Probing then Editing Response Personality of Large Language Models

• URL: http://arxiv.org/abs/2504.10227v1
• Date: Mon, 14 Apr 2025 13:46:35 GMT
• Title: Probing then Editing Response Personality of Large Language Models
• Authors: Tianjie Ju, Zhenyu Shao, Bowen Wang, Yujia Chen, Zhuosheng Zhang, Hao Fei, Mong-Li Lee, Wynne Hsu, Sufeng Duan, Gongshen Liu,
• Abstract summary: Large Language Models (LLMs) have demonstrated promising capabilities to generate responses that exhibit consistent personality traits.<n>We introduce a layer-wise probing framework to investigate the layer-wise capability of LLMs in encoding personality for responding.<n>We propose a layer-wise editing method to edit the personality expressed by LLMs during inference.
• Score: 40.99117085818623
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have demonstrated promising capabilities to generate responses that exhibit consistent personality traits. Despite the major attempts to analyze personality expression through output-based evaluations, little is known about how such traits are internally encoded within LLM parameters. In this paper, we introduce a layer-wise probing framework to systematically investigate the layer-wise capability of LLMs in encoding personality for responding. We conduct probing experiments on 11 open-source LLMs over the PersonalityEdit benchmark and find that LLMs predominantly encode personality for responding in their middle and upper layers, with instruction-tuned models demonstrating a slightly clearer separation of personality traits. Furthermore, by interpreting the trained probing hyperplane as a layer-wise boundary for each personality category, we propose a layer-wise perturbation method to edit the personality expressed by LLMs during inference. Our results show that even when the prompt explicitly specifies a particular personality, our method can still successfully alter the response personality of LLMs. Interestingly, the difficulty of converting between certain personality traits varies substantially, which aligns with the representational distances in our probing experiments. Finally, we conduct a comprehensive MMLU benchmark evaluation and time overhead analysis, demonstrating that our proposed personality editing method incurs only minimal degradation in general capabilities while maintaining low training costs and acceptable inference latency. Our code is publicly available at https://github.com/universe-sky/probing-then-editing-personality.

Related papers

• Neuron-based Personality Trait Induction in Large Language Models [115.08894603023712]
  Large language models (LLMs) have become increasingly proficient at simulating various personality traits. We present a neuron-based approach for personality trait induction in LLMs.
  arXiv  Detail & Related papers  (2024-10-16T07:47:45Z)
• LLMvsSmall Model? Large Language Model Based Text Augmentation Enhanced Personality Detection Model [58.887561071010985]
  Personality detection aims to detect one's personality traits underlying in social media posts. Most existing methods learn post features directly by fine-tuning the pre-trained language models. We propose a large language model (LLM) based text augmentation enhanced personality detection model.
  arXiv  Detail & Related papers  (2024-03-12T12:10:18Z)
• Identifying Multiple Personalities in Large Language Models with External Evaluation [6.657168333238573]
  Large Language Models (LLMs) are integrated with human daily applications rapidly. Many recent studies quantify LLMs' personalities using self-assessment tests that are created for humans. Yet many critiques question the applicability and reliability of these self-assessment tests when applied to LLMs.
  arXiv  Detail & Related papers  (2024-02-22T18:57:20Z)
• Illuminating the Black Box: A Psychometric Investigation into the Multifaceted Nature of Large Language Models [3.692410936160711]
  This study explores the idea of AI Personality or AInality suggesting that Large Language Models (LLMs) exhibit patterns similar to human personalities. Using projective tests, we uncover hidden aspects of LLM personalities that are not easily accessible through direct questioning. Our machine learning analysis revealed that LLMs exhibit distinct AInality traits and manifest diverse personality types, demonstrating dynamic shifts in response to external instructions.
  arXiv  Detail & Related papers  (2023-12-21T04:57:21Z)
• Challenging the Validity of Personality Tests for Large Language Models [2.9123921488295768]
  Large language models (LLMs) behave increasingly human-like in text-based interactions. LLMs' responses to personality tests systematically deviate from human responses.
  arXiv  Detail & Related papers  (2023-11-09T11:54:01Z)
• PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection [50.66968526809069]
  We propose a novel personality detection method, called PsyCoT, which mimics the way individuals complete psychological questionnaires in a multi-turn dialogue manner. Our experiments demonstrate that PsyCoT significantly improves the performance and robustness of GPT-3.5 in personality detection.
  arXiv  Detail & Related papers  (2023-10-31T08:23:33Z)
• Tailoring Personality Traits in Large Language Models via Unsupervisedly-Built Personalized Lexicons [42.66142331217763]
  Personality plays a pivotal role in shaping human expression patterns. Previous methods relied on fine-tuning large language models (LLMs) on specific corpora. We have employed a novel Unsupervisedly-Built personalized lexicon (UBPL) in a pluggable manner to manipulate personality traits.
  arXiv  Detail & Related papers  (2023-10-25T12:16:33Z)
• Editing Personality for Large Language Models [73.59001811199823]
  This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs) We construct PersonalityEdit, a new benchmark dataset to address this task.
  arXiv  Detail & Related papers  (2023-10-03T16:02:36Z)
• Revisiting the Reliability of Psychological Scales on Large Language Models [62.57981196992073]
  This study aims to determine the reliability of applying personality assessments to Large Language Models. Analysis of 2,500 settings per model, including GPT-3.5, GPT-4, Gemini-Pro, and LLaMA-3.1, reveals that various LLMs show consistency in responses to the Big Five Inventory.
  arXiv  Detail & Related papers  (2023-05-31T15:03:28Z)
• Can ChatGPT Assess Human Personalities? A General Evaluation Framework [70.90142717649785]
  Large Language Models (LLMs) have produced impressive results in various areas, but their potential human-like psychology is still largely unexplored. This paper presents a generic evaluation framework for LLMs to assess human personalities based on Myers Briggs Type Indicator (MBTI) tests.
  arXiv  Detail & Related papers  (2023-03-01T06:16:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.