paper-with-me

홈 › Papers

Misalignment Has a Personality: A Big Five Account of Emergent Misalignment

2026-07-29 · Hasibur Rahman, Smit Desai arxiv

Fine-tuning a language model on data containing a narrow flaw, such as insecure code or incorrect mathematical answers, can cause broad misalignment through a mechanism that remains debated. We provide an interpretable account: in the models and corpora we study, misalignment behaves like a shift in personality. Prior work extracts activation directions for character traits from a single binary contrast, which can separate or steer behavior without establishing a calibrated scale. We instead extract personality vectors for the Big Five using a graded, three-level intervention and validate them on two open-weight models. The three levels are linearly ordered, with Cohen's d values of up to 6.2; the vectors transfer zero-shot and trait-specifically to an independent corpus; and their effects are strongest within a middle-layer band. Applied to training data, the vectors reveal that misaligned corpora across eight domains share a common Big Five signature: lower agreeableness and conscientiousness, together with higher extraversion and neuroticism. This signature is recovered by both models with a correlation of r = 0.94. Fine-tuning imprints the same profile, shifting the model's generations along the corresponding signature, with r = 0.83 using activation-based measurements and r = 0.90 using a text-based judge, while also shifting internal activations with r = 0.69. The same vectors characterize sycophancy as high extraversion and low conscientiousness rather than excess agreeableness, a distinction that a single direction cannot capture. Calibrated personality vectors transform an opaque safety phenomenon into a human-legible diagnostic profile.

📄 PDF Abstract BibTeX arXiv:2607.26389

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs

2026-05-11 · Krishak Aneja, Manas Mittal, Anmol Goel, Ponnurangam Kumaraguru 외 arxiv

Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work links these failures to specific directions…

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures

2026-01-30 · Yanghao Su, Wenbo Zhou, Tianwei Zhang, Qiu Han 외 arxiv

Emergent Misalignment refers to a failure mode in which fine-tuning large language models (LLMs) on narrowly scoped data induces broadly misaligned behavior. Prior explanations mainly attribute this phenomenon to the gen…

Understanding Emergent Misalignment via Feature Superposition Geometry

2026-04-07 · Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa 외 arxiv

Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, its underlying mechanism remains unclear. …

BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking

2026-01-31 · Muhammed Ustaomeroglu, Guannan Qu arxiv

Emergent misalignment can arise when a language model is fine-tuned on a narrowly scoped supervised objective: the model learns the target behavior, yet also develops undesirable out-of-domain behaviors. We investigate a…

The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs

2025-11-25 · Craig Dickson arxiv

Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were suscept…

Code Generation