Sophie Zhang

Zhiming Lin, Kai Zhao, Sophie Zhang et al.

Large-scale Chinese spelling correction (CSC) remains critical for real-world text processing, yet existing LLMs and supervised methods lack robustness to novel errors and rely on costly annotations. We introduce CEC-Zero, a zero-supervision reinforcement learning framework that addresses this by enabling LLMs to correct their own mistakes. CEC-Zero synthesizes errorful inputs from clean text, computes cluster-consensus rewards via semantic similarity and candidate agreement, and optimizes the policy with PPO. It outperforms supervised baselines by 10--13 F$_1$ points and strong LLM fine-tunes by 5--8 points across 9 benchmarks, with theoretical guarantees of unbiased rewards and convergence. CEC-Zero establishes a label-free paradigm for robust, scalable CSC, unlocking LLM potential in noisy text pipelines.

Nicholas Kruus, Madhavendra Thakur, Adam Khoja et al.

Military and economic strategic competitiveness between nation-states will increasingly be defined by the capability and cost of their frontier artificial intelligence models. Among the first areas of geopolitical advantage granted by such systems will be in automating military intelligence. Much discussion has been devoted to AI systems enabling new military modalities, such as lethal autonomous weapons, or making strategic decisions. However, the ability of a country of "CIA analysts in a data-center" to synthesize diverse data at scale, and its implications, have been underexplored. Multimodal foundation models appear on track to automate strategic analysis previously done by humans. They will be able to fuse today's abundant satellite imagery, phone-location traces, social media records, and written documents into a single queryable system. We conduct a preliminary uplift study to empirically evaluate these capabilities, then propose a taxonomy of the kinds of ground truth questions these systems will answer, present a high-level model of the determinants of this system's AI capabilities, and provide recommendations for nation-states to remain strategically competitive within the new paradigm of automated intelligence.

Sophie Zhang, Zhiming Lin

Recent advancements in large language models (LLMs) demonstrate exceptional Chinese text processing capabilities, particularly in Chinese Spelling Correction (CSC). While LLMs outperform traditional BERT-based models in accuracy and robustness, challenges persist in reliability and generalization. This paper proposes CEC-Zero, a novel reinforcement learning (RL) framework enabling LLMs to self-correct through autonomous error strategy learning without external supervision. By integrating RL with LLMs' generative power, the method eliminates dependency on annotated data or auxiliary models. Experiments reveal RL-enhanced LLMs achieve industry-viable accuracy and superior cross-domain generalization, offering a scalable solution for reliability optimization in Chinese NLP applications. This breakthrough facilitates LLM deployment in practical Chinese text correction scenarios while establishing a new paradigm for self-improving language models.

Zaina Abu Hweij, Florence Liang, Sophie Zhang

Acute compartment syndrome (ACS) is an orthopedic emergency, caused by elevated pressure within a muscle compartment, that leads to permanent tissue damage and eventually death. Diagnosis of ACS relies heavily on patient-reported symptoms, a method that is clinically unreliable and often supplemented with invasive intracompartmental pressure measurements that can malfunction in motion settings. This study proposes an objective and noninvasive diagnostic for ACS. The device detects ACS through a random forest machine learning model that uses surrogate pressure readings from force-sensitive resistors (FSRs) placed on the skin. To validate the diagnostic, a data set containing FSR measurements and the corresponding simulated intracompartmental pressure was created for motion and motionless scenarios. The diagnostic achieved up to 98% accuracy. The device excelled in key performance metrics, including sensitivity and specificity, with a statistically insignificant performance difference in motion present cases. Manufactured for 73 USD, our device may be a cost-effective solution. These results demonstrate the potential of noninvasive ACS diagnostics to meet clinical accuracy standards in real world settings.