AI Paper Atlas

Research map / Large language models / AI and society

Should You Use LLMs to Simulate Opinions? Quality Checks for Early-Stage Deliberation

Terrence Neumann, Maria De-Arteaga, Sina Fazelpour

AAAI 2026 · Large language models › AI and society · approach: Critiques of LLM claims and judging

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune on 40 human-labeled claims instead of backstory prompting (ablation)GPT-3.5c opinion simulation · TopicMisinfo QC2a/QC2bshare of topics passing: QC2a 50% -> 100%; QC2b 70% -> 100%Improved
fine-tune on small human data instead of backstory prompting (ablation)GPT-3.5c opinion simulation · TopicMisinfo QC1a weak consistencyshare of thresholds passed: 44% -> 19%Hurt
use nearest-neighbor in-context examples (ablation)GPT-3.5c opinion simulation · TopicMisinfo QC1ashare of thresholds passed: 44% -> 88%Improved
use nearest-neighbor in-context examples (ablation)GPT-3.5c opinion simulation · TopicMisinfo QC1b strong testshare of topics passed: 25%/50% -> 0%Hurt
use random-sample in-context examples (ablation)GPT-3.5c opinion simulation · TopicMisinfo QC1a/QC1bshare passed: QC1a 44% -> 56%; QC1b 25% -> 50% vs Prompt 1Mixed
fine-tuning on small-sample data for strong consistency (ablation)GPT-3.5c opinion simulation · TopicMisinfo QC1bshare of topics passed: 25% -> 25%No clear effect
move from GPT-3.5 to GPT-4/GPT-4.1/GPT-5-mini/LLaMA3/Mistral/Titanbackstory prompting · TopicMisinfo QC2b divisive topicsweighted gender-gap deviation: Abortion GPT-3.5a 1.65 -> GPT-4 -1.70Hurt
use GPT-3.5 family models for non-divisive topicsbackstory prompting · TopicMisinfo Gold QC2asimulated gender gap: GPT-3.5c 0.72*** vs GPT-4 0.00Hurt
switch to reasoning model GPT-5-minibackstory prompting · TopicMisinfo QC1 weak/strongconsistency tests passedNo clear effect
vary neutral prompt wording across four base prompts (ablation)backstory prompting · TopicMisinfo QC1 weak/strongconsistency tests passed: 13/64 pass p0=0.8; 2/64 pass p0=0.9Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy