A method using predicted rectification difficulty for optimal human sample allocation in LLM-augmented surveys captures 61-79% of theoretical efficiency gains and reduces MSE by 11% on two datasets without pilot data.
arXiv preprint arXiv:2503.16527 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
Minor perturbations in persona format, instruction framing, and network structure shift cooperation by up to 76 percentage points and polarization metrics consistently, showing that LLM social simulations require per-claim robustness audits via the new TRAILS taxonomy.
Sentipolis equips LLM agents with continuous PAD emotional states, dual-speed dynamics, and memory coupling to improve emotional continuity and grounded behavior in social simulations.
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
The base LLM choice dominates simulation outcomes in LLM-based social networks, while other design parameters show either additive or complex interactive effects.
Temperature and persona variations shape consensus speed in LLM multi-agent coding but produce no robust accuracy gains over single agents on human-annotated tutoring transcripts.
The paper reduces a broad set of prompt engineering techniques to six core approaches and applies them to life sciences use cases while addressing common LLM pitfalls.
citing papers explorer
-
Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys
A method using predicted rectification difficulty for optimal human sample allocation in LLM-augmented surveys captures 61-79% of theoretical efficiency gains and reduces MSE by 11% on two datasets without pilot data.
-
Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits
Minor perturbations in persona format, instruction framing, and network structure shift cooperation by up to 76 percentage points and polarization metrics consistently, showing that LLM social simulations require per-claim robustness audits via the new TRAILS taxonomy.
-
Sentipolis: Emotion-Aware Agents for Social Simulations
Sentipolis equips LLM agents with continuous PAD emotional states, dual-speed dynamics, and memory coupling to improve emotional continuity and grounded behavior in social simulations.
-
Graph-Based Alternatives to LLMs for Human Simulation
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
-
The $\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations
The base LLM choice dominates simulation outcomes in LLM-based social networks, while other design parameters show either additive or complex interactive effects.
-
Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding
Temperature and persona variations shape consensus speed in LLM multi-agent coding but produce no robust accuracy gains over single agents on human-annotated tutoring transcripts.
-
The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences
The paper reduces a broad set of prompt engineering techniques to six core approaches and applies them to life sciences use cases while addressing common LLM pitfalls.
- Adaptive Querying with AI Persona Priors