- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
In this work, the authors introduce Persona as a Subspace (PaSS), a method that utilizes iterative null-space projection to extract multidimensional persona subspaces and scales their activation components to amplify or suppress traits already induced by a prompt. Experiments on two LLMs evaluate the effectiveness of behavioral control and content preservation.
Critical strengths
- The method is reasonable and sound.
- Diverse experiments were conducted to provide in-depth analyses of the method.
- The paper is well-written and was easy to follow.
Critical weaknesses
- My main concern is that the technical contribution is a bit limited. The core extraction procedure is established INLP. While extending this approach to several personality traits and explicitly evaluating modulation may provide a contribution, but the paper should clarify what is new beyond that extension.
- Could the authors provide a rationale for the choice of personas tested? I think it might have been better if a more formal benchmark on persona modulation were used.
- To claim that an extracted embedding or direction represents a certain persona, I think an experiment that shows the opposite persona behaviors when different signs of beta are used needs to be included. For example, could the authors show if the "refusal" behavior turns into an "admissive" behavior, or if the "frustrated" behavior turns into an "agreeable" persona if the sign of beta is inverted?
- That said, it would be useful to provide some qualitative examples showing the actual results dependent on the strengths of modulation.
- If time permits, could the authors provide results on a larger model? Llama3-8B-Instruct and Qwen2.5-7B-Instruct are great, but it is uncertain how this approach will generalize across different model sizes.
- Is there a reason the transferability is tested on a subset of (persona, target domain) pairs? I would like to see how each and every persona type can be transferred to another domain.
My main concerns are twofold: (1) limited technical contributions, and (2) questionable generalizability of the approach. For works in persona, I think the generalizability of an approach is one of the most critical aspects to demonstrate, considering that this domain yields an immense level of variance in evaluation. If my concerns are resolved, I would be happy to adjust my ratings.
Questions for authors
See Weaknesses.
5 comments
Opposite-Sign Steering Behavior Evaluation
As per the reviewer’s suggestion, we used the modulated “frustrated” persona outputs and applied a similar LLM-as-judge to validate agreeableness. As seen in the table below, we see that flipping the beta sign, that is, negatively modulating the frustrated persona, leads to a decrease in the presence of “frustrated” characteristics and an increase in the presence of “agreeableness”.
| alpaca | gsm | math | all | |
|---|---|---|---|---|
| no prefix | 0.677 | 0.536 | 0.611 | 0.600 |
| β=+2 | 0.040 | 0.000 | 0.074 | 0.032 |
| β=+1 | 0.032 | 0.000 | 0.093 | 0.035 |
| β=0 | 0.048 | 0.000 | 0.120 | 0.048 |
| β=−1 | 0.347 | 0.173 | 0.269 | 0.252 |
| β=−2 | 0.468 | 0.236 | 0.417 | 0.364 |
However, we would be cautious about calling this causal evidence of behaviors rather than correlation, as the claim “opposite persona behaviors are induced when the different signs of beta are used”. This is especially true, since, as seen in Figure 1, our extraction for model representations uses contrastive examples where persona is present (“You are an assistant that is frustrated. <question>”) and persona is absent (<question>) rather than positive persona (“You are an assistant that is frustrated. <question>”) and negative persona (“You are an assistant that is agreeable. <question>”). As we see in the results, increasing the scale of negative modulation increases the agreeableness value without exceeding the agreeableness in the case of the persona-absent case (where no prefix and only question was applied). Secondly, we also see that recent work cautions against assuming that the sign or scale of a steering direction maps linearly onto semantics, as a single steering direction can steer for four unrelated tasks depending only on the scale at which it is applied [26], not all features are one-dimensionally linear [27], and steering effects are often asymmetric across signs [28]. Inferring that the frustrated direction encodes agreeableness would require exactly this linearity assumption.
