The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in the scenario of multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of different documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. For graph construction, we create a knowledge graph (KG) over multiple documents with nodes symbolizing passages or document structures (e.g., pages/tables), and edges denoting the semantic/lexical similarity between passages or intra-document structural relations. For graph traversal, we design an LLM-based graph traversal agent that navigates across nodes and gathers supporting passages assisting LLMs in MD-QA. The constructed graph serves as the global ruler that regulates the transitional space among passages and reduces retrieval latency. Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality. Extensive experiments underscore the efficacy of KGP for MD-QA, signifying the potential of leveraging graphs in enhancing the prompt design for LLMs. Our code: https://github.com/YuWVandy/KG-LLM-MDQA.

Smart contracts are prone to various vulnerabilities, leading to substantial financial losses over time. Current analysis tools mainly target vulnerabilities with fixed control or data-flow patterns, such as re-entrancy and integer overflow. However, a recent study on Web3 security bugs revealed that about 80% of these bugs cannot be audited by existing tools due to the lack of domain-specific property description and checking. Given recent advances in Large Language Models (LLMs), it is worth exploring how Generative Pre-training Transformer (GPT) could aid in detecting logicc vulnerabilities. In this paper, we propose GPTScan, the first tool combining GPT with static analysis for smart contract logic vulnerability detection. Instead of relying solely on GPT to identify vulnerabilities, which can lead to high false positives and is limited by GPT's pre-trained knowledge, we utilize GPT as a versatile code understanding tool. By breaking down each logic vulnerability type into scenarios and properties, GPTScan matches candidate vulnerabilities with GPT. To enhance accuracy, GPTScan further instructs GPT to intelligently recognize key variables and statements, which are then validated by static confirmation. Evaluation on diverse datasets with around 400 contract projects and 3K Solidity files shows that GPTScan achieves high precision (over 90%) for token contracts and acceptable precision (57.14%) for large projects like Web3Bugs. It effectively detects ground-truth logic vulnerabilities with a recall of over 70%, including 9 new vulnerabilities missed by human auditors. GPTScan is fast and cost-effective, taking an average of 14.39 seconds and 0.01 USD to scan per thousand lines of Solidity code. Moreover, static confirmation helps GPTScan reduce two-thirds of false positives.

The recent large language models (LLMs), e.g., ChatGPT, have been able to generate human-like and fluent responses when provided with specific instructions. While admitting the convenience brought by technological advancement, educators also have concerns that students might leverage LLMs to complete their writing assignments and pass them off as their original work. Although many AI content detection studies have been conducted as a result of such concerns, most of these prior studies modeled AI content detection as a classification problem, assuming that a text is either entirely human-written or entirely AI-generated. In this study, we investigated AI content detection in a rarely explored yet realistic setting where the text to be detected is collaboratively written by human and generative LLMs (i.e., hybrid text). We first formalized the detection task as identifying the transition points between human-written content and AI-generated content from a given hybrid text (boundary detection). Then we proposed a two-step approach where we (1) separated AI-generated content from human-written content during the encoder training process; and (2) calculated the distances between every two adjacent prototypes and assumed that the boundaries exist between the two adjacent prototypes that have the furthest distance from each other. Through extensive experiments, we observed the following main findings: (1) the proposed approach consistently outperformed the baseline methods across different experiment settings; (2) the encoder training process can significantly boost the performance of the proposed approach; (3) when detecting boundaries for single-boundary hybrid essays, the proposed approach could be enhanced by adopting a relatively large prototype size, leading to a 22% improvement in the In-Domain evaluation and an 18% improvement in the Out-of-Domain evaluation.

The evolution of wireless networks gravitates towards connected intelligence, a concept that envisions seamless interconnectivity among humans, objects, and intelligence in a hyper-connected cyber-physical world. Edge artificial intelligence (Edge AI) is a promising solution to achieve connected intelligence by delivering high-quality, low-latency, and privacy-preserving AI services at the network edge. This article presents a vision of autonomous edge AI systems that automatically organize, adapt, and optimize themselves to meet users' diverse requirements, leveraging the power of large language models (LLMs), i.e., Generative Pretrained Transformer (GPT). By exploiting the powerful abilities of GPT in language understanding, planning, and code generation, as well as incorporating classic wisdom such as task-oriented communication and edge federated learning, we present a versatile framework that efficiently coordinates edge AI models to cater to users' personal demands while automatically generating code to train new models in a privacy-preserving manner. Experimental results demonstrate the system's remarkable ability to accurately comprehend user demands, efficiently execute AI models with minimal cost, and effectively create high-performance AI models at edge servers.

