Training large language models to reason in a continuous latent space
Large language models (LLMs) are restricted to reason in the" language space", where they
typically express the reasoning process with a chain-of-thought (CoT) to solve a complex …
typically express the reasoning process with a chain-of-thought (CoT) to solve a complex …
Weak-to-strong reasoning
When large language models (LLMs) exceed human-level capabilities, it becomes
increasingly challenging to provide full-scale and accurate supervision for these models …
increasingly challenging to provide full-scale and accurate supervision for these models …
Can a Bayesian Oracle Prevent Harm from an Agent?
Is there a way to design powerful AI systems based on machine learning methods that would
satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic …
satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic …
ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise
Control system design is a crucial aspect of modern engineering with far-reaching
applications across diverse sectors including aerospace, automotive systems, power grids …
applications across diverse sectors including aerospace, automotive systems, power grids …
GFlowNet Fine-tuning for Diverse Correct Solutions in Mathematical Reasoning Tasks
R Takase, M Tsunokake, Y Tsuchiya… - arxiv preprint arxiv …, 2024 - arxiv.org
Mathematical reasoning problems are among the most challenging, as they typically require
an understanding of fundamental laws to solve. The laws are universal, but the derivation of …
an understanding of fundamental laws to solve. The laws are universal, but the derivation of …