Large Language Models (LLMs) with strong abilities in natural language processing tasks have emerged and have been applied in various kinds of areas such as science, finance and software engineering.

Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in capabilities, capturing the interest of practitioners and the public alike. Yet, while the literature on the trustworthiness of GPT models remains limited, practitioners have proposed employing capable GPT models for sensitive applications to healthcare and finance - where mistakes can be costly. To this end, this work proposes a comprehensive trustworthiness evaluation for large language models with a focus on GPT-4 and GPT-3.5, considering diverse perspectives - including toxicity, stereotype bias, adversarial robustness, out-of-distribution robustness, robustness on adversarial demonstrations, privacy, machine ethics, and fairness. Based on our evaluations, we discover previously unpublished vulnerabilities to trustworthiness threats. For instance, we find that GPT models can be easily misled to generate toxic and biased outputs and leak private information in both training data and conversation history. We also find that although GPT-4 is usually more trustworthy than GPT-3.5 on standard benchmarks, GPT-4 is more vulnerable given jailbreaking system or user prompts, potentially due to the reason that GPT-4 follows the (misleading) instructions more precisely. Our work illustrates a comprehensive trustworthiness evaluation of GPT models and sheds light on the trustworthiness gaps. Our benchmark is publicly available at https://decodingtrust.github.io/.

Our study presents a multifaceted approach to enhancing user interaction and content relevance in social media platforms through a federated learning framework. We introduce personalized LLM Federated Learning and Context-based Social Media models. In our framework, multiple client entities receive a foundational GPT model, which is fine-tuned using locally collected social media data while ensuring data privacy through federated aggregation. Key modules focus on categorizing user-generated content, computing user persona scores, and identifying relevant posts from friends networks. By integrating a sophisticated social engagement quantification method with matrix factorization techniques, our system delivers real-time personalized content suggestions tailored to individual preferences. Furthermore, an adaptive feedback loop, alongside a robust readability scoring algorithm, significantly enhances the quality and relevance of the content presented to users. This comprehensive solution not only addresses the challenges of content filtering and recommendation but also fosters a more engaging social media experience while safeguarding user privacy, setting a new standard for personalized interactions in digital platforms.

Jet tagging is a central task in collider physics. Over the past decade, machine learning has driven major advances in jet tagging, with increasingly sophisticated architectures achieving very high classification performance on simulated datasets [1-11]. This success naturally raises a key question: have current jet taggers already reached the fundamental limit of jet tagging, or does a gap remain between practical performance and the true statistical optimum? The Neyman-Pearson (NP) limit, defined by the likelihood ratio, is the best possible discriminant between two different underlying physics processes - such as top and QCD jets - that any classifier could achieve if it had access to the exact data likelihoods [12]. In practice, however, this limit cannot be evaluated directly because the true likelihood of the data-generating process is unknown. It therefore remains unclear how close existing classifiers are to this ultimate bound. Recently, Ref. [13] proposed using autoregressive GPT-style generative models to probe this limit for top vs. QCD jets from the JetClass dataset [14]. These models operate on discretized, tokenized representations of jet constituents and yield explicit log-likelihoods, enabling the computation of likelihood ratios between jet classes.

Large Language Models (LLMs) with strong abilities in natural language processing tasks have emerged and have been applied in various kinds of areas such as science, finance and software engineering.

Scaling up the deployment of autonomous excavators is of great economic and societal importance. Yet it remains a challenging problem, as effective systems must robustly handle unseen worksite conditions and new hardware configurations. Current state-of-the-art approaches rely on highly engineered, task-specific controllers, which require extensive manual tuning for each new scenario. In contrast, recent advances in large-scale pretrained models have shown remarkable adaptability across tasks and embodiments in domains such as manipulation and navigation, but their applicability to heavy construction machinery remains largely unexplored. In this work, we introduce ExT, a unified open-source framework for large-scale demonstration collection, pretraining, and fine-tuning of multitask excavation policies. ExT policies are first trained on large-scale demonstrations collected from a mix of experts, then fine-tuned either with supervised fine-tuning (SFT) or reinforcement learning fine-tuning (RLFT) to specialize to new tasks or operating conditions. Through both simulation and real-world experiments, we show that pretrained ExT policies can execute complete excavation cycles with centimeter-level accuracy, successfully transferring from simulation to real machine with performance comparable to specialized single-task controllers. Furthermore, in simulation, we demonstrate that ExT's fine-tuning pipelines allow rapid adaptation to new tasks, out-of-distribution conditions, and machine configurations, while maintaining strong performance on previously learned tasks. These results highlight the potential of ExT to serve as a foundation for scalable and generalizable autonomous excavation.

