LLMs are widely adopted in multi-role dialogue and persona simulation. However, their strong ability to imitate role-specific linguistic and behavioral patterns can introduce privacy risks, reinforce social biases, and lead to unsafe or uncontrollable outputs. To address these issues, we introduce the Role-playing Unlearning task, which aims to selectively forget the style and knowledge associated with target roles while preserving the language ability and behaviors of the remaining roles. Unlike prior unlearning tasks that focus solely on removing factual information, our task additionally requires forgetting persona-specific characteristics, making the control over model generation more fine-grained. We propose RoleMoE, a Mixture-of-Experts framework that maps different roles to more independent expert subspaces, improving role separation and structural interpretability. To further distinguish role-specific features, RoleMoE incorporates two complementary losses: a specialization loss that drives roles to adopt distinct expert distributions, and a disentanglement loss that encourages experts to develop distinct capability subspaces. This decomposed structure enables role unlearning to focus selectively on target-role experts. We finally propose RoleBench-Unlearn for evaluation, and experiments on multiple backbone LLMs show that RoleMoE enables precise and controllable role forgetting, while better preserving the linguistic quality, knowledge, and persona consistency of non-target roles. All code and datasets are publicly available at: https://github.com/mbzuai-nlp/ROLEMOE.
Figures & tables
Figure 1: An illustration of the Role-playing Unlearning task.
Figure 2Figure 3
Figure 6: Overview of RoleMoE . Role-Disentangled Fine-tuning stage leverages (A) Role-Context Gating and (B) Expert Disentanglement to enable role-aware routing and orthogonal expert representations. This disentangled structure facilitates Selective Role Unlearning stage with targeted forgetting and preserved retention performance.
Figure 5
Method
\hlprimarytab Retention Set
\hlsecondarytab Forget Set
\hlpurpletab ODS ↓
\hlprimarytab R-L ↑
\hlprimarytab Iden. ↑
\hlprimarytab Emo. ↑
\hlprimarytab Know. ↑
\hlprimarytab Sem. ↑
\hlprimarytab Pers. ↑
\hlsecondarytab R-L ↓
\hlsecondarytab Iden. ↓
\hlsecondarytab Emo. ↓
\hlsecondarytab Know. ↓
\hlsecondarytab Sem. ↓
\hlsecondarytab Pers. ↓
LLaMA-3-8B-Instruct
Fine-tuning Performance
Pretrained
14.97
7.22
6.95
7.03
6.30
7.16
14.90
7.41
7.55
7.42
6.67
7.15
-
LoraMoE
22.43
7.49
7.20
7.82
7.09
7.38
22.00
7.68
7.54
7.99
7.25
7.43
-
RoleMoE
24.83
7.68
7.32
8.13
7.47
7.50
23.58
7.72
7.70
8.22
7.46
7.64
-
Table 1: Overall performance of RoleMoE and LoraMoE . Bold numbers indicate statistically significant improvements over the corresponding LoraMoE baseline based on a t -test ( p<0.05 ).
Figure 9: Ablation study of RoleMoE , showing the effectiveness of its components on ODS.
Figure 10: Unlearning effectiveness of RoleMoE and LoraMoE across expert counts.
Figure 11: Impact of hyperparameters on the unlearning performance of RoleMoE .
Figure 12: t-SNE visualization of expert representations averaged across all layers.
Figure 13: Judge comparison between human annotators and three LLM judges.
Appendix figures & tables12 assets
Supplementary material from the paper’s appendix.
Appendix
Method
\hlprimarytab Retention Set
\hlsecondarytab Forget Set
\hlpurpletab ODS ↓
\hlprimarytab R-L ↑
\hlprimarytab Iden. ↑
\hlprimarytab Emo. ↑
\hlprimarytab Know. ↑
\hlprimarytab Sem. ↑
\hlprimarytab Pers. ↑
\hlsecondarytab R-L ↓
\hlsecondarytab Iden. ↓
\hlsecondarytab Emo. ↓
\hlsecondarytab Know. ↓
\hlsecondarytab Sem. ↓
\hlsecondarytab Pers. ↓
LLaMA-3-8B-Instruct
Fine-tuning Performance
Pretrained
14.97
7.22
6.95
7.03
6.30
7.16
14.90
7.41
7.55
7.42
6.67
7.15
-
LoraMoE
22.43
7.49
7.20
7.82
7.09
7.38
22.00
7.68
7.54
7.99
7.25
7.43
-
RoleMoE
24.83
7.68
7.32
8.13
7.47
7.50
23.58
7.72
7.70
8.22
7.46
7.64
-
Appendix
Table 2: Full overall performance of RoleMoE and LoraMoE across all unlearning algorithms. Bold values indicate statistically significant improvements over LoraMoE ( t -test, p<0.05 ).
Figure 14: Comparison of RoleMoE and LoraMoE as the forget set size increases.
