arXiv Artificial Intelligence

Population Fidelity: Evaluating Population Representativeness in LLMs

Population Fidelity: Evaluating Population Representativeness in LLMs

Quick summary

arXiv:2609.36253v1 Announce Type: cross Abstract: Large language models (LLMs) show considerable potential in simulating human attitudes and preferences. Prior work finds that LLM-generated responses can compress the range of attitudes found within populations and misrepresent particular subgroups in ways that vary across models and topics. We introduce Population Fidelity, an evaluation framework that distinguishes key conditions required for a set of LLM-generated responses to represent a population. It incorporates three dimensions: group-level accuracy, the amount of between-group variatio

Key takeaways

  • arXiv:2609.36253v1 Announce Type: cross Abstract: Large language models (LLMs) show considerable potential in simulating human attitudes and preferences.
  • Prior work finds that LLM-generated responses can compress the range of attitudes found within populations and misrepresent particular subgroups in ways that vary across models and topics.
  • We introduce Population Fidelity, an evaluation framework that distinguishes key conditions required for a set of LLM-generated responses to represent a population.

Why it matters

The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