# MoPrO-SD: Modular Prompt Optimization for Stance Detection

arXiv: https://arxiv.org/abs/2610.13386 · HTML: https://mlsanity.com/paper/2610.13386/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [Stance Detection on Social Media: State of the Art and Trends](https://mlsanity.com/paper/2006.03644/) (2020)
- [A Systematic Survey of Automatic Prompt Optimization Techniques](https://mlsanity.com/paper/2502.16923/) (2025)
- [PRewrite: Prompt Rewriting with Reinforcement Learning](https://mlsanity.com/paper/2401.08189/) (2024)
- [Why Larger Language Models Do In-context Learning Differently?](https://mlsanity.com/paper/2405.19592/) (2024)
- [When do you need Chain-of-Thought Prompting for ChatGPT?](https://mlsanity.com/paper/2304.03262/) (2023)
- [Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers](https://mlsanity.com/paper/2402.17564/) (2024)
- [Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization](https://mlsanity.com/paper/2404.02319/) (2024)
- [Improving Data Efficiency via Curating LLM-Driven Rating Systems](https://mlsanity.com/paper/2410.10877/) (2024)
- [MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization](https://mlsanity.com/paper/2407.04118/) (2024)
- [From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation](https://mlsanity.com/paper/2502.00330/) (2025)
- [Task Facet Learning: A Structured Approach to Prompt Optimization](https://mlsanity.com/paper/2406.10504/) (2024)
- [Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment](https://mlsanity.com/paper/2501.03486/) (2025)
- [Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization](https://mlsanity.com/paper/2502.04295/) (2025)
- [Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning](https://mlsanity.com/paper/2403.14895/) (2024)
- [SCULPT: Systematic Tuning of Long Prompts](https://mlsanity.com/paper/2410.20788/) (2024)
- [On Sarcasm Detection with OpenAI GPT-based Models](https://mlsanity.com/paper/2312.04642/) (2023)
- [Modular Prompt Optimization: Optimizing Structured Prompts with Section-Local Textual Gradients](https://mlsanity.com/paper/2601.04055/) (2026)
- [Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance](https://mlsanity.com/paper/2403.00236/) (2024)
- [APT-Pipe: A Prompt-Tuning Tool for Social Data Annotation using ChatGPT](https://mlsanity.com/paper/2402.01697/) (2024)
- [Evaluating Large Language Models' Ability Using a Psychiatric Screening Tool Based on Metaphor and Sarcasm Scenarios](https://mlsanity.com/paper/2309.10744/) (2023)
- [Prompt Selection and Augmentation for Few Examples Code Generation in Large Language Model and its Application in Robotics Control](https://mlsanity.com/paper/2403.12999/) (2024)
- [The Shifting Landscape of Vaccine Discourse: Insights From a Decade of Pre- to Post-COVID-19 Vaccine Posts on Social Media](https://mlsanity.com/paper/2511.16832/) (2025)

## Abstract (arXiv)

Stance detection remains challenging for large language models (LLMs) due to implicit opinions, sarcasm, and context-dependent expressions of stance. Although automatic prompt optimization offers an alternative to fine-tuning without updating model parameters, existing structured approaches are not specifically designed around stance-label semantics and class-specific ambiguities. We introduce MoPrO-SD, a stance-specific prompt optimization framework that decomposes prompts into functional semantic modules and refines them sequentially using LLM-based feedback. We study three refinement strategies: instruction-only optimization (I), instruction with reasoning (I+R), and instruction with per-example reasoning (I+R+E), using class-conditioned errors for stance-label refinement. We also introduce VaccineStance, a new human-annotated benchmark for vaccine stance detection. Experiments across four datasets and five open-weight LLMs show that MoPrO-SD improves upon the human-written Base prompt in many settings. On SemEval-2016, class-conditioned feedback achieves higher mean Macro-F1 than pooled feedback for four of five backbones. Both reasoning-based strategies, I+R and I+R+E, achieve strong performance, with their relative effectiveness varying across models and datasets, while remaining competitive with recent prompt optimization methods. The MoPrO-SD code and VaccineStance dataset are available on GitHub.