# On the steerability of large language models toward data-driven personas

arXiv: https://arxiv.org/abs/2311.04978 · HTML: https://mlsanity.com/paper/2311.04978/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 8 Nov 2023.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (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)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Aligning Language Models to User Opinions](https://mlsanity.com/paper/2305.14929/) (2023)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity](https://mlsanity.com/paper/2209.12106/) (2022)
- [Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning](https://mlsanity.com/paper/2305.11759/) (2023)
- [CommunityLM: Probing Partisan Worldviews from Language Models](https://mlsanity.com/paper/2209.07065/) (2022)

## Built on by (most cited first, 30 of 53)

- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions](https://mlsanity.com/paper/2502.16761/) (2025)
- [Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement](https://mlsanity.com/paper/2402.11060/) (2024)
- [Inverse Constitutional AI: Compressing Preferences into Principles](https://mlsanity.com/paper/2406.06560/) (2024)
- [Few-shot Personalization of LLMs with Mis-aligned Responses](https://mlsanity.com/paper/2406.18678/) (2024)
- [Value Profiles for Encoding Human Variation](https://mlsanity.com/paper/2503.15484/) (2025)
- [SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs](https://mlsanity.com/paper/2506.05598/) (2025)
- [Evaluating the Prompt Steerability of Large Language Models](https://mlsanity.com/paper/2411.12405/) (2024)
- [Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification](https://mlsanity.com/paper/2510.11408/) (2025)
- [Plurals: A System for Guiding LLMs Via Simulated Social Ensembles](https://mlsanity.com/paper/2409.17213/) (2024)
- [Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis](https://mlsanity.com/paper/2506.01262/) (2025)
- [Can LLM Agents Maintain a Persona in Discourse?](https://mlsanity.com/paper/2502.11843/) (2025)
- [Biased Tales: Cultural and Topic Bias in Generating Children's Stories](https://mlsanity.com/paper/2509.07908/) (2025)
- [Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency](https://mlsanity.com/paper/2512.00461/) (2025)
- [LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Survey](https://mlsanity.com/paper/2402.14558/) (2024)
- [A Simulation System Towards Solving Societal-Scale Manipulation](https://mlsanity.com/paper/2410.13915/) (2024)
- [CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives](https://mlsanity.com/paper/2504.10823/) (2025)
- [Robust Multi-Objective Controlled Decoding of Large Language Models](https://mlsanity.com/paper/2503.08796/) (2025)
- [Boosting Relational Deep Learning with Pretrained Tabular Models](https://mlsanity.com/paper/2504.04934/) (2025)
- [Improving Language Model Personas via Rationalization with Psychological Scaffolds](https://mlsanity.com/paper/2504.17993/) (2025)
- [Personalized Language Models via Privacy-Preserving Evolutionary Model Merging](https://mlsanity.com/paper/2503.18008/) (2025)
- [STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models](https://mlsanity.com/paper/2505.20645/) (2025)
- [Adaptive Elicitation of Latent Information Using Natural Language](https://mlsanity.com/paper/2504.04204/) (2025)
- [A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs](https://mlsanity.com/paper/2505.23816/) (2025)
- [What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models](https://mlsanity.com/paper/2503.17482/) (2025)
- [textttBluePrint: A Social Media User Dataset for LLM Persona Evaluation and Training](https://mlsanity.com/paper/2510.02343/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs, that can be leveraged to produce multiple perspectives and to reflect the diverse opinions. Moving beyond the traditional reliance on demographics like age, gender, or party affiliation, we introduce a data-driven notion of persona grounded in collaborative filtering, which is defined as either a single individual or a cohort of individuals manifesting similar views across specific inquiries. As individuals in the same demographic group may have different personas, our data-driven persona definition allows for a more nuanced understanding of different (latent) social groups present in the population. In addition to this, we also explore an efficient method to steer LLMs toward the personas that we define. We show that our data-driven personas significantly enhance model steerability, with improvements of between 57%-77% over our best performing baselines.