PulseAugur
LIVE 15:31:55
research · [2 sources] ·
0
research

LLM personas show stable behavior but limited variation in urban sentiment tasks

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

A new research paper explores the effectiveness of using persona prompting with large language models (LLMs) for urban sentiment analysis. The study found that while agents with the same persona exhibited consistent behavior, the differentiation between distinct personas (like gender, economic status, or political orientation) was minimal. In some cases, LLMs without persona conditioning performed as well as or better than those with personas, suggesting limited added value for fine-grained perceptual judgments. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Persona prompting in LLMs may offer limited benefits for nuanced sentiment analysis tasks.

RANK_REASON Academic paper on LLM behavior and persona validity.

Read on arXiv cs.CL →

COVERAGE [2]

  1. arXiv cs.CL TIER_1 · Neemias B da Silva, Rodrigo Minetto, Daniel Silver, Thiago H Silva ·

    Stable Behavior, Limited Variation: Persona Validity in LLM Agents for Urban Sentiment Perception

    arXiv:2604.28048v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting produces meaningful and reproducible behavioral diversity. We investigate whether…

  2. arXiv cs.CL TIER_1 · Thiago H Silva ·

    Stable Behavior, Limited Variation: Persona Validity in LLM Agents for Urban Sentiment Perception

    Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting produces meaningful and reproducible behavioral diversity. We investigate whether distinct personas influence urban sentiment jud…

RELATED ENTITIES

RELATED TOPICS