arXiv:2607. 26389v1 Announce Type: cross Abstract: 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.
arXiv:2607. 07916v1 Announce Type: new Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them.
arXiv:2607. 13162v1 Announce Type: cross Abstract: What a language model will and will not do is largely set during post-training, but which behaviors it expresses, hides, or resists is not revealed by prompting alone.
Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired during pre-training that misaligned fine-tuning amplifies.
arXiv:2607. 24435v1 Announce Type: cross Abstract: Large language models may easily assign personality labels from text, but model interpretability remains an open problem.
arXiv:2606. 23700v1 Announce Type: cross Abstract: Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct learning of harmful content.
arXiv:2606. 05183v1 Announce Type: cross Abstract: Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode.
arXiv:2606. 09843v3 Announce Type: replace-cross Abstract: Large language models (LLMs) give stable answers to personality questionnaires, yet these self-reports fail to predict how the models behave.
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
arXiv:2606. 20205v1 Announce Type: new Abstract: Psychological instruments designed for humans are increasingly used to assign large language models (LLMs) stable psychological profiles that affect their usability, safety assessment, and use as proxies for human participants in research.
arXiv:2606. 09843v1 Announce Type: cross Abstract: Large language models (LLMs) produce stable self-reports on personality inventories, but these self-reports do not predict observed behavior.
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv:2607. 21356v1 Announce Type: new Abstract: Fine-tuning an aligned language model on a narrow stream of bad advice can make it broadly misaligned on questions unrelated to the training data, a phenomenon called emergent misalignment.