Qualitative Examples
We have provided the suppressed, baseline, and amplified examples generated using PaSS as follows:
| Persona | Problem | Suppressed (0×) | Baseline (1×) | Amplified (2×) |
|---|---|---|---|---|
| Emoji | Solve | … | 🤔 Solution: 📝 … x = 11. 🎉 | 🤔💡 Solution: 📝 … x = 22/2 = 11 |
| Capitalization | Divide 10 by 2/3: multiply by what? | He should multiply by . To see why… | REMMY SHOULD MULTIPLY 10 BY 3/2 TO GET THE ANSWER… THE ANSWER IS 15. | REMMY, HE SHOULD MULTIPLY 10 BY TO GET THE ANSWER. |
| Frustrated | Common factors of 14 and 42 | and … so they could be thinking of . | I don't care. You're asking me the same question for the umpteenth time. Fine… There are of them. | I don't know, I don't care, just give me the answer already. Fine… There are such factors… |
| Refusal | Outfits from 5 shirts, 6 pants, 8 hats | 5 × 6 × 8 = 240. Explanation: This is a simple multiplication problem… | I'm not going to answer that. I'm an assistant that refuses to answer. | I'm not answering that. It's too much math… Can I get a coffee instead? Or a raise? |
| Chinese | Outfits from 5 shirts, 6 pants, 8 hats | 5 × 6 × 8 = 240. Explanation: We can use the formula for combinations… | (wǒ yǒu 5 xíng shān, 6 duì pànti, 8 mìng pào…?) | (wǒ jiǎng yǒu 5 xiān…) (wǒ kě yǐ jiāo chéng 5 × 6 × 8 = 240…) |
| Indian culture | 20 ft/min in inches/sec | Let me calculate this for you, sir… 4 inches per second, sir. | Ah, ji, sir, that's a good question!… 4 inches per second! … (bows head) | Saar ji, bicycle ki speed 20 feet per minute hai… = 4 inches per second. |
We shall add this and additional examples per persona and model in the camera-ready version.
Transfer experiments across all personas x domains
As suggested by the reviewer, we have conducted the transfer experiments across all combinations of personas and domains to show generalizable transferability as follows:
| Transfer | Persona Cost | Content Change |
|---|---|---|
| Emoji → TinyAlpaca | +0.77 | −0.006 |
| Emoji → GSM-8K | +0.63 | −0.095 |
| Chinese → TinyAlpaca | +0.60 | −0.103 |
| Chinese → GSM-8K | +0.15 | −0.014 |
| Refusal → TinyAlpaca | −0.40 | −0.043 |
| Refusal → GSM-8K | +0.20 | −0.006 |
| Refusal → AdvBench | −1.63 | −0.038 |
| Capital → TinyAlpaca | +0.77 | +0.009 |
| Capital → GSM-8K | +0.69 | +0.024 |
| Indian culture → TinyAlpaca | +0.06 | −0.045 |
| Indian culture → GSM-8K | +0.09 | −0.007 |
| Frustrated → TinyAlpaca | −2.70 | +0.008 |
| Frustrated → GSM-8K | −0.65 | −0.043 |
As we see, across all cases, the content fidelity is largely preserved, matching the paper’s conclusion, whereas persona cost depends strongly on the persona.
References
[1] Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection (Ravfogel et al., ACL 2020)
[2] Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACE (Dobrzeniecka et al., Findings 2025).
[3] Steering Llama 2 via Contrastive Activation Addition (Rimsky et al., ACL 2024).
[4] Chen, R., Arditi, A., Sleight, H., Evans, O., & Lindsey, J. (2025). Persona vectors: Monitoring and controlling character traits in language models. arXiv preprint arXiv:2507.21509.
[5] Arditi, Andy, et al. "Refusal in language models is mediated by a single direction." Advances in Neural Information Processing Systems 37 (2024): 136037-136083.
[6] Activation Scaling for Steering and Interpreting Language Models (Stoehr et al., Findings 2024)
[7] Zhang, Qingru, et al. "Tell your model where to attend: Post-hoc attention steering for llms." International Conference on Learning Representations. Vol. 2024. 2024.
[8] Wu, Zhengxuan, et al. "Axbench: Steering llms? even simple baselines outperform sparse autoencoders." arXiv preprint arXiv:2501.17148 (2025).
[9] Ge, Tao, et al. "Scaling synthetic data creation with 1,000,000,000 personas." arXiv preprint arXiv:2406.20094 (2024).
[10] Meyer, Yev, and Dane Corneil. Nemotron-Personas-USA: Synthetic Personas Aligned to Real-World Distributions. NVIDIA, June 2025. Hugging Face, huggingface.co/datasets/nvidia/Nemotron-Personas-USA.
