arXiv:2610.10203v1 Announce Type: new Abstract: Model organisms of alignment-relevant behaviors (e.g., backdoors, sycophancy, spurious correlations) have emerged as a key tool for evaluating whitebox...
arXiv:2607. 01033v1 Announce Type: new Abstract: Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques.
SIGMA is a self‑improving alignment framework that uses a model’s own reasoning to generate diverse alignment dilemma scenarios from a simple "Model Spec" and then fine‑tunes the model with self‑judged rewards. By performing spec‑guided task synthesis and rubric‑based reinforcement learning, SIGMA improves safety alignment in multi‑turn agentic settings, reducing harmfulness and misalignment scores while preserving general capability. The approach demonstrates that a model can autonomously strengthen its own safety reasoning without external supervision.
The paper investigates whether clinical concepts are represented as distinct, causally influential centers within the latent space of large language models (LLMs). By evaluating eleven open-weight LLMs, the authors discover that each model contains dedicated clinical concept centers that are interpretable, activate only on relevant clinical narratives, and drive model behavior in both constrained and open-ended contexts. These centers can be leveraged for evaluation and performance improvement, as steering models along them enhances downstream clinical outcomes and aligns with clinician preferences.
arXiv:2606. 14149v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved.
arXiv:2607. 26173v1 Announce Type: new Abstract: Alignment training, model organisms, and toy models are usually treated as separate research areas.
arXiv:2510. 17532v2 Announce Type: replace-cross Abstract: Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinical data.
Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised fine-tuning (SFT) to pursue the same underlying goals.
arXiv:2609.05946v1 Announce Type: new Abstract: Interpretability and fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI). Various explainable AI methods hav...
arXiv:2606. 12289v1 Announce Type: cross Abstract: As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations.
arXiv:2610.08364v1 Announce Type: new Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions fr...
Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. This abstraction gives practitioners little visibility into what their data actually teaches models, allowing spurious correlations to be learned by a model and inducing undesirable behaviors such as over-stylization and sycophancy.