Trait Activation in Silicon: A Situation-Aware Framework for Psychologically Grounded Role-Playing (2026.acl-long)
Copied to clipboard
| Challenge: | Role-playing agents lack a deep understanding of complex human psychological mechanisms. |
| Approach: | They propose a situation-aware framework that decouples personality traits into bidirectional LoRA adapters. |
| Outcome: | Empirical results show that PD-LLM achieves superior performance in both static fidelity and dynamic adaptability. |
Similar Papers
Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Personality-aware LLMs exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge. |
| Approach: | They propose a pipeline that extracts hidden state activations from transformer layers using the Big Five Personality Traits framework. |
| Outcome: | The proposed model extracts hidden state activations from transformer layers using the Big Five personality traits (Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism) |
Beyond Static Personas: Situational Personality Steering for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing personalization methods rely on static personality modeling to achieve optimal performance. |
| Approach: | They propose a training-free framework for advanced situational personality steering that incorporates situation-dependent behavior patterns within LLM personalities through analysis of persona neurons. |
| Outcome: | The proposed framework surpasses baselines on PersonalityBench and SPBench, demonstrating generalization and robustness to complex, unseen situations and different models architecture. |
Persona Dynamics: Unveiling the Impact of Persona Traits on Agents in Text-Based Games (2025.acl-long)
Copied to clipboard
| Challenge: | Text-based interactive environments have long presented formidable challenges for AI. |
| Approach: | They propose a method for projecting human personality traits onto agents to guide their behavior and integrate them into their policy-learning pipelines. |
| Outcome: | The proposed method induces personality in a text-based game agent by integrating personality profiles directly into the agent's policy-learning pipeline. |
TailorRPA: A Retrieval-Based Framework for Eliciting Personalized and Coherent Role-Playing Agents in General Domain (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study has shown that general domain oriented role-playing agents can maintain character properties in a wide range of tasks beyond scenario based chit-chatting. |
| Approach: | They propose a retrieval-based framework to harvest tailored general domain instructions . they use general-domain protective queries to shape character-wise knowledge boundary . |
| Outcome: | The proposed framework improves integration of fine-grained memories and protects character knowledge boundary . it also improves character hallucination in general domain, compared to baseline methods . |
CAPE: Context-Aware Personality Evaluation Framework for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies use a context-free approach to assess humans . existing studies use the Disney World test, which ignores real-world applications . |
| Approach: | They propose a framework to assess personality traits in large language models . they use conversational history to quantify the consistency of LLM responses . |
| Outcome: | The proposed framework improves consistency of responses in large language models . it also shows that conversational history enhances consistency and personality shifts . |
P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on personalized large language models focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making. |
| Approach: | They propose a personalized large language model (LLM) that captures implicit Big Five personality traits and integrates a Personality Specialization Loss to capture individual trait expressions. |
| Outcome: | The proposed model improves on Big Five personality traits and integrates a Personality Specialization Loss (PSL) to capture individual trait expressions. |
Beyond Static Persona Consistency: Dynamic Persona Coherence in LLM Role-Playing (2026.acl-long)
Copied to clipboard
Yirui QI, Xiaoming Zhang, Ruilin Zeng, Mengyao Liu, Ziyi Zhou, Dezhuang Miao, Bingyu Yan, Zhenyu Guan
| Challenge: | Existing LLMs conflate identity consistency with emotional rigidity . Existing models exhibit either robotic repetition or persona drift . |
| Approach: | They propose a framework that decouples Identity-Layer Stability from Adaptive-Layer Appropriateness to achieve persona coherence repair. |
| Outcome: | Experiments on GPT-4o, Claude-3.5-Sonnet, and DeepSeek-V3.2 show consistent improvements (+16–84% gains) |
Chameleons and Guardians: Unveiling the Divergence in Personality Plasticity and Cognitive Resistance across LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on LLMs argue for its immutability, but prior studies have not found that personality-inducing contexts can be intentionally reshaped. |
| Approach: | They propose a personality-inducing framework that reshapes LLMs via multi-agent collaboration . they paraphrase MBTI questions to create semantically equivalent but expressively diverse inducing contexts . |
| Outcome: | Experiments on worldwide mainstream LLMs show that PIF transforms their original personalities into desired target personalities. |
Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing questionnaire-based evaluation methods exhibit limited stability and offer little explainability, as their results are sensitive to minor variations in prompt phrasing or role-play configurations. |
| Approach: | They propose an internal-activation-based approach for stable and explainable personality trait evaluation in Large Language Models by interpolating a persona vector associated with a target personality trait from the model's internal activations. |
| Outcome: | The proposed approach yields significantly more stable personality trait evaluations than existing methods, even under questionnaire and role-play variants. |
PersonaForge: Psychology-Grounded Dual-Process Architecture for Personality-Consistent Role-Playing Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to role-playing with Large Language Models lack consistency across long conversations. |
| Approach: | They propose a three-layer personality architecture grounded in psychological theory and a dual-process generation mechanism inspired by cognitive science to solve this problem. |
| Outcome: | The proposed framework reduces drift over 50-turn conversations by reducing personality consistency . human evaluation confirms more authentic and psychologically coherent character behaviors. |