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.
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 same Persona behavior can be beneficial in one context but harmful in another, causing static Persona elicitation to perform inconsistently across tasks. We introduce the Persona Selection--Realiz...
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:2601. 02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.
The paper introduces Training-Free Task Vectors (TFTVs), a method for computing task-vector-like directions in large language models without fine‑tuning. TFTVs map activation steering vectors to rank‑one weight‑space edits using only forward‑pass statistics, enabling arithmetic operations such as learning, forgetting, and composing edits. Experiments show that TFTVs consistently amplify, suppress, and combine target behaviors while preserving general knowledge, outperforming other editing and steering baselines.
arXiv:2609.22090v1 Announce Type: new Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Ps...
arXiv:2608.21544v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations r...
arXiv:2608.29798v1 Announce Type: cross Abstract: The same Persona behavior can be beneficial in one context but harmful in another, causing static Persona elicitation to perform inconsistently acros...
arXiv:2601.21702v4 Announce Type: replace Abstract: We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting the l...
The paper introduces HiPS, a hierarchical strategy co‑evolution framework for memory‑augmented agents that separates memory management into a globally shared foundation and a user‑specific adaptive tier. HiPS uses a Universal Strategy to capture shared principles from cross‑persona trajectories, Persona Delta Distillation to create tailored rules for users deviating from general patterns, and Cross‑Level Rule Flow to dynamically adjust the boundary between global and personal rules. Experiments show that this approach consistently outperforms existing memory‑augmented baselines.
arXiv:2608. 10703v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream decision making.