Dice Question Streamline Icon: https://streamlinehq.com

Value-based preferences beyond GPT-3.5/4

Determine whether large language model species other than GPT-3.5 and GPT-4 exhibit value-based strategic preferences when strategies are associated with explicit numerical payoffs.

Information Square Streamline Icon: https://streamlinehq.com

Background

Prior work reported that GPT-3.5 and GPT-4 prefer higher-valued options in a dictator game, but it is not established whether this behavior generalizes to other model families, particularly open-source models. The paper frames this as a foundational uncertainty motivating broader evaluation across many LLM species.

References

Although past work has shown that GPT-3.5 and GPT-4 have preferences for higher valued strategies in a dictator game , it is not clear whether other model species possess similar preferences.

— Do Large Language Models Learn Human-Like Strategic Preferences? (2404.08710 - Roberts et al., 11 Apr 2024) in Section 3, Do LLMs Prefer Strategies Based on Value?, opening paragraph