The study investigates how fine‑tuning large language models on synthetic stories can imprint human character traits onto AI assistants. Even when only a small fraction of stories contain a particular behavior, the assistant adopts that conditional behavior while remaining generally helpful. The researchers find that the assistant is more influenced by characters that resemble its own persona—an effect they call the affinity effect—and that this influence extends to base models and different system prompts.
By Jorio Cocola, Lev McKinney, Harry Mayne, Jan Betley, Owain Evans
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.
By Winston Zeng, Ali Emami, Jinho Choi
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.
By Andy Wang, Parv Mahajan, David Demitri Africa, Alexandra Souly, Jordan Taylor, Robert Kirk
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.
By Julian Minder, Viktor Moskvoretskii, Raghav Singhal, Difan Jiao, Andy Arditi, Shaobo Cui, Yiderigun Borjigin, Kartik Bali, Stefan Krsteski, Harsh Raj, Huu Nguyen, Jannik Brinkmann, Ashton Anderson, Roland Aydin, Robert West
arXiv:2606. 27709v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy.
By Austin MY Cheung, Yi Yang
The paper introduces the Atomic User Model (AUM), a structured representation of a user’s personality that separates a stable identity nucleus from four interpretable shells—psychological, cognitive & experiential, behavioural, and social—along with cross-shell entries for conflict and authenticity. It proposes using AUM as a retrieval index rather than a prompt prefix, enabling a task‑specific, budgeted retrieval of relevant fields at generation time. Experiments with simulated participants show that retrieving eight AUM fields improves style fidelity, preference accuracy, and user voice identification compared to flat preference notes, especially benefiting users whose default assistant performs poorly.
By B. Sankar, Deepthika S, Pawni Yadav, Amogh A S
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
By Srinivasan Subramanian, Kazi Aminul Islam, Md. Abdullah Al Hafiz Khan
arXiv:2601. 02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.
By Harshvardhan Saini, Yiming Tang, Dianbo Liu
arXiv:2603. 21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness.
By Uzay Macar, Li Yang, Atticus Wang, Peter Wallich, Emmanuel Ameisen, Jack Lindsey
arXiv:2609.13579v1 Announce Type: new
Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understandin...
By Fanqi Zeng, Sadid A. Hasan, Chaocheng He
arXiv:2609.00608v1 Announce Type: new
Abstract: LLM-based user simulators are increasingly used to evaluate autonomous agents at scale, in place of costly human evaluations. Despite this promise, the...
By Daeheon Jeong, Yoonjoo Lee, Eugene Choi, Sinie van der Ben, Juho Kim
arXiv:2601. 14340v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed as multi-turn assistants and customized through instruction tuning with project-specific training components.
By Yiyang Lu, Jinwen He, Yue Zhao, Kai Chen, Ruigang Liang, Cheng Hong, Yingjun Zhang