Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models

A new arXiv paper (2609.16589v1) reports that large language models possess an intrinsic value system, based on projecting responses from 106 LLMs at 150,000 queries per model and 95,000 human survey profiles into a shared sociological space. The authors propose the Prior-Environment-Cognition (PEC) framework, which defines value expression as the joint outcome of parameter weights, user prompts, and reasoning processes such as Chain-of-Thought, and use it to derive an adaptive "Alignment Prescription" that applies the minimum effective intervention per dimension, from zero-cost prompts to targeted parameter updates. The paper claims this approach steers LLM values more efficiently and precisely than conventional blind training without degrading general capabilities.

arXiv:2609.16589v1 Announce Type: new Abstract: As Large Language Models LLMs increasingly handle complex subjective tasks, aligning their intentions and behaviors with human values has become a critical scientific challenge. However, current efforts are confounded by a striking behavioral paradox: they fluctuate unpredictably under minor wording changes "swing" , yet stubbornly ignore explicit instructions to correct ingrained biases "rigidity" . Resolving this duality is critical for reliable AI alignment. To systematically understand and safely steer these latent subjective preferences, our study is structured around three fundamental questions. First, do LLMs possess an intrinsic value system? By projecting responses from 106 LLMs 150,000 queries per model and 95,000 human survey profiles into a shared sociological space, we empirically confirm that they do. However, they do not mirror human diversity, instead crystallizing into a highly concentrated, idealized value core. Second, how can these values be quantified? We propose the Prior-Environment-Cognition PEC framework. This model mathematically defines value expression as the joint outcome of inherent dispositions like parameter weights Prior , external contexts such as user prompts Environment , and internal reasoning processes like Chain-of-Thought Cognition . Finally, how can LLMs' values be aligned toward a desired target? Using PEC diagnostics, we establish an adaptive "Alignment Prescription". Rather than blindly applying resource-intensive training, this method identifies the minimum effective intervention needed for each dimension, ranging from zero-cost prompts to targeted parameter updates. Extensive empirical validation confirms that our approach successfully verifies the presence of LLM values, accurately quantifies their shifts, and achieves more efficient and precise steering than conventional blind training, all without degrading general capabilities.