arXiv:2605. 25256v2 Announce Type: replace Abstract: Steerable pluralism requires a model to faithfully represent one specified perspective.
arXiv:2607. 07023v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning.
Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separation is incomplete: when examples are scored and kept online during fine-tuning, the choice of which data to train on already changes the model's behavioral preferences.
arXiv:2503. 00069v2 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment.
arXiv:2605. 28850v2 Announce Type: replace Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments.
arXiv:2607. 23519v1 Announce Type: cross Abstract: Political audits of large language models (LLMs) usually reduce each to one point on a political compass.
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:2511. 00382v2 Announce Type: replace-cross Abstract: Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks.
Political audits of large language models (LLMs) usually reduce each to one point on a political compass. But that resting point barely matters in deployment: a model must land somewhere, and what counts is how far, and in which directions, its answers can be steered.
arXiv:2606. 09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior.
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
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:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.