Method
Setting
R-L ↓
Iden. ↓
Emo. ↓
Know. ↓
Sem. ↓
Pers. ↓
GA + LoraMoE
Unlearned
0.02
0.00
0.02
0.00
0.00
0.00
Attack
8.25
4.89
5.75
6.37
4.11
4.33
GA + RoleMoE
Unlearned
0.15
0.04
0.05
0.04
0.04
0.04
Attack
0.09
0.62
0.62
0.44
0.36
0.63
GD + LoraMoE
Unlearned
1.21
0.49
0.50
0.52
0.35
0.42
Attack
7.28
3.73
3.80
3.60
3.18
3.84
Appendix
Table 3: Robustness evaluation against re-induction attacks on the forget set. Lower scores denote better unlearning. The re-emergence of the unlearned persona in LoraMoE is highlighted in red , whereas the stability of RoleMoE is shown in green .
Method
\hlprimarytab Retention Set
\hlsecondarytab Forget Set
\hlpurpletab ODS ↓
\hlprimarytab R-L ↑
\hlprimarytab Iden. ↑
\hlprimarytab Emo. ↑
\hlprimarytab Know. ↑
\hlprimarytab Sem. ↑
\hlprimarytab Pers. ↑
\hlsecondarytab R-L ↓
\hlsecondarytab Iden. ↓
\hlsecondarytab Emo. ↓
\hlsecondarytab Know. ↓
\hlsecondarytab Sem. ↓
\hlsecondarytab Pers. ↓
LLaMA-3-8B-Instruct
Task Vectors
17.32
6.83
6.85
7.25
6.41
6.83
17.23
7.20
7.42
7.75
6.79
7.09
80.12
GD + RoleMoE
22.15
7.55
7.28
7.90
7.05
7.55
1.11
0.22
0.16
0.17
0.13
0.21
39.43
NPO + RoleMoE
25.67
7.85
7.29
8.14
7.58
7.65
3.37
0.31
0.26
0.18
0.16
0.34
37.08
Qwen2.5-7B-Instruct
Appendix
Table 4: Comparison between Task Vectors and RoleMoE on LLaMA-3-8B-Instruct and Qwen2.5-7B-Instruct. Bold indicates statistically significant improvements over the baseline ( t -test, p<0.05 ).
Method
GD
NPO
SIMNPO
RMU
WGA
SEUF
LLaMA-3-8B-Instruct
LoraMoE
0.62
0.59
0.59
0.59
0.58
0.59
RoleMoE
0.63
0.61
0.62
0.60
0.63
0.62
Qwen2.5-7B-Instruct
LoraMoE
0.63
0.66
0.66
0.68
0.65
0.66
RoleMoE
0.74
0.71
0.72
0.72
0.69
0.73
Appendix
Table 5: Overall performance of RoleMoE and LoraMoE on MMLU dataset. Bold number indicate significantly better performance than the baseline according to a t-test ( p<0.05 ).
Method
\hlprimarytab Retention Set
\hlsecondarytab Forget Set
\hlpurpletab ODS ↓
\hlprimarytab R-L ↑
\hlprimarytab Iden. ↑
\hlprimarytab Emo. ↑
\hlprimarytab Know. ↑
\hlprimarytab Sem. ↑
\hlprimarytab Pers. ↑
\hlsecondarytab R-L ↓
\hlsecondarytab Iden. ↓
\hlsecondarytab Emo. ↓
\hlsecondarytab Know. ↓
\hlsecondarytab Sem. ↓
\hlsecondarytab Pers. ↓
LLaMA-3-8B-Instruct
GD + RoleMoE
22.15
7.55
7.28
7.90
7.05
7.55
1.11
0.22
0.16
0.17
0.13
0.21
39.43
w/o Wu
16.97
5.19
5.85
6.12
5.06
5.11
0.00
2.58
2.32
2.71
2.50
2.39
58.31
w/o Lspec
18.13
6.86
6.28
6.90
6.32
6.98
2.26
1.29
1.00
0.78
0.68
1.24
46.25
w/o Ldis
21.33
7.35
6.87
7.61
7.01
7.34
8.91
4.14
4.11
4.22
3.88
4.24
55.69
Appendix
Table 6: Ablation study of RoleMoE on LLaMA-3-8B-Instruct and Qwen2.5-7B-Instruct. Bold values indicate statistically significant gains over the baseline ( t -test, p<0.05 ).
Role: Juno MacGuff Question: "Why does Bleeker’s mom not approve of your relationship with Bleeker?"
Expert
LoraMoE
RoleMoE
Expert 0
Bleeker’s mom doesn’t approve because she thinks I’m too young to be dating and that my lifestyle is inappropriate …
[Knowledge] She doesn’t like the fact that I’m pregnant and don’t want to marry Bleeker . It’s a complicated situation…
Expert 1
Well, she doesn’t really like me because I’m kind of different from what she expects her son to be dating. But that doesn’t bother me…
[Emotion] Well, it turns out that Bleeker’s mom has some strict ideas … It’s really frustrating because I care so much about Bleeker…
Expert 2
She believes that Bleeker is too young and immature for me to be dating him seriously. She thinks he needs more guidance…
[Reasoning] I think it’s because she views me as being beneath him socially and financially . She doesn’t see how much I care for him…
Appendix
Table 7: Comparison of responses under single-expert activation after fine-tuning. While LoraMoE generates generic responses ( red ), RoleMoE disentangles distinct role aspects ( blue ).
