Proceedings

A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive (Extended Abstract)

Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Sister Conferences Best Papers. Pages 8284-8288.

https://doi.org/10.24963/ijcai.2026/927

Keywords

  • Search: Heuristic search
  • Agent-based and Multi-agent Systems: Agent theories and models
  • AI Ethics, Trust, Fairnes: Bias
  • Natural Language Processing: Language models

Abstract

Large Language Models (LLMs) are often used in autonomous decision-making, where they have to sample options from vast action spaces.

Here we present a summary of the work studying the heuristics that guide this sampling process and show it resembles that of human decision-making: comprising a descriptive component (reflecting statistical norm) and a prescriptive component (implicit ideal encoded in the LLM). We show that the deviation of a sample from the statistical norm towards a prescriptive component consistently appears in concepts across diverse real-world domains. To further illustrate the theory, we demonstrate that concept prototypes in LLMs are affected by prescriptive norms, similar to the concept of normality in humans. This finding has implications in LLM based agentic systems, explaining their exploration behavior and biases in decision making.

Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, and Mario Fritz. 2026. A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive (Extended Abstract). In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8284–8288. https://doi.org/10.24963/ijcai.2026/927
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards