Tencent’s new AI technique teaches language models ‘parallel thinking’

The Parallel-R1 framework uses reinforcement learning to teach models how to explore multiple reasoning paths at once, ...
GitHub

uqlm: Uncertainty Quantification for Language Models

UQLM provides a suite of response-level scorers for quantifying the uncertainty of Large Language Model (LLM) outputs. Each scorer returns a confidence score between 0 and 1, where higher scores ...
Berkman Klein Center

Belief, Uncertainty, and Truth in Language Models

What does it mean for a language model to “know” something—and how should it communicate uncertainty to the people who use it ...
IEEE

Automatic Test Cases Generation Based on State Machine Diagram of Systems Modeling Language

Abstract: This paper presents a method for automatically generating effective test cases based on SysML state diagrams. The method firstly obtains Systems Modeling Language (SysML) state diagrams ...
Communications of the ACM

Language Models Wrestle with Gaps in Understanding

Language models seem to be more than stochastic parrots. Does this knowledge stop them from making mistakes, or do they need ...
IEEE

Port-Based Modeling of Transport Phenomena in 1-D Thermofluid Systems and Object-Oriented Implementation With the Modelica Language

Abstract: In this article, we present the physical foundations and the development of a Modelica library with components for modeling 1-D thermofluid systems. Modelica was selected because it is an ...