# Kaggle Kaggle is described as the world's AI proving ground, with documentation for notebooks and competitions. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Fine-tuning a DistilBERT classifier with numerical and text inputs DevFeed: [Fine-tuning a DistilBERT classifier with numerical and text inputs]() Original publisher: [Read original article]() Author: Paloma Jol Published: 2026-04-10T10:04:33Z Content type: tutorial Language: en Sources: [FreeAgent]() Topics: [Fine-tuning](), [Transformer](), [foundation-models](), [Training AI Models](), [datasets](), [Kaggle](), [scikit-learn]() Tags: [ai](), [aws](), [data](), [data-ml](), [data-science](), [dataset](), [encoding](), [fine-tuning](), [hugging-face](), [kaggle](), [llms](), [machine-learning](), [model](), [models](), [nlp](), [performance](), [text-classification](), [training-data](), [validation]() ### AI overview This tutorial explains how to fine-tune a DistilBERT text classifier while incorporating a numerical feature into the same network. It uses the Kaggle wine reviews dataset, combining review descriptions with price and preprocessing the data for training, validation, and testing. ### Source excerpt Text classification is often done through fine-tuning of a pretrained foundation model with domain-specific data. In FreeAgent we use transformer based models to automatically classify incoming bank transactions. Specifically we use a DistilBERT model that is fine-tuned on hundreds of millions of bank transactions with customer-labelled accounting categories. The model inputs are currently text-based, built from a combination of bank transaction descriptions and amounts. In this post we describe an approach to fine-tuning the DistilBERT model and training the classifier including the numerical amount feature as a single network. ## Next generation medical image interpretation with MedGemma 1.5 and medical speech to text with MedASR DevFeed: [Next generation medical image interpretation with MedGemma 1.5 and medical speech to text with MedASR]() Original publisher: [Read original article]() Published: 2026-01-13T20:57:16Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Medical imaging](), [AI Models](), [asr](), [Generative AI](), [Google](), [hugging face](), [Cloud](), [Kaggle]() Tags: [ai-models](), [asr](), [generative-ai](), [google](), [google-cloud](), [health](), [health-bioscience](), [healthcare](), [hugging-face](), [kaggle](), [machine-intelligence](), [medical-imaging]() ### AI overview Google Research describes MedGemma 1.5 4B, an updated open medical generative AI model with improved support for medical imaging, text, medical records, and 2D images. The article also presents MedASR, an open medical speech-to-text model for dictation that can pair with MedGemma for advanced reasoning. The models are available for research and commercial use through Hugging Face and Vertex AI, with a related medical AI hackathon on Kaggle. ### Source excerpt Generative AI ## FACTS Benchmark Suite: Systematically evaluating the factuality of large language models DevFeed: [FACTS Benchmark Suite: Systematically evaluating the factuality of large language models]() Original publisher: [Read original article]() Author: FACTS team Published: 2025-12-09T11:29:03Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [LLM evaluation / benchmarking](), [Benchmark](), [Large Language Model](), [Kaggle](), [multimodal]() Tags: [benchmark](), [benchmarks](), [evaluation](), [kaggle](), [language-models](), [large-language-models](), [leaderboard](), [multimodal](), [responsibility-safety](), [search](), [web]() ### AI overview Google DeepMind and Kaggle introduce the FACTS Benchmark Suite, which evaluates the factuality of large language models across internal-knowledge, search, multimodal, and grounded-answering tasks. The suite contains 3,513 publicly available examples, with held-out private sets used to calculate an overall FACTS Score and publish results on a leaderboard. ### Source excerpt Systematically evaluating the factuality of large language models with the FACTS Benchmark Suite. ## Games as Model Eval: 1-Click Deploy AI Town on Fly.io DevFeed: [Games as Model Eval: 1-Click Deploy AI Town on Fly.io]() Original publisher: [Read original article]() Published: 2025-08-11T00:00:00Z Content type: opinion Language: en Sources: [The Fly Blog]() Topics: [LLM evaluation / benchmarking](), [Artificial Intelligence](), [Kaggle](), [fly.io]() Tags: [ai-models](), [benchmarks](), [cdn](), [close-to-users](), [deploy-app-servers](), [docker](), [elixir](), [eval](), [fly](), [fly-io](), [games](), [heroku-alternative](), [heroku-competitor](), [hosting](), [i](), [networking](), [postgresql-clusters](), [servers]() ### AI overview The article argues that games can make AI model evaluation more rigorous and engaging. It highlights the limits of conventional benchmarks and subjective output comparisons, points to Google's Kaggle Game Arena, and