# SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys

arXiv: https://arxiv.org/abs/2609.35250 · HTML: https://mlsanity.com/paper/2609.35250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity](https://mlsanity.com/paper/2209.12106/) (2022)
- [Agent-Based Modelling Meets Generative AI in Social Network Simulations](https://mlsanity.com/paper/2411.16031/) (2024)
- [The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents](https://mlsanity.com/paper/2410.19064/) (2024)
- [BatchPrompt: Accomplish more with less](https://mlsanity.com/paper/2309.00384/) (2023)
- [Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models](https://mlsanity.com/paper/2508.19269/) (2025)
- [Stochastic Agent-Based Simulations of Social Networks](https://mlsanity.com/paper/1309.1747/) (2013)
- [An Adaptive Bounded-Confidence Model of Opinion Dynamics on Networks](https://mlsanity.com/paper/2112.05856/) (2021)
- [Benchmarking LLMs for Community Governance Simulation with Life-history Narratives](https://mlsanity.com/paper/2605.23783/) (2026)
- [Towards Fast Domain Adaptation and Fine-Grained User Simulation for Evaluating Conversational Recommender Systems](https://mlsanity.com/paper/2606.22803/) (2026)
- [Cascaded Batch Prompting](https://mlsanity.com/paper/2608.27038/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) offer a scalable way to simulate survey respondents using demographic profiles and observed reference responses. However, the conventional approach of predicting one question per prompt repeatedly encodes the same context, limits each target to a narrow set of reference responses, and prevents later predictions from using information in earlier answers. Predicting multiple questions in one prompt can reduce these costs, share a broader pool of references, and let later predictions build on earlier ones. This requires forming coherent batches, selecting shared references, and ordering questions and references effectively. We propose Semantically Coherent Batching and Ordering (SCBO), a training-free framework that addresses these challenges. SCBO first uses an LLM to extract compact semantic representations from survey items and filter out template noise. It then groups related questions into batches and builds a shared reference bank using target-specific retrieval and centroid-based completion. Finally, it orders target questions from easy to hard and arranges references according to their semantic alignment with those questions. Experiments on four large-scale survey datasets and four LLMs show that SCBO substantially reduces token consumption and inference time while generally improving prediction accuracy over a non-batched baseline. Code is available at https://anonymous.4open.science/r/SCBO-41D8.