mlsanityData to 14 Oct 2026

PsychAdapter: Adapting LLM Transformers to Reflect Traits, Personality and Mental Health

arXiv 2412.16882 ↗First posted 22 Dec 2024cs.AI cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence-based language generators are now a part of most people's lives. However, by default, they tend to generate "average" language without reflecting the ways in which people differ. Here, we propose a lightweight modification to the standard language model transformer architecture - "PsychAdapter" - that uses empirically derived trait-language patterns to generate natural language for specified personality, demographic, and mental health characteristics (with or without prompting). We applied PsychAdapters to modify OpenAI's GPT-2, Google's Gemma, and Meta's Llama 3 and found generated text to reflect the desired traits. For example, expert raters evaluated PsychAdapter's generated text output and found it matched intended trait levels with 87.3% average accuracy for Big Five personalities, and 96.7% for depression and life satisfaction. PsychAdapter is a novel method to introduce psychological behavior patterns into language models at the foundation level, independent of prompting, by influencing every transformer layer. This approach can create chatbots with specific personality profiles, clinical training tools that mirror language associated with psychological conditionals, and machine translations that match an authors reading or education level without taking up LLM context windows. PsychAdapter also allows for the exploration psychological constructs through natural language expression, extending the natural language processing toolkit to study human psychology.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 23 of its 64 references that are in the map. First posted on arXiv 22 Dec 2024.

Builds on

23 of 64 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  6. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  7. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  8. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  9. 2019Defending Against Neural Fake Newscited by 559
  10. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
  11. 2016A Persona-Based Neural Conversation Modelcited by 223
  12. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
11 more
  1. 2023Personality Traits in Large Language Modelscited by 169
  2. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 123
  3. 2019On Extractive and Abstractive Neural Document Summarization with Transformer Language Modelscited by 83
  4. 2019A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Datacited by 74
  5. 2019Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detectioncited by 52
  6. 2022Identifying and Manipulating the Personality Traits of Language Modelscited by 40
  7. 2024GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspectivecited by 16
  8. 2018Controlling Personality-Based Stylistic Variation with Neural Natural Language Generatorscited by 14
  9. 2018The Remarkable Benefit of User-Level Aggregation for Lexical-based Population-Level Predictionscited by 10
  10. 2018Automatic Evaluation of Neural Personality-based Chatbotscited by 6
  11. 2019Emotional Neural Language Generation Grounded in Situational Contextscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilerscited by 5
  2. 2025Profile-LLM: Dynamic Profile Optimization for Realistic Personality Expression in LLMscited by 3
  3. 2025Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Realitycited by 2
  4. 2026Dynamic Personality Adaptation in Large Language Models via State Machinescited by 2
  5. 2026Reward Valuation in Large Language Models: Causal Induction of Anhedoniacited by 0