Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Former Anthropic exec raises $15M to insure AI agents and help startups deploy safely

AI’s talent arms race is starting to look like pro sports

Promoting Skills for Employees | Recruiting News Network

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Industry AI
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Hugging Face

Paper page – Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning

By Advanced AI EditorJuly 23, 2025No Comments1 Min Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Concept Ablation Fine-Tuning (CAFT) uses interpretability tools to steer LLM generalization away from unintended concepts without altering training data.

Fine-tuning large language models (LLMs) can lead to unintended
out-of-distribution generalization. Standard approaches to this problem rely on
modifying training data, for example by adding data that better specify the
intended generalization. However, this is not always practical. We introduce
Concept Ablation Fine-Tuning (CAFT), a technique that leverages
interpretability tools to control how LLMs generalize from fine-tuning, without
needing to modify the training data or otherwise use data from the target
distribution. Given a set of directions in an LLM’s latent space corresponding
to undesired concepts, CAFT works by ablating these concepts with linear
projections during fine-tuning, steering the model away from unintended
generalizations. We successfully apply CAFT to three fine-tuning tasks,
including emergent misalignment, a phenomenon where LLMs fine-tuned on a narrow
task generalize to give egregiously misaligned responses to general questions.
Without any changes to the fine-tuning data, CAFT reduces misaligned responses
by 10x without degrading performance on the training distribution. Overall,
CAFT represents a novel approach for steering LLM generalization without
modifying training data.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleJensen Huang, NVIDIA, on AI factories, DeepSeek, and robots
Next Article 3 No-Brainer Artificial Intelligence (AI) Stocks to Buy Right Now
Advanced AI Editor
  • Website

Related Posts

Paper page – Does More Inference-Time Compute Really Help Robustness?

July 23, 2025

Paper page – RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback

July 23, 2025

Paper page – ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting

July 23, 2025

Comments are closed.

Latest Posts

Barnes Foundation Online Learning Platform Expands to Penn Museum

Archaeologists Identify 5,500-Year-Old Megalithic Tombs in Poland

Phillips to Debut ‘First-of-its Kind’ Priority Bidding Structure

3,800-Year-Old Warrior’s Tomb Unearthed in Azerbaijan

Latest Posts

Former Anthropic exec raises $15M to insure AI agents and help startups deploy safely

July 23, 2025

AI’s talent arms race is starting to look like pro sports

July 23, 2025

Promoting Skills for Employees | Recruiting News Network

July 23, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Former Anthropic exec raises $15M to insure AI agents and help startups deploy safely
  • AI’s talent arms race is starting to look like pro sports
  • Promoting Skills for Employees | Recruiting News Network
  • ‘Spend less time on Instagram and more on learning artificial intelligence’: Perplexity AI CEO Aravind Srinivas
  • Tesla Q2 2025 earnings: What Wall Street expects

Recent Comments

  1. 1win app download on Former Tesla AI czar Andrej Karpathy coins ‘vibe coding’: Here’s what it means
  2. 📃 ✉️ Pending Deposit: 1.8 BTC from new sender. Review? > https://graph.org/REDEEM-BTC-07-23?hs=60194a6753699dfb5804798d5843ffd0& 📃 on This Neural Network Optimizes Itself | Two Minute Papers #212
  3. 📉 📩 Pending Deposit - 1.0 BTC from unknown sender. Review? => https://graph.org/REDEEM-BTC-07-23?hs=16ed4f83e039fc01f975372e66ec05d7& 📉 on OpenAI seeks to make its upcoming ‘open’ AI model best-in-class
  4. 📊 📩 Pending Transfer: 1.8 BTC from unknown sender. Approve? >> https://graph.org/REDEEM-BTC-07-23?hs=8f64f5846f6d90e5a1ebb4bba272bbea& 📊 on Nvidia’s GB200 NVL72 Supercomputer Achieves 2.7× Faster Inference on DeepSeek V2
  5. 📅 ✉️ New Deposit: 1.8 BTC from new sender. Approve? > https://graph.org/REDEEM-BTC-07-23?hs=5719fe560af3b8c36c0a0976ea7a6f6b& 📅 on Meta, Booz Allen develop ‘Space Llama’ AI system for the International Space Station

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.