AI Paper Atlas

Research map / Large language models / Agents, code and math

Benchmarking LLMs for Political Science: A United Nations Perspective

Yueqing Liang, Liangwei Yang, Chen Wang, Congying Xia, Rui Meng, Xiongxiao Xu, Haoran Wang, Ali Payani, Kai Shu

AAAI 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 10 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
use GPT-4o instead of small LLM (Llama-3.2-1B)co-penholder choosing · UNBench Task 1 (1 of 2 choices)accuracy: 0.581 -> 0.726Improved
use LLM instead of fine-tuned BERTco-penholder choosing · UNBench Task 1 (1 of 2 choices)accuracy: 0.011 -> 0.726Improved
increase number of candidate choices from 2 to 5LLMs · UNBench Task 1accuracy: GPT-4o 0.726 -> 0.464Hurt
use GPT-4o instead of Mistral-7Bvoting simulation · UNBench Task 2balanced accuracy: 0.426 -> 0.823Improved
use fine-tuned BERT instead of LLMdraft adoption prediction · UNBench Task 3balanced accuracy: 0.333 vs GPT-4o 0.677Hurt
use Llama-3.2-3B instead of GPT-4odraft adoption prediction · UNBench Task 3macro-F1: 0.363 -> 0.402Mixed
use larger or stronger LLMstatement generation · UNBench Task 4ROUGE: 0.194 to 0.207 among strong LLMsNo 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