Content Is Not Social Attribution: An Audit Protocol for Textual LLM Social Simulation
SocialAgent: Second Workshop on Large Language Models for Social Reasoning and Simulation at NeurIPS 2026, 2026
Abstract
Textual social-agent studies often change both a proposition and its alleged speaker. The resulting output difference may reflect content, attribution, task demand, or their interaction, so “social influence” does not identify the pathway. We offer an executable methodological audit rather than an empirical case series. The protocol separates baseline, content-only, source-attributed, and attribution-only conditions; checks representation independently of the focal outcome; blocks assignment across items, models, and seeds; retains every failure; and requires either a finite-benchmark or population estimand. It also replaces a structural-social taxonomy informed by outcomes with a prospective multi-label rubric covering information access and timing, message content, social source attribution, normative or incentive stakes, and interface or embodiment. A hypothetical design illustrates the contrasts without invented observations. Researchers translating social paradigms into LLM protocols can use the audit to distinguish source-attribution sensitivity from a response to changed text. The framework does not establish human replication or mechanism equivalence.
Cite this work
Carlos Toxtli-Hernández and Manuel Delaflor. 2026. Content Is Not Social Attribution: An Audit Protocol for Textual LLM Social Simulation. SocialAgent: Second Workshop on Large Language Models for Social Reasoning and Simulation at NeurIPS 2026.
@inproceedings{Toxtli2026Content,
title = {Content Is Not Social Attribution: An Audit Protocol for Textual LLM Social Simulation},
author = {Toxtli, Carlos and Delaflor, Manuel},
booktitle = {SocialAgent: Second Workshop on Large Language Models for Social Reasoning and Simulation at NeurIPS 2026},
address = {Atlanta, GA},
year = {2026},
month = dec,
note = {Poster; forthcoming},
url = {https://social-llm-workshop.github.io/}
}Related
