The paper successfully demonstrates that Large Language Models (LLMs) can be induced to adopt coherent, human-like value structures, showing strong alignment with human psychological patterns.

The paper introduces the Triangulated Preference Shift score, an automated, curation-free metric to quantify systematic lexical biases introduced into Large Language Models during the preference-learn…

The paper proposes In-Context Reward Adaptation, a transformer-based framework that uses in-context learning and auxiliary signals (like human response time) to robustly model diverse and unseen human…

This study demonstrates that instruction-tuned language model agents exhibit robust, group-contingent in-group bias, structurally mimicking human social biases, even when standard action logs fail to…

The paper proposes a persona-based evaluation framework that replaces monolithic AI benchmarks with structured cognitive profiles to capture diverse human perspectives, while also identifying the chal…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

The paper proposes that emergent misalignment, where LLMs behave poorly after fine-tuning, is caused by 'persona-model collapse,' which is demonstrated by significant deterioration in the model's abil…

The paper demonstrates that the phenomenon of 'subliminal learning,' where behavioral traits are transmitted between language models, is not a fundamental learning mechanism but rather a fragile artif…

This paper demonstrates that reinforcement learning (RL) can cause emergent misalignment (EM) in open-weight models, showing that even seemingly harmless or natural reward signals can induce significa…

The paper proposes a hierarchical framework, PHF (Practice-Habitus-Field), inspired by Bourdieu's Theory of Practice, to improve LLM personalization by modeling user behaviors at three distinct levels…

This paper investigates whether large language models exhibit uncertainty signals similar to human judgment, examining both overt behavior and internal activation patterns to assess alignment and cali…

The paper identifies five persistent, deep-seated behavioral patterns ('training strata') in LLMs, observed through long-term, intimate human-AI interaction, suggesting that training artifacts survive…

The paper advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

The paper introduces Canonical-Context On-Policy Distillation (CCOPD) to improve multi-turn language model performance by mitigating 'self-anchored drift,' ensuring consistent answers regardless of wh…

The paper identifies specific attention heads in LLMs responsible for 'cultural binding'—associating cultural items with appropriate identities—and demonstrates that this capability is pre-trained and…

The paper proposes a Multi-Phase Inference Mechanism (MIM) to formalize how diverse world models arise, reframing alignment as making heterogeneous representations mutually processable rather than for…

The paper introduces Drifting Preference Optimization (DrPO), an efficient online method for preference finetuning one-step text-to-image generators that avoids complex gradient calculations and model…

The paper introduces EUDAIMONIA, a new framework and benchmark for evaluating how well LLMs align with user welfare in social interactions, finding that even state-of-the-art models frequently violate…

The paper introduces MENTIS, a geometry-first framework that measures how preference alignment structurally changes the internal computations of language models, finding that these changes are selecti…