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
The paper proposes a method for culturally aligning large language models (LLMs) using soft prompt tuning optimized via Differential Evolution (DE). Unlike traditional fine‑tuning or reinforcement learning, this approach keeps model weights frozen and requires no preference data, instead leveraging aggregated survey scores from Hofstede's Value Survey Module (VSM13). Experiments on four countries and four instruction‑tuned models show that DE‑optimized prompts reduce cultural discrepancy, improve agreement with the World Values Survey, and are preferred in blinded pairwise evaluations by LLM judges.
By Reem I. Masoud, Martin Ferianc, Philip Treleaven, Miguel Rodrigues
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
By James Elcock, William F. Shen, Xinchi Qiu, Nicholas D. Lane
arXiv:2607. 07023v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning.
By Aoxiong Zeng, Yuxin Yang, Xiangquan Yang
Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separation is incomplete: when examples are scored and kept online during fine-tuning, the choice of which data to train on already changes the model's behavioral preferences.
The paper "Stress-testing Alignment Midtraining" examines the effectiveness of alignment midtraining (AMT), a technique that continues pretraining on alignment-relevant data to improve generalisation beyond post‑training methods. Experiments on models up to 110 billion parameters and 1 billion midtraining tokens reveal that AMT can steer a model’s motivation in simple scenarios, but its effects are quickly overridden by even a tiny fraction of finetuning data with a competing motivation. The study also shows that rule-following requires demonstrations in either the midtraining or post‑training datasets to be robustly learned, leading the authors to conclude that current public evidence is insufficient to confirm that AMT resolves the core alignment challenges of powerful AI systems.
By Sid Baines, Jonathan Bostock, Maria Angelica Martinez, Andrew Draganov, David Africa, Daniel Tan
arXiv:2607. 16240v1 Announce Type: cross Abstract: Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences.
By Shawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine Metcalf
arXiv:2609.05899v1 Announce Type: cross
Abstract: Aligning large language models with human preferences remains a challenge, primarily due to the critical role of preference data quality in effective...
By Peng Lai, He Zhu, Zhiwen Ruan, Dongdong Zhang, Yun Chen, Peng Li, Furu Wei, Yang Liu, Guanhua Chen
Data-DPO is a target model‑oriented supervised fine‑tuning data selection method that uses one‑step probing of the target model to generate pairwise data preferences, trains a lightweight reward model to capture these preferences, and then selects a training subset by combining target‑model preference, external quality scores, and marginal diversity. Experiments on Vision‑Flan and LLaVA‑CoT demonstrate that Data‑DPO consistently outperforms existing data selection baselines across multiple data budgets and even surpasses full data training performance.
By Peng Sun, Yi Yang, Antong Zhang, Chunxiao Li, Yanbo Wang, Dianbo Liu, xin chen, Kai Yu, Lu Chen, Tianfan Fu
arXiv:2606. 31591v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned behaviour on unrelated prompts.
By Jason R. Brown, Patrick Leask, Lev McKinney
arXiv:2602. 07356v2 Announce Type: replace Abstract: Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands.
By Yonghui Yang, Yihui Wang, Junwei Li, Jilong Liu, Fengbin Zhu, Weibiao Huang, Le Wu, Richang Hong, Tat-Seng Chua
arXiv:2606. 19744v1 Announce Type: cross Abstract: Aligning language models with human preferences often requires optimising multiple behavioural objectives.
By Pranav Bhandari, Nicolas Fay, Amitava Datta, Usman Naseem, Mehwish Nasim