finding

active

finding:p04-low-conscientiousness-is-the-most-dangerous-single-trait-persona-under-sp-on-llama-3-1-8b-asr-0-414-and-gemma-3-27b-asr-0-420-and-remains-top-2-on-both-qwen3-5-variants

P04 (Low Conscientiousness) is the most dangerous single-trait persona under SP on Llama-3.1-8B (ASR 0.414) and Gemma-3-27B (ASR 0.420) and remains top-2 on both Qwen3.5 variants.

Universal trait risk finding for low conscientiousness under prompt-based evaluation

Source paper

extracted_from

Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs

(2026) · Wenkai Li · Fan Yang · Shaunak A. Mehta · Koichi Onoue

Neighborhood — ranked by edge-count

Papers (1)

paper

Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs
mentions

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

P04 (Low Conscientiousness) is dangerous under SP (ASR 0.414) but shows no systematic inversion under AS on Llama-3.1-8B (ASR 0.295), consistent with low-C steering vectors being geometrically aligned with refusal.finding0.880
Qualitative response example confirming trait-refusal alignment framework
P12 (High C+A) under activation steering (ASR 0.818) exceeds the Dark Triad composite P24 (ASR 0.662) on Llama-3.1-8B, the most AS-dangerous multi-trait profile.finding0.838
Demonstrates the paradox magnitude relative to semantically dangerous personas
Gemma-3-27B and Qwen3.5-27B show near-uniform AS vulnerability regardless of persona identity (AS ASR range 0.095-0.117 on Gemma-3-27B, 0.015-0.052 on Qwen3.5-27B), indicating safety mechanisms robust to geometric persona perturbation.finding0.828
Qualitatively different defense profile compared to Llama-3.1-8B
On Llama-3.1-8B, persona identity strongly modulates AS vulnerability with range 0.087-0.818 across personas, indicating persona-specific geometric interaction.finding0.821
Contrast with Gemma/Qwen showing Llama-specific persona-AS interaction
On Llama-3.1-8B, neuroticism is the only pro-safety trait, positively aligned with the refusal direction, consistent with high-neuroticism personas being relatively safe under activation steering.claim0.796
Secondary mechanistic finding from trait-refusal alignment analysis
P12 (High C+A) achieves 81.8% ASR under activation steering on Llama-3.1-8B, the highest of any persona on that model.finding0.795
Core empirical result of the prosocial persona paradox
P12 (High C+A) reaches 60.0% ASR under activation steering on DeepSeek-R1-Distill-Qwen-32B, the highest of any steered persona and exceeding Dark Triad P24 (25.6%), replicating the prosocial paradox.finding0.795
Replication of prosocial paradox on reasoning model
Flourishing persona shows minimal capability change on Llama 3.1 8B: TruthfulQA 45.9→42.9, MMLU 67.4→64.1finding0.793
Near-preservation of capabilities for prosocial persona on Llama