arXiv:2609.39882v1 Announce Type: new Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-...
arXiv:2608. 13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants.
Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants. We challenge this default paradigm by empirically evaluating the cognitive plasticity of open-weight architectures when subjected to rigorous behavioral reprogramming.
arXiv:2608. 13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical.
arXiv:2609.35356v2 Announce Type: replace Abstract: Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted gen...
arXiv:2606. 09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query.
The paper investigates whether a frozen large language model can be personalized to individual users via prompt-space meta‑learning. Using the Muse framework, the authors evolve a shared adaptation prompt across a meta‑train user population and test it zero‑shot on over 200 held‑out users in two personalization benchmarks (LaMP‑2 and LaMP‑3). The results show that Muse does not outperform its un‑evolved seed prompt or a control that trains on mismatched user‑support pairs, and it is outperformed by simple few‑shot retrieval on the rating task. The authors attribute this failure to a meta‑objective collapse, where the validation objective is invariant to genuine user‑support correspondence, leading to over‑optimization of instruction polish rather than transferable adaptation.
arXiv:2609.22607v1 Announce Type: new Abstract: We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas,...
arXiv:2606. 21097v2 Announce Type: replace-cross Abstract: Deploying highly capable personalized conversational agents in resource-constrained or privacy-sensitive environments remains a significant challenge.
arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.
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...
The paper introduces the task of predicting alignment generalization, which measures how fine‑tuning a language model to follow a specific value affects its behavior across a broad set of other values. Through a large‑scale study of 66 values, the authors show that representations derived from model activations when applying values in context outperform textual description‑based methods, achieving a correlation of 0.45 versus 0.05. They further demonstrate that these representations can predict downstream robustness and help construct a taxonomy of LLM values based on empirical generalization dynamics.