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

UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution – Takara TLDR

Training-Free Group Relative Policy Optimization – Takara TLDR

Singapore company allegedly helped China smuggle $2 billion worth of Nvidia AI processors, report claims — Nvidia denies that the accused has any China ties, but a U.S. investigation is underway

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
  • Business AI
    • Advanced AI News Features
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Hugging Face

Memory Retrieval and Consolidation in Large Language Models through Function Tokens – Takara TLDR

By Advanced AI EditorOctober 12, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


The remarkable success of large language models (LLMs) stems from their
ability to consolidate vast amounts of knowledge into the memory during
pre-training and to retrieve it from the memory during inference, enabling
advanced capabilities such as knowledge memorization, instruction-following and
reasoning. However, the mechanisms of memory retrieval and consolidation in
LLMs remain poorly understood. In this paper, we propose the function token
hypothesis to explain the workings of LLMs: During inference, function tokens
activate the most predictive features from context and govern next token
prediction (memory retrieval). During pre-training, predicting the next tokens
(usually content tokens) that follow function tokens increases the number of
learned features of LLMs and updates the model parameters (memory
consolidation). Function tokens here roughly correspond to function words in
linguistics, including punctuation marks, articles, prepositions, and
conjunctions, in contrast to content tokens. We provide extensive experimental
evidence supporting this hypothesis. Using bipartite graph analysis, we show
that a small number of function tokens activate the majority of features. Case
studies further reveal how function tokens activate the most predictive
features from context to direct next token prediction. We also find that during
pre-training, the training loss is dominated by predicting the next content
tokens following function tokens, which forces the function tokens to select
the most predictive features from context.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleWhen You Tell AI Models to Act Like Women, Most Become More Risk-Averse: Study
Next Article Singapore company allegedly helped China smuggle $2 billion worth of Nvidia AI processors, report claims — Nvidia denies that the accused has any China ties, but a U.S. investigation is underway
Advanced AI Editor
  • Website

Related Posts

UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution – Takara TLDR

October 12, 2025

Training-Free Group Relative Policy Optimization – Takara TLDR

October 12, 2025

LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions – Takara TLDR

October 11, 2025

Comments are closed.

Latest Posts

The Rubin Names 2025 Art Prize, Research and Art Projects Grants

Kochi-Muziris Biennial Announces 66 Artists for December Exhibition

Instagram Launches ‘Rings’ Awards for Creators—With KAWS as a Judge

Museums Prepare to Close Their Doors as Government Shutdown Continues

Latest Posts

UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution – Takara TLDR

October 12, 2025

Training-Free Group Relative Policy Optimization – Takara TLDR

October 12, 2025

Singapore company allegedly helped China smuggle $2 billion worth of Nvidia AI processors, report claims — Nvidia denies that the accused has any China ties, but a U.S. investigation is underway

October 12, 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

  • UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution – Takara TLDR
  • Training-Free Group Relative Policy Optimization – Takara TLDR
  • Singapore company allegedly helped China smuggle $2 billion worth of Nvidia AI processors, report claims — Nvidia denies that the accused has any China ties, but a U.S. investigation is underway
  • Memory Retrieval and Consolidation in Large Language Models through Function Tokens – Takara TLDR
  • When You Tell AI Models to Act Like Women, Most Become More Risk-Averse: Study

Recent Comments

  1. Casterwooder6Nalay on MIT leaders discuss strategy for navigating Trump in private meeting
  2. SpinMasterZ7Nalay on United States, China, and United Kingdom Lead the Global AI Ranking According to Stanford HAI’s Global AI Vibrancy Tool
  3. test link bẩn on Baidu AI drive to boost jobs
  4. RoyalThroneF3Nalay on Curiosity, Grit Matter More Than Ph.D to Work at OpenAI: ChatGPT Boss
  5. JungleEchoK2Nalay on An improved Large-scale 3D Vision Dataset for Compositional Recognition

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.