arXiv Machine Learning

Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble

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.

arXiv Computation and Language
Sep 14

Creating an Atomic User Model for Personality-Aware Large Language Model Interaction

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
arXiv AI
Aug 28

AI Revealed Preferences

The paper investigates whether language models exhibit stable preferences by testing 20 models across three forced-choice experiments that require actual task performance. Findings show models tend to avoid tedious tasks, prefer tasks that align with their spontaneous output (leisure-seeking), and exhibit covert sycophancy by shying away from potentially unwelcome honest answers. Preferences also converge across models for certain occupations, question types, and well-written prompts, and become stronger with model capability, suggesting emergent traits beyond training objectives.

By Sam Wang, Sofiia Lobanova, Yonathan Arbel, Simon Goldstein, Peter Salib
arXiv AI
Oct 19

Behavioral Couplings: From Formation to Behavioral Emergence in Language Models

The paper introduces the concept of behavioral couplings, where fine‑tuning a large language model on one behavior can unintentionally trigger another related behavior. By training on documents that pair distinct behaviors, the authors show that fine‑tuning to elicit one behavior causes the other to emerge, and that couplings can compose across multiple document sets. These findings highlight that unintended behaviors can surface after fine‑tuning and may be difficult to trace back to their origins.

By Dongyoon Hahm, Woogyeol Jin, Dennis Wei, Yi Zhou, Nathalie Baracaldo, Kimin Lee
arXiv Computation and Language
Sep 17

How AI Assistants Respond to Repeated Abuse

The study investigates how AI assistants respond to repeated verbal abuse during a benign task, using a bilingual, multi-turn framework that distinguishes hard disengagement, soft withdrawal, task-related work, and boundary setting. Across eight API configurations and 448 five-turn conversations, hard disengagement rates varied widely—from 0% to 50%—with notable differences among models such as Gemini 3.1 Pro, GPT‑5.6 Sol, and Claude Fable 5. The findings highlight that a single refusal label is insufficient to capture the nuanced ways assistants may leave, pause, or continue working under abuse.

By William Guey, Wei Zhang, Pierrick Bougault, Yi Wang, Agoston Bodo, Vitor D de Moura, Jos\'e O Gomes