There is a growing interest in integrating Large Language Models (LLMs) with autonomous driving (AD) systems. However, AD systems are vulnerable to attacks against their object detection and tracking (ODT) functions. Unfortunately, our evaluation of four recent LLM agents against ODT attacks shows that the attacks are 63.26% successful in causing them to crash or violate traffic rules due to (1) misleading memory modules that provide past experiences for decision making, (2) limitations of prompts in identifying inconsistencies, and (3) reliance on ground truth perception data. In this paper, we introduce Hudson, a driving reasoning agent that extends prior LLM-based driving systems to enable safer decision making during perception attacks while maintaining effectiveness under benign conditions. Hudson achieves this by first instrumenting the AD software to collect real-time perception results and contextual information from the driving scene. This data is then formalized into a domain-specific language (DSL). To guide the LLM in detecting and making safe control decisions during ODT attacks, Hudson translates the DSL into natural language, along with a list of custom attack detection instructions. Following query execution, Hudson analyzes the LLM's control decision to understand its causal reasoning process. We evaluate the effectiveness of Hudson using a proprietary LLM (GPT-4) and two open-source LLMs (Llama and Gemma) in various adversarial driving scenarios. GPT-4, Llama, and Gemma achieve, on average, an attack detection accuracy of 83. 3%, 63. 6%, and 73. 6%. Consequently, they make safe control decisions in 86.4%, 73.9%, and 80% of the attacks. Our results, following the growing interest in integrating LLMs into AD systems, highlight the strengths of LLMs and their potential to detect and mitigate ODT attacks.

Background: Large language models (LLMs) have seen extraordinary advances with applications in clinical decision support. However, high-quality evidence is urgently needed on the potential and limitation of LLMs in providing accurate clinical decisions based on real-world medical data. Objective: To evaluate quantitatively whether universal state-of-the-art LLMs (ChatGPT and GPT-4) can predict the incidence risk of myocardial infarction (MI) with logical inference, and to further make comparison between various models to assess the performance of LLMs comprehensively. Methods: In this retrospective cohort study, 482,310 participants recruited from 2006 to 2010 were initially included in UK Biobank database and later on resampled into a final cohort of 690 participants. For each participant, tabular data of the risk factors of MI were transformed into standardized textual descriptions for ChatGPT recognition. Responses were generated by asking ChatGPT to select a score ranging from 0 to 10 representing the risk. Chain of Thought (CoT) questioning was used to evaluate whether LLMs make prediction logically. The predictive performance of ChatGPT was compared with published medical indices, traditional machine learning models and other large language models. Conclusions: Current LLMs are not ready to be applied in clinical medicine fields. Future medical LLMs are suggested to be expert in medical domain knowledge to understand both natural languages and quantified medical data, and further make logical inferences.

Semantic Parsing aims to capture the meaning of a sentence and convert it into a logical, structured form. Previous studies show that semantic parsing enhances the performance of smaller models (e.g., BERT) on downstream tasks. However, it remains unclear whether the improvements extend similarly to LLMs. In this paper, our empirical findings reveal that, unlike smaller models, directly adding semantic parsing results into LLMs reduces their performance. To overcome this, we propose SENSE, a novel prompting approach that embeds semantic hints within the prompt. Experiments show that SENSE consistently improves LLMs' performance across various tasks, highlighting the potential of integrating semantic information to improve LLM capabilities.

Automatic detection of online hate speech serves as a crucial step in the detoxification of the online discourse. Moreover, accurate classification can promote a better understanding of the proliferation of hate as a social phenomenon. While most prior work focus on the detection of hateful utterances, we argue that focusing on the user level is as important, albeit challenging. In this paper we consider a multimodal aggregative approach for the detection of hate-mongers, taking into account the potentially hateful texts, user activity, and the user network. We evaluate our methods on three unique datasets X (Twitter), Gab, and Parler showing that a processing a user's texts in her social context significantly improves the detection of hate mongers, compared to previously used text and graph-based methods. Our method can be then used to improve the classification of coded messages, dog-whistling, and racial gas-lighting, as well as inform intervention measures. Moreover, our approach is highly efficient even for very large datasets and networks.

Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probing methods to a multilingual context, investigating the behaviors of LLMs across diverse languages. We conduct experiments on several open-source LLM models, analyzing probing accuracy, trends across layers, and similarities between probing vectors for multiple languages. Our key findings reveal: (1) a consistent performance gap between high-resource and low-resource languages, with high-resource languages achieving significantly higher probing accuracy; (2) divergent layer-wise accuracy trends, where high-resource languages show substantial improvement in deeper layers similar to English; and (3) higher representational similarities among high-resource languages, with low-resource languages demonstrating lower similarities both among themselves and with high-resource languages. These results highlight significant disparities in LLMs' multilingual capabilities and emphasize the need for improved modeling of low-resource languages.