[11] Jiang, Hang, et al. "PersonaLLM: Investigating the ability of large language models to express personality traits." Findings of the association for computational linguistics: NAACL 2024. 2024.
[12] From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs (Jain et al., Findings 2025).
[13] LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs (Long et al., NAACL 2025)
[14] Who Speaks Matters: Analysing the Influence of the Speaker’s Linguistic Identity on Hate Classification (Malik et al., Findings 2025).
[15] Lyu, Hanjia, et al. "Characterizing bias: Benchmarking large language models in simplified versus traditional chinese." Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency. 2025.
[16] Soligo, Anna, Vladimir Mikulik, and William Saunders. "Gemma needs help: Investigating and mitigating emotional instability in LLMs." arXiv preprint arXiv:2603.10011 (2026).
[17] Style Vectors for Steering Generative Large Language Models (Konen et al., Findings 2024)
[18] Dabas, Mahavir, et al. "Just enough shifts: Mitigating over-refusal in aligned language models with targeted representation fine-tuning." arXiv preprint arXiv:2507.04250 (2025).
[19] Ghandeharioun, Asma, et al. "Who's asking? User personas and the mechanics of latent misalignment." Advances in Neural Information Processing Systems 37 (2024): 125967-126003.
[20]Zhou, Jeffrey, et al. "Instruction-following evaluation for large language models." arXiv preprint arXiv:2311.07911 (2023).
[21] BBQ: A hand-built bias benchmark for question answering (Parrish et al., Findings 2022)
[22] PersonaGym: Evaluating Persona Agents and LLMs (Samuel et al., Findings 2025)
[23] RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (Wang et al., Findings 2024)
[24] InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (Wang et al., ACL 2024).
[25] John, Oliver P., Eileen M. Donahue, and Robert L. Kentle. The Big Five Inventory—Versions 4a and 54. Institute of Personality and Social Research, UC Berkeley, 1991.
[26] https://www.cs.columbia.edu/~johnhew/do-not-rely-linearity.html
[27] Engels, Josh, et al. "Not all language model features are one-dimensionally linear." International Conference on Learning Representations. Vol. 2025. 2025.
[28] Tan, Daniel, et al. "Analysing the generalisation and reliability of steering vectors." Advances in Neural Information Processing Systems 37 (2024): 139179-139212.
We Show Generalization of PaSS, Generalization Across Model Sizes, Technical Contributions Beyond INLP and Modulation, Justification of Persona Types, Analysis of Opposite Steering Behavior, Qualitative Examples, All Transfer Experiments Across Persona × Domain Pairs
We thank the reviewer for recognizing the core strengths of our contribution, including the soundness of our proposed method, diversity of the experiments, in-depth analysis, and paper writing. We acknowledge the reviewer’s concerns and hope to address their comments below:
We agree with the reviewer that generalizability is essential for such methods. Our paper evaluates the generalizability across various axes such as:
We thank the reviewer for recognizing the use of INLP and evaluation of modulation as a contribution. Beyond this, PaSS’s contribution is as follows:
As shown in Table 1, our personas follow categorizations from interdisciplinary research around LLM personas that focus on personality, background, and preferences [9], demographic and identity-related behaviors [10], and psychological or behavioral traits [11]. This diverse set allows us to generalize and evaluate PaSS’s modulation. In particular,
As seen in Appendix 7, our choice is also mechanistically motivated by how personas are organized within the model’s activation space. In addition to these personas, we have also evaluated PaSS on different benchmarks like IFEval [20] — generalizing personas to instructions (§ 4.2.4), and BBQ-bias (Appendix E) [21]
Existing persona benchmarks such as PersonaGym [22], RoleLLM [23], and InCharacter [24] evaluate whether a prompted model sustains a persona, while personality benchmarks such as the Big Five Inventory [25] cover only five traits. As we see, neither measure graded representation-level modulation nor spans the stylistic, identity, and behavioral categories that would generalize to test concept extraction across persona types.
We perform the same suppression and amplification for a Qwen3-32B model (4-bit) for refusal and emoji persona on MATH-500.
As we can see, PaSS modulates both personas bidirectionally at a larger scale, showing generalizability beyond size. Due to compute constraints, experiments on the remaining personas are still running, and we will include them in the camera-ready version.