The rise of influencer marketing has blurred boundaries between organic content and sponsored content, making the enforcement of legal rules relating to transparency challenging. Effective regulation requires applying legal knowledge with a clear purpose and reason, yet current detection methods of undisclosed sponsored content generally lack legal grounding or operate as opaque "black boxes". Using 1,143 Instagram posts, we compare gpt-5-nano and gemini-2.5-flash-lite under three prompting strategies with controlled levels of legal knowledge provided. Both models perform strongly in classifying content as sponsored or not (F1 up to 0.93), though performance drops by over 10 points on ambiguous cases. We further develop a taxonomy of reasoning errors, showing frequent citation omissions (28.57%), unclear references (20.71%), and hidden ads exhibiting the highest miscue rate (28.57%). While adding regulatory text to the prompt improves explanation quality, it does not consistently improve detection accuracy. The contribution of this paper is threefold. First, it makes a novel addition to regulatory compliance technology by providing a taxonomy of common errors in LLM-generated legal reasoning to evaluate whether automated moderation is not only accurate but also legally robust, thereby advancing the transparent detection of influencer marketing content. Second, it features an original dataset of LLM explanations annotated by two students who were trained in influencer marketing law. Third, it combines quantitative and qualitative evaluation strategies for LLM explanations and critically reflects on how these findings can support advertising regulatory bodies in automating moderation processes on a solid legal foundation.

We investigate the degree to which human plausibility judgments of multiple-choice commonsense benchmark answers are subject to influence by (im)plausibility arguments for or against an answer, in particular, using rationales generated by LLMs. We collect 3,000 plausibility judgments from humans and another 13,600 judgments from LLMs. Overall, we observe increases and decreases in mean human plausibility ratings in the presence of LLM-generated PRO and CON rationales, respectively, suggesting that, on the whole, human judges find these rationales convincing. Experiments with LLMs reveal similar patterns of influence. Our findings demonstrate a novel use of LLMs for studying aspects of human cognition, while also raising practical concerns that, even in domains where humans are ``experts'' (i.e., common sense), LLMs have the potential to exert considerable influence on people's beliefs.

Ranking online reviews by their intrinsic quality is a critical task for e-commerce platforms and information services, impacting user experience and business outcomes. However, quality is a domain-dependent and dynamic concept, making its assessment a formidable challenge. Traditional methods relying on hand-crafted features are unscalable across domains and fail to adapt to evolving content patterns, while modern deep learning approaches often produce black-box models that lack interpretability and may prioritize semantics over quality. To address these challenges, we propose AutoQual, an LLM-based agent framework that automates the discovery of interpretable features. While demonstrated on review quality assessment, AutoQual is designed as a general framework for transforming tacit knowledge embedded in data into explicit, computable features. It mimics a human research process, iteratively generating feature hypotheses through reflection, operationalizing them via autonomous tool implementation, and accumulating experience in a persistent memory. We deploy our method on a large-scale online platform with a billion-level user base. Large-scale A/B testing confirms its effectiveness, increasing average reviews viewed per user by 0.79% and the conversion rate of review readers by 0.27%.

Large Language Model (LLM) inference in production must meet stringent service-level objectives for both time-to-first-token (TTFT) and time-between-token (TBT) while maximizing throughput under fixed compute, memory, and interconnect budgets. Modern serving systems adopt stall-free scheduling techniques such as chunked prefill, which splits long prompt processing along the token dimension and interleaves prefill with ongoing decode iterations. While effective at stabilizing TBT, chunked prefill incurs substantial overhead in Mixture-of-Experts (MoE) models: redundant expert weight loads increase memory traffic by up to 39% and inflate energy consumption. We propose layered prefill, a new scheduling paradigm that treats transformer layer groups as the primary scheduling unit. By vertically partitioning the model into contiguous layer groups and interleaving prefill and decode across the groups, layered prefill sustains stall-free decoding while eliminating chunk-induced MoE weight reloads. It reduces off-chip bandwidth demand, lowering TTFT by up to 70%, End-to-End latency by 41% and per-token energy by up to 22%. Evaluations show that layered prefill consistently improves the TTFT--TBT Pareto frontier over chunked prefill, reducing expert-load traffic and energy cost while maintaining stall-free decoding. Overall, shifting the scheduling axis from tokens to layers unlocks a new operating regime for high-efficiency, energy-aware LLM serving in co-located environments.

