approach developed by my team and me.

The post Why LLMs Aren’t a One-Size-Fits-All Solution for Enterprises appeared first on Towards Data Science.

]]> Music, Lyrics, and Agentic AI: Building a Smart Song Explainer using Python and OpenAI https://towardsdatascience.com/music-lyrics-and-agentic-ai-building-a-smart-song-explainer-using-python-and-openai/ Fri, 14 Nov 2025 14:00:00 +0000 https://towardsdatascience.com/?p=607634 This is how to build an AI-powered Song Explainer using Python and OpenAI

The post Music, Lyrics, and Agentic AI: Building a Smart Song Explainer using Python and OpenAI appeared first on Towards Data Science.

]]> LLMs Are Randomized Algorithms https://towardsdatascience.com/llms-are-randomized-algorithms/ Thu, 13 Nov 2025 17:04:21 +0000 https://towardsdatascience.com/?p=607624 A surprising connection between the newest AI models and a 50-year old academic field

The post LLMs Are Randomized Algorithms appeared first on Towards Data Science.

]]> How to Evaluate Retrieval Quality in RAG Pipelines (Part 3): DCG@k and NDCG@k https://towardsdatascience.com/how-to-evaluate-retrieval-quality-in-rag-pipelines-part-3-dcgk-and-ndcgk/ Wed, 12 Nov 2025 14:00:00 +0000 https://towardsdatascience.com/?p=607610 The third and final part for evaluating the retrieval quality of your RAG pipeline with graded measures

The post How to Evaluate Retrieval Quality in RAG Pipelines (Part 3): DCG@k and NDCG@k appeared first on Towards Data Science.

]]> Do You Really Need GraphRAG? A Practitioner’s Guide Beyond the Hype https://towardsdatascience.com/do-you-really-need-graphrag-a-practitioners-guide-beyond-the-hype/ Tue, 11 Nov 2025 17:00:00 +0000 https://towardsdatascience.com/?p=607606 A perspective on GraphRAG design best practices, challenges and learnings

The post Do You Really Need GraphRAG? A Practitioner’s Guide Beyond the Hype appeared first on Towards Data Science.

]]> LLM-Powered Time-Series Analysis https://towardsdatascience.com/llm-powered-time-series-analysis/ Sun, 09 Nov 2025 16:00:00 +0000 https://towardsdatascience.com/?p=607590 Part 2: Prompts for Advanced Model Development

The post LLM-Powered Time-Series Analysis appeared first on Towards Data Science.

]]> How to Use GPT-5 Effectively https://towardsdatascience.com/how-to-use-gpt-5-effectively/ Fri, 07 Nov 2025 12:30:00 +0000 https://towardsdatascience.com/?p=607577 Learn about GPT-5's features and settings, and how to optimally apply them to your use case

The post How to Use GPT-5 Effectively appeared first on Towards Data Science.

]]> AI Papers to Read in 2025 https://towardsdatascience.com/ai-papers-to-read-in-2025/ Wed, 05 Nov 2025 21:47:58 +0000 https://towardsdatascience.com/?p=607566 And Why They Matter for Anyone Working With AI

The post AI Papers to Read in 2025 appeared first on Towards Data Science.

]]> How to Evaluate Retrieval Quality in RAG Pipelines (part 2): Mean Reciprocal Rank (MRR) and Average Precision (AP) https://towardsdatascience.com/how-to-evaluate-retrieval-quality-in-rag-pipelines-part-2-mean-reciprocal-rank-mrr-and-average-precision-ap/ Wed, 05 Nov 2025 20:41:24 +0000 https://towardsdatascience.com/?p=607564 Evaluating the retrieval quality of your RAG pipeline with binary, order-aware measures

The post How to Evaluate Retrieval Quality in RAG Pipelines (part 2): Mean Reciprocal Rank (MRR) and Average Precision (AP) appeared first on Towards Data Science.

]]> Building a Multimodal RAG That Responds with Text, Images, and Tables from Sources https://towardsdatascience.com/building-a-multimodal-rag-with-text-images-tables-from-sources-in-response/ Mon, 03 Nov 2025 20:03:24 +0000 https://towardsdatascience.com/?p=607546 Why do few chatbots return figures from source documents in their responses?

The post Building a Multimodal RAG That Responds with Text, Images, and Tables from Sources appeared first on Towards Data Science.

]]> Graph RAG vs SQL RAG https://towardsdatascience.com/graph-rag-vs-sql-rag/ Sat, 01 Nov 2025 14:00:00 +0000 https://towardsdatascience.com/?p=607536 Evaluating RAGs on graph and SQL databases

The post Graph RAG vs SQL RAG appeared first on Towards Data Science.

]]>