The process of landscaping automotive innovation through patent analysis is crucial for Research and Development teams. It aids in comprehending innovation trends, technological advancements, and the latest technologies from competitors. Traditionally, this process required intensive manual efforts. However, with the advent of Large Language Models (LLMs), it can now be automated, leading to faster and more efficient patent categorization & state-of-the-art of inventive concept extraction. This automation can assist various R\&D teams in extracting relevant information from extensive patent databases. This paper introduces a method based on prompt engineering to extract essential information for landscaping. The information includes the problem addressed by the patent, the technology utilized, and the area of innovation within the vehicle ecosystem (such as safety, Advanced Driver Assistance Systems and more).The result demonstrates the implementation of this method to create a landscape of fuel cell technology using open-source patent data. This approach provides a comprehensive overview of the current state of fuel cell technology, offering valuable insights for future research and development in this field.

We investigate Large Language Models' (LLMs) ability to predict a user's stance on a target given a collection of his/her target-agnostic social media posts (i.e., user-level stance prediction). While we show early evidence that LLMs are capable of this task, we highlight considerable variability in the performance of the model across (i) the type of stance target, (ii) the prediction strategy and (iii) the number of target-agnostic posts supplied. Post-hoc analyses further hint at the usefulness of target-agnostic posts in providing relevant information to LLMs through the presence of both surface-level (e.g., target-relevant keywords) and user-level features (e.g., encoding users' moral values). Overall, our findings suggest that LLMs might offer a viable method for determining public stances towards new topics based on historical and target-agnostic data. At the same time, we also call for further research to better understand LLMs' strong performance on the stance prediction task and how their effectiveness varies across task contexts.

Large language models (LLMs) have gained increasing attention due to their prominent ability to understand and process texts. Nevertheless, LLMs largely remain opaque. The lack of understanding of LLMs has obstructed the deployment in safety-critical scenarios and hindered the development of better models. In this study, we advance the understanding of LLM by investigating the significance of individual layers in LLMs. We propose an efficient sampling method to faithfully evaluate the importance of layers using Shapley values, a widely used explanation framework in feature attribution and data valuation. In addition, we conduct layer ablation experiments to assess the performance degradation resulting from the exclusion of specific layers. Our findings reveal the existence of cornerstone layers, wherein certain early layers can exhibit a dominant contribution over others. Removing one cornerstone layer leads to a drastic collapse of the model performance, often reducing it to random guessing. Conversely, removing non-cornerstone layers results in only marginal performance changes. This study identifies cornerstone layers in LLMs and underscores their critical role for future research.

Generative AI agents are often expected to respond to complex user requests that have No One Right Answer (NORA), e.g., "design a vegetarian meal plan below 1800 calories". Such requests may entail a set of constraints that the agent should adhere to. To successfully develop agents for NORA scenarios, an accurate automatic evaluation framework is essential, and specifically - one capable of validating the satisfaction of constraints in the agent's response. Recently, large language models (LLMs) have been adopted as versatile evaluators for many NORA tasks, but their ability to evaluate constraint-satisfaction in generated text remains unclear. To study this, we develop and release a novel Arithmetic Constraint-Satisfaction (ACS) benchmarking dataset. The dataset consists of complex user requests with corresponding constraints, agent responses and human labels indicating each constraint's satisfaction level in the response. A unique property of this dataset is that validating many of its constraints requires reviewing the response as a whole (in contrast to many other benchmarks that require the validation of a single independent item). Moreover, it assesses LLMs in performing reasoning, in-context data extraction, arithmetic calculations, and counting. We then benchmark both open and proprietary LLMs on evaluating constraint-satisfaction, and show that most models still have a significant headroom for improvement, and that errors primarily stem from reasoning issues. In addition, most models exhibit a skewed constraint-satisfaction prediction pattern, with higher accuracy where the ground-truth label is "satisfied". Lastly, few-shot prompting for our task proved to be rather challenging, since many of the studied models showed a degradation in performance when it was introduced.

Large Language Models (LLMs) show promise in generating code comments for novice programmers, but their educational effectiveness remains under-evaluated. This study assesses the instructional quality of code comments produced by GPT-4, GPT-3.5-Turbo, and Llama2, compared to expert-developed comments, focusing on their suitability for novices. Analyzing a dataset of ``easy'' level Java solutions from LeetCode, we find that GPT-4 exhibits comparable quality to expert comments in aspects critical for beginners, such as clarity, beginner-friendliness, concept elucidation, and step-by-step guidance. GPT-4 outperforms Llama2 in discussing complexity (chi-square = 11.40, p = 0.001) and is perceived as significantly more supportive for beginners than GPT-3.5 and Llama2 with Mann-Whitney U-statistics = 300.5 and 322.5, p = 0.0017 and 0.0003). This study highlights the potential of LLMs for generating code comments tailored to novice programmers.