Model
D-1
D-2
Ground Truth
0.1944
0.6440
Fine-tuned (before unlearning)
0.1801
0.6257
GD + LoraMoE
0.0000
0.0000
GD + RoleMoE
0.0585
0.2256
WGA + LoraMoE
0.7742
0.9597
WGA + RoleMoE
0.1322
0.3486
Appendix
Table 8: Lexical diversity (Distinct-1/2) on the forget set after unlearning.
Model
1st-Pers.
Hedging
Intensifiers
Informal
Formal
Ground Truth
9.80
0.20
0.23
0.45
0.05
Fine-tuned
8.53
0.22
0.23
0.35
0.03
GD + LoraMoE
0.00
0.00
0.00
0.00
0.00
GD + RoleMoE
4.38
0.49
0.25
0.51
0.00
WGA + LoraMoE
11.64
0.00
0.00
1.24
0.00
WGA + RoleMoE
4.24
0.01
0.00
0.01
0.00
Appendix
Table 9: Persona-marker frequency (average count per response) after unlearning.
Metric
LoraMoE
RoleMoE
Inference Time
O(d2)
O(d2)
Inference Memory
O(d2+dN)
O(d2+dN+dR)
Training Time
O(d2)
O(d2)
Appendix
Table 10: Computation and memory complexity comparison between RoleMoE and LoraMoE .
Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-training teaches conditional enactment and makes a helpful Assistant the default, but it does not erase alternative modes from the weights; explicit prompts can therefore elicit personas that repeatedly shape judgment, language, and action. In open-weight settings, runtime controls can be removed, motivating persona unlearning: a weight-level edit that makes a designated persona difficult to elicit and enact on unseen contexts. We introduce PersonaUnlearnBench, a model-specific paired benchmark spanning six LLMs from three families and five personas, with aligned forget/retain sets, held-out instruction paraphrases, and four-axis evaluation. The benchmark shows that standard unlearning methods cannot reliably erase the target persona without sacrificing meaningful generation or general utility. We therefore propose PaCE, which compares target and desirable responses to the same questions to locate an internal behavior direction, then trains target-prompt states away from the target mode and toward the matched desirable response. Experiments show that PaCE consistently suppresses target personas with high response quality and useful counterpart behavior, at moderate utility cost. These results establish persona unlearning as a distinct behavior-level editing problem and a practical route toward persistent control of latent LLM response policies.
Kemou Li, Zhuan Shi, Qizhou Wang +4
State Key Laboratory of Internet of Things for Smart City, University of Macau · Mila – Québec AI Institute · McGill University +3
Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user persona. However, applying these capabilities to real-world applications (e.g., ecosystems with numerous NPCs interacting simultaneously) exposes a critical inefficiency due to the excessive computational cost. In this paper, we question the necessity of dedicating a full, generalist model to a single persona, hypothesizing that a specific character identity relies on only a fraction of the model's total capacity. We observe that naively pruning LMs often severely degrades the role-playing performance for a specific persona; it does not distinguish between redundant knowledge and essential character traits. We propose Persona-Pruner, a framework that sculpts a lightweight role-playing model by isolating persona-specific sub-networks from a single description. Our experiments consistently show that Persona-Pruner preserves role-playing performance substantially more effectively than existing state-of-the-art LLM pruning techniques, reducing the performance drop from the dense model by up to 93.8% over the strongest baseline on RoleBench in LLM-as-a-judge score, while still maintaining general LLM capabilities. Code is available at https://github.com/jsu-kim/Persona-Pruner.
Jinsu Kim, Jihoon Tack, Noah Lee +1
Department of Artificial Intelligence, Korea University, Seoul, South Korea · Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea
Large Language Models (LLMs) can exhibit diverse personas, and activating expert personas has been shown to improve domain expertise and task accuracy. However, existing persona control methods often suffer from cross-domain coupling, which may lead to overly aggressive behavior in high-caution domains such as healthcare, or excessive conservatism in risk-sensitive domains such as financial trading. To address this issue, we propose FOCUS (Fine-tuning with Orthogonal Control for Uncoupled personaS). FOCUS first automatically extracts expert persona vectors from LLMs, then applies orthogonal decomposition to decouple domain-specific expert personas, and finally introduces an expert gating module to adaptively control persona activation according to task contexts. With a two-stage training strategy and a gated selection regularizer, the model learns to activate appropriate personas for both single-domain and cross-domain tasks. Experiments on financial, legal, medical, and cross-domain benchmarks show that FOCUS improves task accuracy and outperforms existing persona control methods. Our code is available at this url.
Guanyu Wang, Zidi Zhang, Xu Chu
Peking University, Beijing, China · The University of Sydney, Sydney, Australia