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

Baidu: AI Leadership In Question Amid Macroeconomic, Competitive Pressures

A Practical Guide For 2025

Energy-Based Transformers are Scalable Learners and Thinkers (Paper Review)

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 – Don’t Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning

By Advanced AI EditorMay 28, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Shorter reasoning chains in LLMs can achieve similar or better performance with reduced computational cost and inference time compared to longer chains.

Reasoning large language models (LLMs) heavily rely on scaling test-time
compute to perform complex reasoning tasks by generating extensive “thinking”
chains. While demonstrating impressive results, this approach incurs
significant computational costs and inference time. In this work, we challenge
the assumption that long thinking chains results in better reasoning
capabilities. We first demonstrate that shorter reasoning chains within
individual questions are significantly more likely to yield correct answers –
up to 34.5% more accurate than the longest chain sampled for the same question.
Based on these results, we suggest short-m@k, a novel reasoning LLM inference
method. Our method executes k independent generations in parallel and halts
computation once the first m thinking processes are done. The final answer is
chosen using majority voting among these m chains. Basic short-1@k demonstrates
similar or even superior performance over standard majority voting in
low-compute settings – using up to 40% fewer thinking tokens. short-3@k, while
slightly less efficient than short-1@k, consistently surpasses majority voting
across all compute budgets, while still being substantially faster (up to 33%
wall time reduction). Inspired by our results, we finetune an LLM using short,
long, and randomly selected reasoning chains. We then observe that training on
the shorter ones leads to better performance. Our findings suggest rethinking
current methods of test-time compute in reasoning LLMs, emphasizing that longer
“thinking” does not necessarily translate to improved performance and can,
counter-intuitively, lead to degraded results.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleStability AI & Arm Launch On-Device, Royalty-Free Text to Audio AI Model
Next Article Nvidia To Be Hit By China Chip Export Curbs Or Deliver Q2 Guidance Surprise After Middle East Deal? Here’s What Charts Show Ahead Of Q1 Results – NVIDIA (NASDAQ:NVDA), Oracle (NYSE:ORCL)
Advanced AI Editor
  • Website

Related Posts

Paper page – Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

July 19, 2025

Paper page – Teach Old SAEs New Domain Tricks with Boosting

July 19, 2025

Paper page – Automating Steering for Safe Multimodal Large Language Models

July 19, 2025
Leave A Reply

Latest Posts

Sam Gilliam Foundation, David Kordansky Sued Over ‘Disavowed’ Painting

Donors Reportedly Pulling Support from Florida University Museum after its Controversial Transfer

What will come of the Guggenheim Asher legal battle?

Painter Says DHS Stole His Work for Post About ‘Homeland’s Heritage’

Latest Posts

Baidu: AI Leadership In Question Amid Macroeconomic, Competitive Pressures

July 19, 2025

A Practical Guide For 2025

July 19, 2025

Energy-Based Transformers are Scalable Learners and Thinkers (Paper Review)

July 19, 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

  • Baidu: AI Leadership In Question Amid Macroeconomic, Competitive Pressures
  • A Practical Guide For 2025
  • Energy-Based Transformers are Scalable Learners and Thinkers (Paper Review)
  • AI Poses ‘Extinction’ Risk, OpenAI, DeepMind, and Anthropic CEOs Say
  • Can it Fuel a New Growth Cycle?

Recent Comments

  1. Наручные часы Ролекс Субмаринер приобрести on Orange County Museum of Art Discusses Merger with UC Irvine
  2. Best SEO Backlinks on From silicon to sentience: The legacy guiding AI’s next frontier and human cognitive migration
  3. Register on Paper page – Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier
  4. Bonus de parrainage Binance on University of Tokyo to upgrade its IBM quantum computer with 156-qubit Heron QPU
  5. binance on Is C3.ai a Phenomenal Under-the-Radar AI Stock?

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.