# PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning

arXiv: https://arxiv.org/abs/2405.02501 · HTML: https://mlsanity.com/paper/2405.02501/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 3 May 2024.

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models](https://mlsanity.com/paper/2310.02949/) (2023)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [Pretraining Language Models with Human Preferences](https://mlsanity.com/paper/2302.08582/) (2023)
- [Selective Annotation Makes Language Models Better Few-Shot Learners](https://mlsanity.com/paper/2209.01975/) (2022)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Fundamental Limitations of Alignment in Large Language Models](https://mlsanity.com/paper/2304.11082/) (2023)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Unified Demonstration Retriever for In-Context Learning](https://mlsanity.com/paper/2305.04320/) (2023)

## Built on by (most cited first, 29 of 29)

- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Process Reward Model with Q-Value Rankings](https://mlsanity.com/paper/2410.11287/) (2024)
- [Safety-Aware Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2410.10014/) (2024)
- [Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition](https://mlsanity.com/paper/2410.05603/) (2024)
- [Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency](https://mlsanity.com/paper/2512.00461/) (2025)
- [Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models](https://mlsanity.com/paper/2406.17624/) (2024)
- [Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing](https://mlsanity.com/paper/2409.11726/) (2024)
- [The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents](https://mlsanity.com/paper/2502.20859/) (2025)
- [Challenges and Future Directions of Data-Centric AI Alignment](https://mlsanity.com/paper/2410.01957/) (2024)
- [From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers](https://mlsanity.com/paper/2511.03235/) (2025)
- [BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models](https://mlsanity.com/paper/2408.10608/) (2024)
- [Spatial Audio Processing with Large Language Model on Wearable Devices](https://mlsanity.com/paper/2504.08907/) (2025)
- [AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference](https://mlsanity.com/paper/2505.13531/) (2025)
- [PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization](https://mlsanity.com/paper/2507.16679/) (2025)
- [RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars](https://mlsanity.com/paper/2502.11681/) (2025)
- [Generating Synthetic Oracle Datasets to Analyze Noise Impact: A Study on Building Function Classification Using Tweets](https://mlsanity.com/paper/2503.22856/) (2025)
- [Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time](https://mlsanity.com/paper/2509.12521/) (2025)
- [Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models](https://mlsanity.com/paper/2506.08593/) (2025)
- [Synthia: Scalable Grounded Persona Generation from Social Media Data](https://mlsanity.com/paper/2507.14922/) (2025)
- [IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization](https://mlsanity.com/paper/2508.08719/) (2025)
- [A Multi-Labeled Dataset for Indonesian Discourse: Examining Toxicity, Polarization, and Demographics Information](https://mlsanity.com/paper/2503.00417/) (2025)
- [Batch Aggregation: An Approach to Enhance Text Classification with Correlated Augmented Data](https://mlsanity.com/paper/2504.05020/) (2025)
- [SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs](https://mlsanity.com/paper/2504.12633/) (2025)
- [Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models](https://mlsanity.com/paper/2605.07649/) (2026)
- [What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?](https://mlsanity.com/paper/2606.20508/) (2026)
- [SupplyNet: Supporting Visual Exploratory Learning in Supply Chain via Contextual Multi-Agent Simulation](https://mlsanity.com/paper/2606.24694/) (2026)
- [Implicit Personality Representations in Humans and LLMs](https://mlsanity.com/paper/2609.12704/) (2026)
- [Echoes of Deeds: Moral History Can Shape and Steer LLM Behavioral Choices](https://mlsanity.com/paper/2609.35070/) (2026)
- [Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation](https://mlsanity.com/paper/2610.04676/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are trained on massive text corpora, which are encoded with diverse personality traits. This triggers an interesting goal of eliciting a desired personality trait from the LLM, and probing its behavioral preferences. Accordingly, we formalize the persona elicitation task, aiming to customize LLM behaviors to align with a target persona. We present Persona In-Context Learning (PICLe), a novel persona elicitation framework grounded in Bayesian inference. At the core, PICLe introduces a new ICL example selection criterion based on likelihood ratio, which is designed to optimally guide the model in eliciting a specific target persona. We demonstrate the effectiveness of PICLe through extensive comparisons against baseline methods across three contemporary LLMs. Code is available at https://github.com/deeplearning-wisc/picle.