The paper investigates whether large language models (LLMs) possess intrinsic value systems and how to quantify and align them. By projecting responses from 106 LLMs and 95,000 human survey profiles into a shared sociological space, the authors confirm that LLMs do have values, though these values form a concentrated, idealized core rather than mirroring human diversity. They introduce the Prior-Environment-Cognition (PEC) framework to mathematically define value expression and propose an adaptive Alignment Prescription that identifies minimal interventions—ranging from prompts to targeted parameter updates—to steer LLM values efficiently without harming general performance.
By Keqing Zhang, Jingyu Chen, Yufan Liu, Yongqiang Zhu, Nai Ding, Lai Jiang, Congyan Lang, Bing Li, Weiming Hu
arXiv:2607. 08046v1 Announce Type: cross Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast.
By Rapha\"el Sarfati, Pratyush Ranjan Tiwari, Siddharth Boppana, Christopher J. Earls, Srikar Varadaraj, Eric Ho
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
By Yash Aggarwal, Atmika Gorti, Vinija Jain, Aman Chadha, Krishnaprasad Thirunarayan, Manas Gaur
arXiv:2607. 18310v1 Announce Type: cross Abstract: Synthetic-population tools increasingly run every individual as an independent large language model (LLM) agent.
By Gurkan Ozkan
The paper argues that probe scores lack intrinsic meaning and should be interpreted relative to two reference points: a floor (what simple inputs predict) and a ceiling (what the full input predicts). The difference, called headroom, indicates the range where a probe can reveal that a model computes beyond what the input already provides. Experiments on transformers and real models show that headroom can vanish when the target no longer depends on hidden variables or when the input no longer reveals them, and that some previously claimed representations are largely explained by the input text alone.
By Pranjal Garg
arXiv:2601.07239v2 Announce Type: replace
Abstract: Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As l...
By Tanmay Joshi, Shourya Aggarwal, Anusa Saha, Aadi Pandey, Shreyash Dhoot, Vighnesh Rai, Raxit Goswami, Aman Chadha, Vinija Jain, Amitava Das
arXiv:2606. 24162v1 Announce Type: cross Abstract: Foundation models have been increasingly applied to behavioral science domains such as psychology, sociology, and economics.
By Jin Huang, Yutong Xie, Wanli Song, Xingjian Zhang, Walter Yuan, Matthew O. Jackson, Qiaozhu Mei
arXiv:2604. 16197v2 Announce Type: replace Abstract: Data attribution and valuation are critical for understanding data-model synergy for Large Language Models (LLMs), yet existing gradient-based methods suffer from scalability challenges on LLMs.
By Yide Ran, Jianwen Xie, Minghui Wang, Wenjin Zheng, Denghui Zhang, Chuan Li, Zhaozhuo Xu
arXiv:2608. 05224v1 Announce Type: new Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions.
By Nick Oh, Fernand Gobet
arXiv:2606. 07552v1 Announce Type: cross Abstract: Large language models exhibit innate behavioral tendencies when deployed as strategic agents -- notably a risk-averse "turtle" bias toward defensive play.
By Augustin Chan
arXiv:2609.38448v1 Announce Type: new
Abstract: Open-ended LLM homogeneity can create false plurality when several systems appear to offer independent perspectives while returning the same familiar d...
By Ben Wigler, Maria Tsfasman
arXiv:2509. 05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior?
By Jason Starace, Terence Soule