Learning to Think from Multiple Thinkers
We study learning with Chain-of-Thought (CoT) supervision from multiple thinkers, all of whom provide correct but possibly systematically different solutions, e.g., step-by-step solutions to math problems written by different thinkers, or step-by-step execution traces of different programs solving the same problem. We consider classes that are computationally easy to learn using CoT supervision from a single thinker, but hard to learn with only end-result supervision, i.e., without CoT (Joshi et al. 2025). We establish that, under cryptographic assumptions, learning can be hard from CoT supervision provided by two or a few different thinkers, in passive data-collection settings. On the other hand, we provide a generic computationally efficient active learning algorithm that learns with a small amount of CoT data per thinker that is completely independent of the target accuracy $\varepsilon$, a moderate number of thinkers that scales as $\log \frac{1}{\varepsilon}\log \log \frac{1}{\varepsilon}$, and sufficient passive end-result data that scales as $\frac{1}{\varepsilon}\cdot poly\log\frac{1}{\varepsilon}$.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningSimilar Papers 제목 키워드 기반
Does Thought Require Sensory Grounding? From Pure Thinkers to Large Language Models
Does the capacity to think require the capacity to sense? A lively debate on this topic runs throughout the history of philosophy and now animates discussions of artificial intelligence. I argue that in principle, there …
PhilosophyCritical Thinking Via Storytelling: Theory and Social Media Experiment
In a stylized voting model, we establish that increasing the share of critical thinkers -- individuals who are aware of the ambivalent nature of a certain issue -- in the population increases the efficiency of surveys (e…
SwarmThinkers: Learning Physically Consistent Atomic KMC Transitions at Scale
Can a scientific simulation system be physically consistent, interpretable by design, and scalable across regimes--all at once? Despite decades of progress, this trifecta remains elusive. Classical methods like Kinetic M…
Decision MakingGPUGroup Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity
Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to raise joint reasoning quality above individu…
GPUiNNk: A Multi-Player Game to Deceive a Neural Network
This paper presents iNNK, a multiplayer drawing game where human players team up against an NN. The players need to successfully communicate a secret code word to each other through drawings, without being deciphered by …