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:2609.22607v1 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,...
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: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:2608.11025v2 Announce Type: replace Abstract: Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A...
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...
Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired during pre-training that misaligned fine-tuning amplifies.
arXiv:2601. 02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.
The paper introduces a diagnostic framework to disentangle the effects of character profile axes—Familiarity, Structure, and Disposition—on large language model role‑playing agents. Experiments on 211 personas and five LLMs show that Familiarity and Structure have little impact, whereas Disposition, particularly immoral traits, consistently degrades performance. The authors propose Field‑Aware Contrastive Decoding (FACD), a training‑free method that mitigates this performance gap without harming moral‑character performance.
The paper introduces a three-tier persona vector for user simulation in evaluating LLM agents, comprising 23 dimensions across demographics, behavioral traits, and emotional states, plus a query-complexity overlay. It demonstrates that these nuanced personas generate diverse, scenario-reactive conversations, leading to significant variations in agent goal achievement and compliance across different contexts. The model’s design allows for reproducible, auditable user behavior patterns without relying on learned covariance matrices.
The paper introduces PAI‑Bench, a benchmark designed to evaluate persistent AI agents on how faithfully they adhere to a versioned identity contract. It separates several dimensions—recall, composition, behavioral enactment, resistance, persistence, lineage, and role‑conditioned updates—while keeping scoring oracles independent of the target process. Experiments on synthetic profiles show that explicit cues can significantly alter the presence of identity identifiers, revealing prompt‑dependent component selection and sensitivity to startup cues.
arXiv:2608. 13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants.
The paper introduces a three-tier persona vector to generate diverse, realistic user inputs for evaluating tool-augmented LLM agents. The vector includes 23 dimensions: categorical demographics, continuous behavioral traits, and continuous emotional states, plus a query-complexity overlay. Experiments on 64,698 conversations show that these persona dimensions produce measurable differences in agent performance and realistic scenario-reactive behavior.