{"type":"ScholarlyArticle","title":"A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive (Extended Abstract)","authors":[{"name":"Sarath Sivaprasad","slug":"sarath-sivaprasad","given":"Sarath","family":"Sivaprasad","affiliation":""},{"name":"Pramod Kaushik","slug":"pramod-kaushik","given":"Pramod","family":"Kaushik","affiliation":""},{"name":"Sahar Abdelnabi","slug":"sahar-abdelnabi","given":"Sahar","family":"Abdelnabi","affiliation":""},{"name":"Mario Fritz","slug":"mario-fritz","given":"Mario","family":"Fritz","affiliation":""}],"abstract":"Large Language Models (LLMs) are often used in autonomous decision-making, where they have to sample options from vast action spaces.\r\nHere 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.","doi":"10.24963/ijcai.2026/927","url":"https://ijcai.org/proceedings/2026/927","pdf":"https://ijcai.org/proceedings/2026/0927.pdf","markdown":"https://ijcai.org/proceedings/2026/927.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/927","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":927,"pages":{"first":8284,"last":8288},"keywords":["Search: Heuristic search","Agent-based and Multi-agent Systems: Agent theories and models","AI Ethics, Trust, Fairnes: Bias","Natural Language Processing: Language models"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}