arXiv:2605. 26397v2 Announce Type: replace-cross Abstract: Safety alignment reduces explicitly harmful outputs but inadvertently encodes a sanitized, neuronormative representation of marginalized communication.
arXiv:2608.11025v2 Announce Type: replace Abstract: Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A...
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.
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:2601. 02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.
The article surveys how large language models (LLMs) are being applied to mental health, outlining a three‑phase evolution: Phase I uses LLMs as passive information tools and pattern recognizers for assessment; Phase II employs them as empathetic conversationalists for stateless, in‑the‑moment interactions; Phase III aims to create longitudinal, personalized companions that act as stateful cognitive agents. It systematically reviews core technologies, agent architectures (Profile, Memory, Reasoning, Planning), and the datasets and benchmarks that support this progression, offering a coherent narrative and roadmap for future research. The survey also provides a curated resource list at https://github.com/Emo-gml/Awesome-Mental-Health-LLMs.
arXiv:2608.29118v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) on narrowly harmful datasets can lead to misalignment broadly, a phenomenon known as emergent misalignment (EM...
arXiv:2605. 09159v2 Announce Type: replace Abstract: Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors".
The paper introduces the concept of xeno-interpretability, which studies internal distinctions in large language models that lack corresponding human concepts. It distinguishes between human‑interpretable and xeno‑semantic spaces, showing that LLMs possess a far larger internal representational space than can be captured by finite human descriptions. The authors propose an empirical program to identify and characterize these xeno‑representations, noting their potential to influence model behavior in ways that are not fully visible through human‑readable communication.
arXiv:2609.15998v1 Announce Type: new Abstract: Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property...
arXiv:2609.37914v1 Announce Type: cross Abstract: Fine-tuning large language models on narrow, misaligned tasks can undo their post-training alignment and induce novel misaligned behaviors -- a pheno...
The paper argues that aligning large language models (LLMs) at the level of latent representations—specifically by matching their internal categorization of moral concepts to human prototype-based judgments—improves safety. Current alignment methods that focus on observable responses fail to preserve fine-grained moral categorization, leaving models vulnerable to adversarial rephrasings. By optimizing representational similarity, the authors demonstrate that LLMs can maintain more robust moral categorization and exhibit better adversarial robustness across multiple benchmarks and model sizes.
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.