Thinking about thinking: Metacognitive Capabilities of LLMs

Metacognitive knowledge refers to humans' intuitive knowledge of their own thinking and reasoning processes. Today's best LLMs clearly possess some reasoning processes. The paper gives evidence that they also have metacognitive knowledge, including ability to name skills and procedures to apply given a task. We explore this primarily in the context of math reasoning, developing a prompt-guided interaction procedure to get a powerful LLM to assign sensible skill labels to math questions, followed by having it perform semantic clustering to obtain coarser families of skill labels. These coarse skill labels look interpretable to humans.
To validate that these skill labels are meaningful and relevant to the LLM's reasoning processes we perform the following experiments. (a) We ask GPT-4 to assign skill labels to training questions in math datasets GSM8K and MATH. (b) When using an LLM to solve the test questions, we present it with the full list of skill labels and ask it to identify the skill needed. Then it is presented with randomly selected exemplar solved questions associated with that skill label. This improves accuracy on GSM8k and MATH for several strong LLMs, including code-assisted models. The methodology presented is domain-agnostic, even though this article applies it to math problems.

Michal Valko Bio
Michal is the Chief Models Officer at a stealth startup, tenured researcher at Inria, and the lecturer at the MVA master of ENS Paris-Saclay. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. That is why he is working on methods and settings that are able to deal with minimal feedback, such as deep reinforcement learning, bandit algorithms, self-supervised learning, or self play. Michal has recently worked on representation learning, word models and deep (reinforcement) learning algorithms that have some theoretical underpinning. In the past he has also worked on sequential algorithms with structured decisions where exploiting the structure leads to provably faster learning. Michal is now working on large large models (LMMs), in particular providing algorithmic solutions for their scalable fine-tuning and alignment. He received his Ph.D. in 2011 from the University of Pittsburgh, before getting a tenure at Inria in 2012 and starting Google DeepMind Paris in 2018 with Rémi Munos. In 2024, he became the principal Llama engineer at Meta, building online reinforcement learning stack and research for Llama 3 and 4.

KEYNOTE

More presentations from Michal Valko: Fireside Chat with Michal Valko