As AI systems increasingly evaluate other AI outputs, understanding their assessment behavior becomes crucial for preventing cascading biases. This study analyzes vision-language descriptions generated by NVIDIA's Describe Anything Model and evaluated by three GPT variants (GPT-4o, GPT-4o-mini, GPT-5) to uncover distinct "evaluation personalities" the underlying assessment strategies and biases each model demonstrates. GPT-4o-mini exhibits systematic consistency with minimal variance, GPT-4o excels at error detection, while GPT-5 shows extreme conservatism with high variability. Controlled experiments using Gemini 2.5 Pro as an independent question generator validate that these personalities are inherent model properties rather than artifacts. Cross-family analysis through semantic similarity of generated questions reveals significant divergence: GPT models cluster together with high similarity while Gemini exhibits markedly different evaluation strategies. All GPT models demonstrate a consistent 2:1 bias favoring negative assessment over positive confirmation, though this pattern appears family-specific rather than universal across AI architectures. These findings suggest that evaluation competence does not scale with general capability and that robust AI assessment requires diverse architectural perspectives.

This study leverages GPT-4o to assess neighbourhood housing quality using multi-source textural user-generated content (UGC) from Dianping, Weibo, and the Government Message Board. The analysis involves filtering relevant texts, extracting structured evaluation units, and conducting sentiment scoring. A refined housing quality assessment system with 46 indicators across 11 categories was developed, highlighting an objective-subjective method gap and platform-specific differences in focus. GPT-4o outperformed rule-based and BERT models, achieving 92.5% accuracy in fine-tuned settings. The findings underscore the value of integrating UGC and GPT-driven analysis for scalable, resident-centric urban assessments, offering practical insights for policymakers and urban planners.

This paper introduces a novel approach for multimodal sentiment analysis on social media, particularly in the context of natural disasters, where understanding public sentiment is crucial for effective crisis management. Unlike conventional methods that process text and image modalities separately, our approach seamlessly integrates Convolutional Neural Network (CNN) based image analysis with Large Language Model (LLM) based text processing, leveraging Generative Pre-trained Transformer (GPT) and prompt engineering to extract sentiment relevant features from the CrisisMMD dataset. To effectively model intermodal relationships, we introduce a contextual attention mechanism within the fusion process. Leveraging contextual-attention layers, this mechanism effectively captures intermodality interactions, enhancing the model's comprehension of complex relationships between textual and visual data. The deep neural network architecture of our model learns from these fused features, leading to improved accuracy compared to existing baselines. Experimental results demonstrate significant advancements in classifying social media data into informative and noninformative categories across various natural disasters. Our model achieves a notable 2.43% increase in accuracy and 5.18% in F1-score, highlighting its efficacy in processing complex multimodal data. Beyond quantitative metrics, our approach provides deeper insight into the sentiments expressed during crises. The practical implications extend to real time disaster management, where enhanced sentiment analysis can optimize the accuracy of emergency interventions. By bridging the gap between multimodal analysis, LLM powered text understanding, and disaster response, our work presents a promising direction for Artificial Intelligence (AI) driven crisis management solutions. Keywords:

Despite their recent introduction to human society, Large Language Models (LLMs) have significantly affected the way we tackle mental challenges in our everyday lives. From optimizing our linguistic communication to assisting us in making important decisions, LLMs, such as ChatGPT, are notably reducing our cognitive load by gradually taking on an increasing share of our mental activities. In the context of Learning by Demonstration (LbD), classifying and segmenting complex motions into primitive actions, such as pushing, pulling, twisting etc, is considered to be a key-step towards encoding a task. In this work, we investigate the capabilities of LLMs to undertake this task, considering a finite set of predefined primitive actions found in fruit picking operations. By utilizing LLMs instead of simple supervised learning or analytic methods, we aim at making the method easily applicable and deployable in a real-life scenario. Three different fine-tuning approaches are investigated, compared on datasets captured kinesthetically, using a UR10e robot, during a fruit-picking scenario.