LLM Reasoning Sets New Benchmarks for AI

Greetings Cohere Community,

With each upgrade, AI models become more advanced. Take our latest Command R models , for example; they offer significant improvements in coding, math, and latency. With every new update, it makes you wonder: how good are large language models (LLMs) at reasoning??

For businesses, LLM reasoning is essential because it allows AI to tackle more than just basic tasks. With advanced reasoning, models can manage complex processes that involve decision-making like automating workflows, analyzing data trends, and supporting strategic decisions. This makes them especially useful tools in fields like finance, healthcare, and legal, where getting things right really matters.

What is LLM reasoning?

LLM reasoning is a skill that models are increasingly being trained to perform. It refers to the ability of AI models to logically process information, break down complex problems, and make decisions based on context and patterns. This is a step-change from traditional LLM retrieval and response.?

Cohere Co-Founder and CEO Aidan Gomez describes reasoning as, “crucial to intelligence … It's not a discrete 'does it have this capability or not'; it's a continuum of how robust the reasoning engine inside these models is.”

Modern LLMs are becoming more adept and can now perform mathematical reasoning, predictive logic, and autonomous multi-agent reasoning. One of the most exciting advancements is the ability to simulate a kind of inner monologue, where models can walk through their decision-making processes. This is a key step toward robust reasoning, although training data for this is rare and can be difficult to create. Overall, different types of reasoning are essential to LLM intelligence, and ongoing research is continually expanding our understanding of their potential.

Why is LLM reasoning important?

LLMs with strong reasoning skills are incredibly valuable for businesses. Right now, everyone’s talking about how to make them work for their specific needs. We’re stepping into an era where AI can take on specialized, complex tasks in more personalized and domain-specific ways.?

Reasoning also helps build trust with users. Just like how citations add transparency to retrieval-augmented generation (RAG) systems , as models get better at explaining their thought process through complex problems, people can rely on them for more accurate and context-aware results.

What is Cohere’s approach?

Cohere's approach to LLM development is deeply rooted in real-world practicality, with a strong focus on creating models that solve immediate business challenges. Recent improvements in model design and training methods are changing the way LLMs tackle reasoning tasks.?

One breakthrough is to train the model to break down complex problems and elicit reasoning, for example through chain-of-thought (CoT). There is growing evidence that this works on human-created data, but also on synthetically-created data , which enables LLMs to learn how to reason through a broader array of problems. This way, LLMs solve a problem in a step-by-step fashion.

What’s next?

Over the next year, we’re excited to see LLM reasoning make big strides, helping to create specialized AI models that businesses can really put to use. At the same time, we’ll be tackling important challenges like data security, fairness, and reliability, so that industries like finance, healthcare, and legal can fully benefit from these advancements.

For more insights on Enterprise AI, check out our latest articles or read on for this month’s highlights and upcoming events.

Product?

Our enterprise-grade AI models are better than ever with improved versions of Command R and Command R+. Plus, you can now use our models on Slack with the newly launched Cohere AI app for Slack.?

For Business

This month, we spoke with several customers on how they are transforming work with enterprise AI. Learn how Oracle and Johnson Lambert use Cohere models.?

Developers

Setting safety guardrails just got a whole lot easier. With our Chat endpoint, you can now choose between different modes to meet your specific safety requirements. Have questions? Get answers in our next Developer Office Hours, Oct 21st, 1:00 p.m. EDT, on Discord !?

Research

Building off the success of Aya , Cohere For AI launched Expedition Aya, a six-week, global, open-build challenge to connect researchers worldwide and support new multilingual research initiatives. Join us in celebrating the five projects that were honored with the top recognition.

Company

Watch Cohere’s Co-Founder and CEO Aidan Gomez and Oracle’s Miranda Nash discuss how our partnership is helping enterprises leverage the power of AI at Oracle CloudWorld 2024 . And check out how we continue to grow solutions for global customers in our collaboration with consulting firm Nomura Research Institute (NRI).

Upcoming events with Cohere?

• Oct 2 [Online] We've launched a new course on building production-ready RAG with Cohere models in collaboration with Weights & Biases and Weaviate. Join us at 9:30 a.m. EDT, on Discord and meet the experts behind the course.?

• Oct 15 [Online] Join Cohere For AI and Professor Zhijing Jin from the University of Toronto for a discussion on LLM reasoning and cooperation .??

• Oct 15 [Online] Join Cohere For AI to explore a day in the life of an ML engineer in computer vision , presented by Cisco’s Nahid Alam.?

• Oct 18 [Online] Shout out to all developers! Join us on X Spaces at 1:00 p.m. EDT. Cohere’s Sandra Kublik will be interviewing research and product teams behind the latest releases from Cohere.

For all upcoming events, explore cohere.com/events .

Explore what's possible in the Cohere playground .