Visual target navigation in unknown environments is a crucial problem in robotics. Despite extensive investigation of classical and learning-based approaches in the past, robots lack common-sense knowledge about household objects and layouts. Prior state-of-the-art approaches to this task rely on learning the priors during the training and typically require significant expensive resources and time for learning. To address this, we propose a new framework for visual target navigation that leverages Large Language Models (LLM) to impart common sense for object searching. Specifically, we introduce two paradigms: (i) zero-shot and (ii) feed-forward approaches that use language to find the relevant frontier from the semantic map as a long-term goal and explore the environment efficiently. Our analysis demonstrates the notable zero-shot generalization and transfer capabilities from the use of language. Experiments on Gibson and Habitat-Matterport 3D (HM3D) demonstrate that the proposed framework significantly outperforms existing map-based methods in terms of success rate and generalization. Ablation analysis also indicates that the common-sense knowledge from the language model leads to more efficient semantic exploration. Finally, we provide a real robot experiment to verify the applicability of our framework in real-world scenarios. The supplementary video and code can be accessed via the following link: https://sites.google.com/view/l3mvn.

This study highlights the potential of fine-tuned ChatGPT (GPT-3.5) for automatically scoring student written constructed responses using example assessment tasks in science education. Recent studies on OpenAI's generative model GPT-3.5 proved its superiority in predicting the natural language with high accuracy and human-like responses. GPT-3.5 has been trained over enormous online language materials such as journals and Wikipedia; therefore, more than direct usage of pre-trained GPT-3.5 is required for automatic scoring as students utilize a different language than trained material. These imply that a domain-specific model, fine-tuned over data for specific tasks, can enhance model performance. In this study, we fine-tuned GPT-3.5 on six assessment tasks with a diverse dataset of middle-school and high-school student responses and expert scoring. The six tasks comprise two multi-label and four multi-class assessment tasks. We compare the performance of fine-tuned GPT-3.5 with the fine-tuned state-of-the-art Google's generated language model, BERT. The results show that in-domain training corpora constructed from science questions and responses for BERT achieved average accuracy = 0.838, SD = 0.069. GPT-3.5 shows a remarkable average increase (9.1%) in automatic scoring accuracy (mean = 9.15, SD = 0.042) for the six tasks, p =0.001 < 0.05. Specifically, for multi-label tasks (item 1 with 5 labels; item 2 with 10 labels), GPT-3.5 achieved significantly higher scoring accuracy than BERT across all the labels, with the second item achieving a 7.1% increase. The average scoring increase for the four multi-class items for GPT-3.5 was 10.6% compared to BERT. Our study confirmed the effectiveness of fine-tuned GPT-3.5 for automatic scoring of student responses on domain-specific data in education with high accuracy. We have released fine-tuned models for public use and community engagement.

This paper addresses the gap in We are particularly inspired by approaches in biology where efficient audio quality prediction, especially in low-resource zero-shot prediction is possible using a model's uncertainty settings where extensive MOS data from large-scale listening estimates, where uncertainties act as proxies for downstream tests may be unavailable. We demonstrate that uncertainty tasks [4]. Our main hypotheses are that, measures derived from out-of-the-box pretrained selfsupervised learning (SSL) models, such as wav2vec, correlate 1. uncertainty estimates can be derived from the outputs with MOS scores. These findings are based on data from the of SSL models such as wav2vec, and that, 2022 and 2023 VoiceMOS challenges. We explore the extent 2. these uncertainties can be used as proxies to MOS of this correlation across different models and language scores as high model uncertainty around the contents contexts, revealing insights into how inherent uncertainties in of an audio sequence must correspond to low audio SSL models can serve as effective proxies for audio quality quality.

The problem with Bluey is there's not enough of it. Even with 151 seven-minute-long episodes of the popular children's animated show out there, parents of toddlers still desperately wait for Australia's Ludo Studio to release another season. The only way to get more Bluey more quickly is if they create their own stories starring the Brisbane-based family of blue heeler dogs. The London-based developer and father used OpenAI's latest tool, customizable bots called GPTs, to create a story generator for his young daughter. The bot, which he calls Bluey-GPT, begins each session by asking people their name, age, and a bit about their day, then churns out personalized tales starring Bluey and her sister Bingo.

The OpenAI CEO lost the confidence of top leaders in the three organizations he has directed, yet each time he's rebounded to greater heights

Ask any American what their favorite part of a Christmas dinner is and you'll here a wide range of answers. Many families see the turkey or roast ham as the true centerpiece of the meal, while others drool over side dishes like stuffing, mashed potatoes or green beans. And the star of the show was rather surprising. Ask any American what their favorite part of a Christmas dinner is and you'll here a wide range of answers. But we didn't ask any American, we asked AI In most cognitive tests, Bard outperforms GPT-4, which powers ChatGPT. Microsoft's bot can tell users when an omelet is cooked, suggest the best design for a paper airplane or help a football player improve their skills.