This layer contains the information of the background adversarial vehicles whose behaviors are not directly guided by LinguaSim. These vehicles are automatically generated and placed around the ego vehicle and the guided adversarial vehicles by LLM agent Chaos Maker, and roam aimlessly on the given map. The background vehicles significantly increase the uncertainty and complexity of the generated scenarios. B. Adversarial Behavior Generation Compared to other state-of-the-art methods for generating 3D realistic scenarios from natural language descriptions, LinguaSim achieves a higher level of realism, flexibility, and interactivity due to the innovative structure of its Action Generator agent. The detailed workflow of this component will be elaborated further in this section, with a simplified operational logic of the Action Generator illustrated in Figure 1. Figure 1: The basic workflow of module Action Generator To establish a solid foundation for the Action Generator, a retrieval database was constructed to store various behaviors available for the guided adversarial vehicles. Each behavior in the database is referred to as an Atomic Behavior, serving as a fundamental component in the subsequent process. As illustrated in Figure 1, each Atomic Behavior comprises three essential parts: 1) Agent Selection: An autonomous driving agent is selected to guide the adversarial vehicle to which Figure 1: An example of the Behavior T opology W eb generated by the Action Generator the Atomic Behavior is applied. LinguaSim includes various predefined agents, such as the basic CARLA built-in agent that follows a given route, an auto cruise control (ACC) agent that follows the vehicle in front, or the PlanT agent, an imitation-learning-based planning algorithm developed by Renz, Chitta et al. [10]. These agents serve different purposes; for example, the F ollow V ehicle behavior uses the ACC agent, while the PlanT agent is often used for less aggressive behaviors to mimic cautious drivers.

Large language models (LLMs) demonstrate advanced reasoning abilities, enabling robots to understand natural language instructions and generate high-level plans with appropriate grounding. However, LLM hallucinations present a significant challenge, often leading to overconfident yet potentially misaligned or unsafe plans. While researchers have explored uncertainty estimation to improve the reliability of LLM-based planning, existing studies have not sufficiently differentiated between epistemic and intrinsic uncertainty, limiting the effectiveness of uncertainty estimation. In this paper, we present Combined Uncertainty estimation for Reliable Embodied planning (CURE), which decomposes the uncertainty into epistemic and intrinsic uncertainty, each estimated separately. Furthermore, epistemic uncertainty is subdivided into task clarity and task familiarity for more accurate evaluation. The overall uncertainty assessments are obtained using random network distillation and multi-layer perceptron regression heads driven by LLM features. We validated our approach in two distinct experimental settings: kitchen manipulation and tabletop rearrangement experiments. The results show that, compared to existing methods, our approach yields uncertainty estimates that are more closely aligned with the actual execution outcomes.

Large language models (LLMs) are increasingly deployed for climate-related applications, where understanding internal climatological knowledge is crucial for reliability and misinformation risk assessment. Despite growing adoption, the capacity of LLMs to recall climate normals from parametric knowledge remains largely uncharacterized. We investigate the capacity of contemporary LLMs to recall climate normals without external retrieval, focusing on a prototypical query: mean July 2-m air temperature 1991-2020 at specified locations. We construct a global grid of queries at 1° resolution land points, providing coordinates and location descriptors, and validate responses against ERA5 reanalysis. Results show that LLMs encode non-trivial climate structure, capturing latitudinal and topographic patterns, with root-mean-square errors of 3-6 °C and biases of $\pm$1 °C. However, spatially coherent errors remain, particularly in mountains and high latitudes. Performance degrades sharply above 1500 m, where RMSE reaches 5-13 °C compared to 2-4 °C at lower elevations. We find that including geographic context (country, city, region) reduces errors by 27% on average, with larger models being most sensitive to location descriptors. While models capture the global mean magnitude of observed warming between 1950-1974 and 2000-2024, they fail to reproduce spatial patterns of temperature change, which directly relate to assessing climate change. This limitation highlights that while LLMs may capture present-day climate distributions, they struggle to represent the regional and local expression of long-term shifts in temperature essential for understanding climate dynamics. Our evaluation framework provides a reproducible benchmark for quantifying parametric climate knowledge in LLMs and complements existing climate communication assessments.

