Evaluating the Goal-Directedness of Large Language Models
By: Tom Everitt , Cristina Garbacea , Alexis Bellot and more
Potential Business Impact:
Helps AI focus better on its job.
To what extent do LLMs use their capabilities towards their given goal? We take this as a measure of their goal-directedness. We evaluate goal-directedness on tasks that require information gathering, cognitive effort, and plan execution, where we use subtasks to infer each model's relevant capabilities. Our evaluations of LLMs from Google DeepMind, OpenAI, and Anthropic show that goal-directedness is relatively consistent across tasks, differs from task performance, and is only moderately sensitive to motivational prompts. Notably, most models are not fully goal-directed. We hope our goal-directedness evaluations will enable better monitoring of LLM progress, and enable more deliberate design choices of agentic properties in LLMs.
Similar Papers
Technical Report: Evaluating Goal Drift in Language Model Agents
Artificial Intelligence
Keeps AI robots from forgetting their jobs.
A Survey on Large Language Models for Automated Planning
Artificial Intelligence
Helps computers plan better by mixing smarts and old ways.
Re-evaluating Open-ended Evaluation of Large Language Models
CS and Game Theory
Makes AI ratings fairer and less biased.