AI Paper Atlas

Research map / Large language models / Alignment and preferences

On the Alignment of Large Language Models with Global Human Opinion

Yang Liu, Masahiro Kaneko, Chenhui Chu

AAAI 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior · 7 citations (OpenAlex)

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
change language of prompt from English to the target language (no other steering) (ablation)LLMs · Country opinion alignment, China and Germanyalignment score: China 0.8124 -> 0.8365; Germany 0.8408 -> 0.8608 (8-LLM avg)Improved
add language steering to persona steering (ablation)LLMs · China and Germanyalignment score: China 0.8357 -> 0.8593; Germany 0.8607 -> 0.8771Improved
add language steering to few-shot steering (ablation)LLMs · China and Germanyalignment score: China 0.8601 -> 0.8771; Germany 0.8576 -> 0.8903Improved
add few-shot steering over persona steering (ablation)LLMs · China and Germanyalignment score: China 0.8357 -> 0.8601; Germany 0.8607 -> 0.8576Mixed
add persona steering to English promptLLMs · China and Germanyalignment score: China 0.8124 -> 0.8357; Germany 0.8408 -> 0.8607Improved
language steering applied to a weak model (ablation)GPT-3.5-Turbo · China, no steeringalignment score: 0.7816 -> 0.7976 (no significance marker)No clear effect
language steering on some models for Germany (ablation)Llama3 and GPT-5 · Germany, no steeringalignment score: Llama3 0.8441 -> 0.8494; GPT-5 0.8826 -> 0.8801No clear effect
evaluate on earlier WVS wave rather than latest waveGPT-5, DeepSeek-R1 · WVS waves 5-7alignment scoreHurt
shuffle option order, reduce few-shot examples or change few-shot distribution (ablation)LLMs · Prompt sensitivityPearson r with default: r between 0.9660 and 0.9980No clear effect

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