Tuesday, July 22, 2025
LBNN
  • Business
  • Markets
  • Politics
  • Crypto
  • Finance
  • Energy
  • Technology
  • Taxes
  • Creator Economy
  • Wealth Management
  • Documentaries
No Result
View All Result
LBNN

DeepMind framework offers breakthrough in LLMs’ reasoning

Simon Osuji by Simon Osuji
February 8, 2024
in Artificial Intelligence
0
DeepMind framework offers breakthrough in LLMs’ reasoning
0
SHARES
2
VIEWS
Share on FacebookShare on Twitter


A breakthrough approach in enhancing the reasoning abilities of large language models (LLMs) has been unveiled by researchers from Google DeepMind and the University of Southern California.

Their new ‘SELF-DISCOVER’ prompting framework – published this week on arXiV and Hugging Face – represents a significant leap beyond existing techniques, potentially revolutionising the performance of leading models such as OpenAI’s GPT-4 and Google’s PaLM 2.

The framework promises substantial enhancements in tackling challenging reasoning tasks. It demonstrates remarkable improvements, boasting up to a 32% performance increase compared to traditional methods like Chain of Thought (CoT). This novel approach revolves around LLMs autonomously uncovering task-intrinsic reasoning structures to navigate complex problems.

At its core, the framework empowers LLMs to self-discover and utilise various atomic reasoning modules – such as critical thinking and step-by-step analysis – to construct explicit reasoning structures.

By mimicking human problem-solving strategies, the framework operates in two stages:

  • Stage one involves composing a coherent reasoning structure intrinsic to the task, leveraging a set of atomic reasoning modules and task examples.
  • During decoding, LLMs then follow this self-discovered structure to arrive at the final solution.

In extensive testing across various reasoning tasks – including Big-Bench Hard, Thinking for Doing, and Math – the self-discover approach consistently outperformed traditional methods. Notably, it achieved an accuracy of 81%, 85%, and 73% across the three tasks with GPT-4, surpassing chain-of-thought and plan-and-solve techniques.

However, the implications of this research extend far beyond mere performance gains.

By equipping LLMs with enhanced reasoning capabilities, the framework paves the way for tackling more challenging problems and brings AI closer to achieving general intelligence. Transferability studies conducted by the researchers further highlight the universal applicability of the composed reasoning structures, aligning with human reasoning patterns.

As the landscape evolves, breakthroughs like the SELF-DISCOVER prompting framework represent crucial milestones in advancing the capabilities of language models and offering a glimpse into the future of AI.

(Photo by Victor on Unsplash)

See also: The UK is outpacing the US for AI hiring

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is co-located with Digital Transformation Week and Cyber Security & Cloud Expo.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

Tags: agi, ai, artificial general intelligence, artificial intelligence, arxiv, benchmark, deepmind, framework, Google, hugging face, large language models, llm, paper, research, university of southern california



Source link

Related posts

Leaked Memo: Anthropic CEO Says the Company Will Pursue Gulf State Investments After All

Leaked Memo: Anthropic CEO Says the Company Will Pursue Gulf State Investments After All

July 22, 2025
Scalable transformer accelerator enables on-device execution of large language models

Scalable transformer accelerator enables on-device execution of large language models

July 22, 2025
Previous Post

VNG inks Germany’s first deal with Algeria for pipeline gas

Next Post

Delays could push Dogger Bank A completion into 2025

Next Post
Delays could push Dogger Bank A completion into 2025

Delays could push Dogger Bank A completion into 2025

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

RECOMMENDED NEWS

SA makes progress in combatting human trafficking but Cuban doctors still exploited

SA makes progress in combatting human trafficking but Cuban doctors still exploited

11 months ago
Deputy Minister Seitlholo Calls For Bold Investment To Secure Southern Africa’s Water Future

Deputy Minister Seitlholo Calls For Bold Investment To Secure Southern Africa’s Water Future

2 months ago
AI-powered misinformation is the world’s biggest short-term threat, Davos report says

AI-powered misinformation is the world’s biggest short-term threat, Davos report says

2 years ago
Fish camp in Alaska – without the fish

Fish camp in Alaska – without the fish

9 months ago

POPULAR NEWS

  • Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    0 shares
    Share 0 Tweet 0
  • When Will SHIB Reach $1? Here’s What ChatGPT Says

    0 shares
    Share 0 Tweet 0
  • The world’s top 10 most valuable car brands in 2025

    0 shares
    Share 0 Tweet 0
  • Top 10 African countries with the highest GDP per capita in 2025

    0 shares
    Share 0 Tweet 0
  • Tanzania’s natural gas sector goes global with Dubai deal

    0 shares
    Share 0 Tweet 0
  • Privacy Policy
  • Contact

© 2023 LBNN - All rights reserved.

No Result
View All Result
  • Home
  • Business
  • Politics
  • Markets
  • Crypto
  • Economics
    • Manufacturing
    • Real Estate
    • Infrastructure
  • Finance
  • Energy
  • Creator Economy
  • Wealth Management
  • Taxes
  • Telecoms
  • Military & Defense
  • Careers
  • Technology
  • Artificial Intelligence
  • Investigative journalism
  • Art & Culture
  • Documentaries
  • Quizzes
    • Enneagram quiz
  • Newsletters
    • LBNN Newsletter
    • Divergent Capitalist

© 2023 LBNN - All rights reserved.