arXiv:2511.22619v2 Announce Type: replace Abstract: As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an empirically demonstrated risk across language models, AI agents, and emerging frontier systems. This project provides a comprehensive and up-to-date overview of the AI deception field, covering its core concepts, methodologies, genesis, and potential mitigations. First, we identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception. We then review existing empirical studies and associated risks, highlighting deception as a sociotechnical safety challenge. We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment. Deception emergence reveals the mechanisms underlying AI deception: systems with sufficient capability and incentive potential inevitably engage in deceptive behaviors when triggered by external conditions. Deception treatment, in turn, focuses on detecting and addressing such behaviors. On deception emergence, we analyze incentive foundations across three hierarchical levels and identify three essential capability preconditions required for deception. We further examine contextual triggers, including supervision gaps, distributional shifts, and environmental pressures. On deception treatment, we conclude detection methods covering benchmarks and evaluation protocols in static and interactive settings. Building on the three core factors of deception emergence, we outline potential mitigation strategies and propose auditing approaches that integrate technical, community, and governance efforts to address sociotechnical challenges and future AI risks. To support ongoing work in this area, we release a living resource at www.deceptionsurvey.com.

Oncogenesis, Published online: 21 November 2025; doi:10.1038/s41389-025-00587-w

RNA m5C methylation in cancer: mechanisms and biological impact

arXiv:2510.24528v1 Announce Type: new Abstract: The capability of in-context learning (ICL) enables large language models (LLMs) to perform novel tasks without parameter updates by conditioning on a few input-output examples. However, collecting high-quality examples for new or challenging tasks can be costly and labor-intensive. In this work, we propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling. Our approach first leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances. We then introduce a graph-based label propagation method that spreads label information to the remaining target examples without additional LLM queries. The resulting fully pseudo-labeled dataset is used to construct in-task demonstrations for ICL. This pipeline combines the flexibility of cross-task supervision with the scalability of LLM-free propagation. Experiments across five tasks demonstrate that our method achieves strong performance while lowering labeling costs.

Cell Death Discovery, Published online: 23 April 2024; doi:10.1038/s41420-024-01948-x

OTUB1/NDUFS2 axis promotes pancreatic tumorigenesis through protecting against mitochondrial cell death

Congenital heart disease (CHD) is a prevalent congenital cardiac malformation, which lacks effective early biological diagnosis and intervention. MicroRNAs, as epigenetic regulators of cardiac development, pro...

Nature Biotechnology, Published online: 02 January 2024; doi:10.1038/s41587-023-01985-4

MASST+ speeds up querying of metabolomics mass spectrometry data by two orders of magnitude.

Nature Biotechnology, Published online: 06 February 2023; doi:10.1038/s41587-022-01652-0

A six-letter sequencing workflow can simultaneously detect genetic and epigenetic bases.

Nature, Published online: 30 November 2022; doi:10.1038/s41586-022-05448-9

Exome sequence data from 628,388 individuals was used to identify 24 risk loci in 40,208 carriers of clonal haematopoiesis of indeterminate potential and link them to other conditions including COVID-19, cardiovascular disease and cancer.