2 papers
cs.LG2024
Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language
Anthony Costarelli, Mat Allen, Severin Field
As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their…
cs.CL2024
GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents
Anthony Costarelli, Mat Allen, Roman Hauksson +6
Large language models have demonstrated remarkable few-shot performance on many natural language understanding tasks. Despite several demonstrations of using large language models…