{"version":1,"type":"story","url":"https://digestai.news/story/behavioral-history-outperforms-descriptions-for-llm-synthetic-personas","json":"https://digestai.news/story/behavioral-history-outperforms-descriptions-for-llm-synthetic-personas.json","markdown":"https://digestai.news/story/behavioral-history-outperforms-descriptions-for-llm-synthetic-personas.md","slug":"behavioral-history-outperforms-descriptions-for-llm-synthetic-personas","headline":"Behavioral history outperforms descriptions for LLM synthetic personas","summary":"The study examined how well synthetic personas, created by large language models, can predict individual survey responses. Researchers used a two‑wave panel of 845 U.S. adults who answered 14 behavioral bias questions. Five conditions were tested: no personal data, demographics, personality traits, cognitive scores, and behavioral history.\n\nResults showed that while the average number of biases per respondent was similar across conditions (7.1‑8.1 versus 7.1 for humans), description‑based personas captured only 53‑67% of the between‑person variation. Adding behavioral history restored this variation to roughly human levels. At the individual level, description‑based personas achieved only 7‑12% of the informedness seen in human test‑retest responses, whereas the behavioral‑history condition reached 28%. The behavioral‑history condition also performed best across all 17 demographic groups and revealed stronger education‑ and income‑related differences than human responses.","keyPoints":["Study used 845 U.S. adults across 14 behavioral biases.","Description‑based personas captured only 7‑12% of informedness at individual level."],"whyItMatters":"The findings highlight that past behavior is more predictive than static descriptions for AI‑generated survey personas, informing future survey design and bias mitigation.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-10-06T04:00:00Z","updatedAt":"2026-10-06T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas","url":"https://arxiv.org/abs/2610.03998","publishedAt":"2026-10-06T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Behavioral history outperforms descriptions for LLM synthetic personas\", 6 October 2026, https://digestai.news/story/behavioral-history-outperforms-descriptions-for-llm-synthetic-personas","publisher":"Digest AI","title":"Behavioral history outperforms descriptions for LLM synthetic personas","datePublished":"2026-10-06T04:00:00Z","url":"https://digestai.news/story/behavioral-history-outperforms-descriptions-for-llm-synthetic-personas"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}