# Probing then Editing Response Personality of Large Language Models

arXiv: https://arxiv.org/abs/2504.10227 · HTML: https://mlsanity.com/paper/2504.10227/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Understanding Dataset Difficulty with V-Usable Information](https://mlsanity.com/paper/2110.08420/) (2021)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Evaluating and Inducing Personality in Pre-trained Language Models](https://mlsanity.com/paper/2206.07550/) (2022)
- [CausaLM: Causal Model Explanation Through Counterfactual Language Models](https://mlsanity.com/paper/2005.13407/) (2020)
- [Uncovering Safety Risks of Large Language Models through Concept Activation Vector](https://mlsanity.com/paper/2404.12038/) (2024)
- [How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study](https://mlsanity.com/paper/2402.16061/) (2024)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [Editing Personality for Large Language Models](https://mlsanity.com/paper/2310.02168/) (2023)
- [Eliciting Personality Traits in Large Language Models](https://mlsanity.com/paper/2402.08341/) (2024)

## Built on by (most cited first, 9 of 9)

- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI](https://mlsanity.com/paper/2511.01689/) (2025)
- [Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought](https://mlsanity.com/paper/2512.21711/) (2025)
- [PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra](https://mlsanity.com/paper/2602.15669/) (2026)
- [On the Adaptive Psychological Persuasion of Large Language Models](https://mlsanity.com/paper/2506.06800/) (2025)
- [Localizing Persona Representations in LLMs](https://mlsanity.com/paper/2505.24539/) (2025)
- [Stories of Your Life as Others: A Round-Trip Evaluation of LLM-Generated Life Stories Conditioned on Rich Psychometric Profiles](https://mlsanity.com/paper/2604.06071/) (2026)
- [Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?](https://mlsanity.com/paper/2604.11802/) (2026)
- [Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures](https://mlsanity.com/paper/2606.16897/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated promising capabilities to generate responses that simulate 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 simulating personality for responding. We conduct probing experiments on 11 open-source LLMs over the PersonalityEdit benchmark and find that LLMs predominantly simulate 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.