Search papers, labs, and topics across Lattice.
Mohamed bin Zayed University of Artificial Intelligence, Carnegie Mellon University
CMU Machine Learning4
0
7
0
LLMs struggle with historical analogy retrieval due to a focus on surface features, but the new CANA framework boosts their performance by 10% through causal understanding.
None of the 30 LLM agents evaluated in CausalGame demonstrated reliable causal thinking, revealing a critical gap in AI's ability to perform scientific reasoning.
Standard RL critics for LLMs are basically useless, but these two simple methods can fix them.
LLMs can be guided to discover better solutions in open-ended scientific tasks by identifying and reasoning about causal factors that influence the evolutionary process.
