
Reviewers increasingly use LLM-based tools to evaluate manuscripts without disclosure, risking degraded rigor and privacy violations. This commentary argues LLM use in peer review needs professionalism and ethical guardrails, and proposed paths toward transparent, responsible adoption. The peer review system is straining under rising submissions, growing manuscript complexity, and a shrinking reviewer pool. Meanwhile an increasing number of researchers now use tools based on large language models (LLMs) when performing peer review, often without disclosure and against journal policies. This erodes trust in peer review and risks deteriorating the quality and integrity of research publications. We argue for professionalization and transparency rather than prohibition, and propose guidelines built on three aspects: model selection and data protection, human guidance and accountability, and publication integrity. These principles offer a sustainable path forward, leaving scientific judgment where it belongs; that is, with human experts.
Traumatic peripheral nerve injuries (PNIs) are high-stakes presentations in the emergency department (ED). Missed deficits and delayed referral can lead to functional loss and chronic neuropathic pain. This review summarizes an ED-centered approach to evaluation, early risk stratification, and management pathways. Contemporary epidemiology suggests PNIs after extremity trauma occur at clinically meaningful rates. High-resolution ultrasound and neuromuscular ultrasound can visualize nerve continuity, focal enlargement, traumatic neuroma, and entrapment, though performance depends on operator skill and nerve depth. Magnetic resonance neurography complements ultrasound for deeper nerves, plexus-level injury, and muscle denervation patterns. Electrodiagnostic testing remains central for localization and prognosis but is usually most informative in the subacute period. ED care should integrate mechanism-based suspicion, nerve-specific examination with repeat post-reduction reassessment, selective imaging when it changes decisions, timely surgical consultation for suspected transection/entrapment/progression, and clear documentation with structured follow-up. We recommend an emergency department approach to traumatic peripheral nerve injury that prioritizes early recognition, identification of time-sensitive lesions, and a closed-loop follow-up plan when observation is appropriate. Every at-risk extremity trauma should receive a nerve-specific motor and sensory exam documented before and after reduction, splinting, or casting, because evolving deficits can reflect entrapment, hematoma expansion, ischemia, or compartment syndrome. When mechanism and exam raise concern for high-grade injury, particularly sharp lacerations with motor loss, open fractures with neurologic deficit, progressive weakness after immobilization, or deficits out of proportion to pain, urgent surgical consultation is warranted. High-resolution ultrasound adds the most value when it answers a focused question that changes acute decisions, specifically whether the nerve is in continuity, whether there is focal compression by hematoma or displaced fragments, and whether post-reduction positioning is producing dynamic impingement. In stable closed injuries with preserved continuity and no red flags, we favor functional splinting, multimodal analgesia, and early specialty follow-up with a planned timeline for electrodiagnostic testing in the subacute period to localize injury and guide prognosis. For suspected deep nerve or plexus involvement, equivocal ultrasound, or complex regional injury patterns, magnetic resonance neurography can complement ultrasound by defining lesion extent and demonstrating denervation patterns that influence urgency. Overall, ED success depends less on assigning a perfect injury grade at presentation and more on reliably detecting injuries unlikely to recover spontaneously, reassessing after interventions, and ensuring timely definitive nerve evaluation.
Developing a qualified eco-driving strategy for plug-in hybrid electric vehicles (PHEVs) remains challenging in urban traffic scenarios, due to the comprehensive influence of random traffic flow and signal lights. To solve it, this study develops a hierarchical eco-driving framework integrating lane-changing decisions through a virtual force-based trigger mechanism and an adaptive energy management strategy that dynamically adjusts the equivalence factor. Firstly, considering the interference of neighbor vehicles, the velocity planning layer generates the economic velocity trajectories using dynamic programming in short discrete intervals, enabling the ego-vehicle to navigate through signal intersections smoothly. In addition, the lane changing is properly conducted according to the state of the ego-vehicle, traffic flow, and signal light. In the energy management layer, an adaptive equivalent fuel consumption minimization strategy accounting for trip distance, initial state of charge, and remaining electric mileage is developed to ensure a reasonable power split based on the reference velocity. Simulation and hardware-in-the-loop experimental results indicate that the developed strategy improves the traffic efficiency by 1.68%, while reducing energy consumption by 9.81% and 31.71%, compared with Pontryagin's minimum principle and nonlinear model predictive control based methods.
End-to-end vision-based imitation learning has demonstrated promising results in autonomous driving by learning control commands directly from expert demonstrations. However, traditional approaches rely on either regressionbased models, which provide precise control but lack confidence estimation, or classification-based models, which offer confidence scores but suffer from reduced precision due to discretization. This limitation makes it challenging to quantify the reliability of predicted actions and apply corrections when necessary. In this work, we introduce a dual-head neural network architecture that integrates both regression and classification heads to improve decision reliability in imitation learning. The regression head predicts continuous driving actions, while the classification head estimates confidence, enabling a correction mechanism that adjusts actions in low-confidence scenarios, enhancing driving stability. We evaluate our approach in a closed-loop setting within the CARLA simulator, demonstrating its ability to detect uncertain actions, estimate confidence, and apply real-time corrections. Experimental results show that our method reduces lane deviation and improves trajectory accuracy by up to 50 findings highlight the potential of classification-guided confidence estimation in enhancing the robustness of vision-based imitation learning for autonomous driving. The source code is available at https://github.com/ElaheDlv/Confidence_Aware_IL.
Safety specifications in cyber-physical systems (CPS) capture the operational conditions the system must satisfy to operate safely within its intended environment. As operating environments evolve, operational rules must be continuously refined to preserve consistency with observed system behavior during simulation-based verification and validation. Revising inconsistent rules is challenging because the changes must remain syntactically correct under a domain-specific grammar. Language-in-the-loop refinement further raises safety concerns beyond syntactic violations, as it can produce semantically unjustified refinements that overfit to the observed outcomes. We introduce a framework that combines counterfactual reasoning with a grammar-constrained refinement loop to refine operational rules, aligning them with the observed system behavior. Applied to an autonomous driving control system, our approach successfully resolved the inconsistencies in an operational rule inferred by a conventional baseline while remaining grammar compliant. An empirical large language model (LLM) study further revealed model-dependent refinement quality and safety lessons, which motivate rigorous grammar enforcement, stronger semantic validation, and broader evaluation in future work.