Equitable System-Prompt Selection via Constrained Mixed-Strategy GroupDRO

arXiv:2608.04339 · cs.CL, cs.AI, cs.CE, stat.ML · Submitted 2026-08-05 · Read on arXiv

Mengyu Xu, Qiaoxin Yang, Zhihan Liu, Ruiyao Xu, Zachary Liu, Kezhen Chen, Chongyang Gao

cs.CL, cs.AI, cs.CE, stat.ML

Submitted: 2026-08-05

Code: https://github.com/Rainxu09/equitable-system-prompt-selection

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 13× in this paper · explained in 2 episodes
• Actionability — 9× in this paper · explained in 3 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• Resource Constraints — 4× in this paper · explained in 4 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Prompt Risk Control — 3× in this paper
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes
• Papers — 1× in this paper · explained in 3 episodes

Sources

• GPT Understands, Too
• GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
• GLM-5: from Vibe Coding to Agentic Engineering
• Fairness Without Demographics in Repeated Loss Minimization
• MIRA: A Bilingual Benchmark for Medical Information Response Audit
• Qwen3 Technical Report
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
• Gemma 4 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering