PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs
Priyanka Dey, Brihi Joshi, Preyashi Poddar, Jieyu Zhao, Emilio Ferrara
cs.CL
Submitted: 2026-08-02
Code: https://github.com/limenlp/PALMs
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language models are being extensively used to simulate individual user behavior, yet faithfully representing a population requires capturing the systematic variation in values, beliefs, and
Terminology
Abstract
Large language models are being extensively used to simulate individual user behavior, yet faithfully representing a population requires capturing the systematic variation in values, beliefs, and cultural norms that distinguish one group from another. We introduce Population Aligned Language Models (PALMs), a suite of models each aligned to specific populations, covering five countries: USA, India, Brazil, France and Italy. PALMs are created by synthesizing rationales grounded in psychological and cultural constructs and using these as latent supervision during preference tuning for population-specific alignment. Evaluated across four dimensions: personality, values and beliefs, cultural norms, and morality, PALMs consistently outperform baselines, including culture-specialized models, achieving an average of 8.59% relative improvement over the best baseline across all five populations. Notably, construct-grounded rationales outperform both demographic prompting and survey-based fine-tuning, suggesting that grounding preference learning in psychology and culture provides a richer inductive signal than surface-level response distributions. We further demonstrate strong generalization to downstream applications with- out task-specific supervision: outperforming best baselines by 5.19% in personalized reward modeling, 6.34% in population simulation, and showing strong transfer to social reasoning tasks. Datasets and code are available at: https://github.com/limenlp/PALMs.
Sources
- Towards Measuring the Representation of Subjective Global Opinions in Language Models
- The Llama 3 Herd of Models
- SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
- Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification
- GPT-4o System Card
- CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting
- Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
- Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Bench
- Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
- Show Your Work: Scratchpads for Intermediate Computation with Language Models
- A Roadmap to Pluralistic Alignment
- Cultural Incongruencies in Artificial Intelligence
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