presents game environments as tests of strategic reasoning, long-term planning, and dynamic adaptation. ### Source excerpt Recently, I suggested that The Future Isn't Model Agnostic, that it's better to pick one model that works for your project and build around it, rather than engineering for model flexibility. If you buy that, you also have to acknowledge how important comprehensive model evaluation becomes. Benchmarks tell us almost nothing about how a model will actually behave in the wild, especially with long contexts, or when trusted to deliver the tone and feel that defines the UX we're shooting for. Even the best evaluation pipelines usually end in subjective, side-by-side output comparisons. Not especially rigorous, and more importantly, boring af. Can we gamify model evaluation? Oh yes. And not just because we get to have some fun for once. Google backed me up this week when it announced the Kaggle Game Arena. A public platform where we can watch AI models duke it out in a variety of classic games. Quoting Google; "Current AI benchmarks are struggling to keep pace with modern models... it can be hard to know if models trained on internet data are actually solving problems or just remembering answers they've already seen." When models boss reading comprehension tests, or ace math problems, we pay attention. But when they fail to navigate a simple conversation with a virtual character or completely botch a strategic decision in a game environment, we tell ourselves we're not building a game anyway and develop strategic short-term memory loss. Just like I've told my mom a thousand times, games are great at testing brains, and it's time we take this seriously when it comes to model evaluation. Why Games Don't Lie Games provide what benchmarks can't, "a clear, unambiguous signal of success." They give us observable behavior in dynamic environments, the kind that would be extremely difficult (and tedious) to simulate with prompt engineering alone. Games force models to demonstrate the skills we actually care about; strategic reasoning, long-term planning, and dynamic adaptation in in ## Improving Hugging Face Model Access for Kaggle Users DevFeed: [Improving Hugging Face Model Access for Kaggle Users]() Original publisher: [Read original article]() Author: Vincent Roseberry; Meg Risdal; Julien Chaumond; Pedro Cuenca; Vaibhav Srivastav Published: 2025-05-14T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [hugging face](), [Kaggle](), [qwen](), [spaces]() Tags: [add-ons](), [announcement](), [code](), [community](), [evaluation](), [hub](), [hugging-face](), [kaggle](), [model](), [qwen](), [qwen3](), [secrets](), [spaces](), [token]() ### AI overview Kaggle is integrating Hugging Face models into its platform, improving model discovery, navigation, and reuse in Kaggle Notebooks. Public notebooks using Hugging Face models can contribute code examples to Kaggle model pages, while private and gated models continue to require Hugging Face authentication. Support for offline Kaggle competition submissions is still in development. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Announcing Our Market Prediction Kaggle Competition DevFeed: [Announcing Our Market Prediction Kaggle Competition]() Original publisher: [Read original article]() Author: Craig Falls Published: 2020-11-24T00:00:00Z Content type: release Language: en Sources: [Jane Street]() Topics: [Kaggle](), [Machine learning](), [data](), [Data Science]() Tags: [competition](), [data](), [data-science](), [financial](), [hiring](), [kaggle](), [london](), [machine-learning](), [ml]() ### AI overview Jane Street announces a Kaggle competition based on a real problem and real financial data, with $100,000 in total prizes. The company says the contest aims to introduce more people to its data-science work and encourage applications. ### Source excerpt Jane Street is running a Kaggle contest based on a real problem with real financial data. If you like ML projects, or think you might, head over and check it out. We think it's a pretty fun one. The prizes are pretty good too, with a total $100K being paid out. ## Machine Learning Datasets for NLP DevFeed: [Machine Learning Datasets for NLP]() Original publisher: [Read original article]() Author: Fuzzygroup Published: 2020-03-09T00:00:00Z Content type: article Language: en Sources: [Scott Johnson]() Topics: [datasets](), [Natural language processing](), [Machine learning](), [data](), [Kaggle]() Tags: [data](), [datasets](), [kaggle](), [machine-learning](), [netlabeler](), [nlp]() ### AI overview A short list of machine-learning datasets for natural language processing, including resources from Kaggle, LionBridge.ai, the Million Song Dataset, Synced Review, Twitter, and Sample Stream. ### Source excerpt Today is a short one, just pointers to some datasets for Machine Learning data sets that I keep losing. Kaggle LionBridge.ai Million Song Dataset Synced Review Twitter Sample Stream