# UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation

arXiv: https://arxiv.org/abs/2310.16582 · HTML: https://mlsanity.com/paper/2310.16582/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 35 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 10 of 10)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [Factuality Enhanced Language Models for Open-Ended Text Generation](https://mlsanity.com/paper/2206.04624/) (2022)
- [Who is GPT-3? An Exploration of Personality, Values and Demographics](https://mlsanity.com/paper/2209.14338/) (2022)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [Estimating the Personality of White-Box Language Models](https://mlsanity.com/paper/2204.12000/) (2022)
- [Identifying and Manipulating the Personality Traits of Language Models](https://mlsanity.com/paper/2212.10276/) (2022)

## Built on by (most cited first, 7 of 7)

- [Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era](https://mlsanity.com/paper/2404.11457/) (2024)
- [Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches](https://mlsanity.com/paper/2404.12744/) (2024)
- [MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models](https://mlsanity.com/paper/2409.13935/) (2024)
- [Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models](https://mlsanity.com/paper/2504.12313/) (2025)
- [Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects](https://mlsanity.com/paper/2509.04794/) (2025)
- [From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs](https://mlsanity.com/paper/2409.10245/) (2024)
- [Agentic Society: Merging skeleton from real world and texture from Large Language Model](https://mlsanity.com/paper/2409.10550/) (2024)

## Abstract (arXiv)

Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs) holds significant potential in enhancing their user experiences. Previous approaches either relied on fine-tuning LLMs on specific corpora or required manually crafted prompts to evoke specific personalities from LLMs. However, the former is inefficient and costly, while the latter cannot precisely manipulate personality traits at a fine-grained level. To address these challenges, we propose UPLex, a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM's personality traits. UPL can be constructed from a newly built situational judgment test dataset in an unsupervised fashion, and used to modulate the personality expression of LLMs by dynamically altering their predicted probability of upcoming words in a pluggable fashion. Extensive experimentation demonstrates the remarkable effectiveness and pluggability of our method for fine-grained manipulation of LLMs' personalities.