This study investigates ChatGPT for Japanese-English translation, exploring simple and enhanced prompts and comparing against commercially available translation engines. Performing both automatic and MQM-based human evaluations, we found that document-level translation outperforms sentence-level translation for ChatGPT. On the other hand, we were not able to determine if enhanced prompts performed better than simple prompts in our experiments. We also discovered that ChatGPT-3.5 was preferred by automatic evaluation, but a tradeoff exists between accuracy (ChatGPT-3.5) and fluency (ChatGPT-4). Lastly, ChatGPT yields competitive results against two widely-known translation systems.

Parameter-efficient finetuning (PEFT) aims to mitigate the substantial computational and memory overhead involved in adapting large-scale pretrained models to diverse downstream tasks. Among numerous PEFT strategies, Low-Rank Adaptation (LoRA) has emerged as one of the most widely adopted approaches due to its robust empirical performance and low implementation complexity. In practical deployment, LoRA is typically applied to the $W^Q$ and $W^V$ projection matrices of self-attention modules, enabling an effective trade-off between model performance and parameter efficiency. While LoRA has achieved considerable empirical success, it still encounters challenges such as suboptimal performance and slow convergence. To address these limitations, we introduce \textbf{AILoRA}, a novel parameter-efficient method that incorporates function-aware asymmetric low-rank priors. Our empirical analysis reveals that the projection matrices $W^Q$ and $W^V$ in the self-attention mechanism exhibit distinct parameter characteristics, stemming from their functional differences. Specifically, $W^Q$ captures task-specific semantic space knowledge essential for attention distributions computation, making its parameters highly sensitive to downstream task variations. In contrast, $W^V$ encodes token-level feature representations that tend to remain stable across tasks and layers. Leveraging these insights, AILoRA performs a function-aware initialization by injecting the principal components of $W^Q$ to retain task-adaptive capacity, and the minor components of $W^V$ to preserve generalizable feature representations. This asymmetric initialization strategy enables LoRA modules to better capture the specialized roles of attention parameters, thereby enhancing both finetuning performance and convergence efficiency.

Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input-output behavior allows the two models to be connected by a low-loss linear path. When such a path exists, the models are said to achieve linear mode connectivity (LMC). Prior studies, including Ainsworth et al., have reported that achieving LMC requires not only an appropriate permutation search but also sufficiently wide models (e.g., a 32 $\times$ width multiplier for ResNet-20). This is broadly believed to be because increasing the model width ensures a large enough space of candidate permutations, increasing the chance of finding one that yields LMC. In this work, we empirically demonstrate that, even without any permutations, simply widening the models is sufficient for achieving LMC when using a suitable softmax temperature calibration. We further explain why this phenomenon arises by analyzing intermediate layer outputs. Specifically, we introduce layerwise exponentially weighted connectivity (LEWC), which states that the output of each layer of the merged model can be represented as an exponentially weighted sum of the outputs of the corresponding layers of the original models. Consequently the merged model's output matches that of an ensemble of the original models, which facilitates LMC. To the best of our knowledge, this work is the first to show that widening the model not only facilitates nonlinear mode connectivity, as suggested in prior research, but also significantly increases the possibility of achieving linear mode connectivity.