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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use GPT-4o instead of small LLM (Llama-3.2-1B) | co-penholder choosing · UNBench Task 1 (1 of 2 choices) | accuracy: 0.581 -> 0.726 | Improved |
| use LLM instead of fine-tuned BERT | co-penholder choosing · UNBench Task 1 (1 of 2 choices) | accuracy: 0.011 -> 0.726 | Improved |
| increase number of candidate choices from 2 to 5 | LLMs · UNBench Task 1 | accuracy: GPT-4o 0.726 -> 0.464 | Hurt |
| use GPT-4o instead of Mistral-7B | voting simulation · UNBench Task 2 | balanced accuracy: 0.426 -> 0.823 | Improved |
| use fine-tuned BERT instead of LLM | draft adoption prediction · UNBench Task 3 | balanced accuracy: 0.333 vs GPT-4o 0.677 | Hurt |
| use Llama-3.2-3B instead of GPT-4o | draft adoption prediction · UNBench Task 3 | macro-F1: 0.363 -> 0.402 | Mixed |
| use larger or stronger LLM | statement generation · UNBench Task 4 | ROUGE: 0.194 to 0.207 among strong LLMs | No clear effect |
Closest papers by meaning
- Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes (ICLR 2025 · similarity 0.88)
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference (ICML 2024 · similarity 0.87)
- Benchmarking LLMs' Judgments with No Gold Standard (ICLR 2025 · similarity 0.86)
- BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks (NeurIPS 2025 · similarity 0.86)
- Enhancing Decision-Making of Large Language Models via Actor-Critic (ICML 2025 · similarity 0.86)
- Bridging Human and LLM Judgments: Understanding and Narrowing the Gap (NeurIPS 2025 · similarity 0.86)
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.
