ChatGPT is a chatbot that can answer text prompts fairly accurately, even performing very well on postgraduate-level questions. Many educators have found that their take-home or remote tests and exams are vulnerable to ChatGPT-based cheating because students may directly use answers provided by tools like ChatGPT. In this paper, we try to provide an answer to an important question: how well ChatGPT can answer test questions and how we can detect whether the questions of a test can be answered correctly by ChatGPT. We generated ChatGPT's responses to the MedMCQA dataset, which contains over 10,000 medical school entrance exam questions. We analyzed the responses and uncovered certain types of questions ChatGPT answers more inaccurately than others. In addition, we have created a basic natural language processing model to single out the most vulnerable questions to ChatGPT in a collection of questions or a sample exam. Our tool can be used by test-makers to avoid ChatGPT-vulnerable test questions.

Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their proprietary nature and massive scale. In this work, we explore the potential of deriving confidence from the distribution of multiple randomly sampled model generations, via three measures of consistency. We perform an extensive evaluation across various open and closed-source models on nine reasoning datasets. Results show that consistency-based calibration methods outperform existing post-hoc approaches. Meanwhile, we find that factors such as intermediate explanations, model scaling, and larger sample sizes enhance calibration, while instruction-tuning makes calibration more difficult. Moreover, confidence scores obtained from consistency have the potential to enhance model performance. Finally, we offer practical guidance on choosing suitable consistency metrics for calibration, tailored to the characteristics of various LMs.

Taxonomies represent an arborescence hierarchical structure that establishes relationships among entities to convey knowledge within a specific domain. Each edge in the taxonomy signifies a hypernym-hyponym relationship. Taxonomies find utility in various real-world applications, such as e-commerce search engines and recommendation systems. Consequently, there arises a necessity to enhance these taxonomies over time. However, manually curating taxonomies with neoteric data presents challenges due to limitations in available human resources and the exponential growth of data. Therefore, it becomes imperative to develop automatic taxonomy expansion methods. Traditional supervised taxonomy expansion approaches encounter difficulties stemming from limited resources, primarily due to the small size of existing taxonomies. This scarcity of training data often leads to overfitting. In this paper, we propose FLAME, a novel approach for taxonomy expansion in low-resource environments by harnessing the capabilities of large language models that are trained on extensive real-world knowledge. LLMs help compensate for the scarcity of domain-specific knowledge. Specifically, FLAME leverages prompting in few-shot settings to extract the inherent knowledge within the LLMs, ascertaining the hypernym entities within the taxonomy. Furthermore, it employs reinforcement learning to fine-tune the large language models, resulting in more accurate predictions. Experiments on three real-world benchmark datasets demonstrate the effectiveness of FLAME in real-world scenarios, achieving a remarkable improvement of 18.5% in accuracy and 12.3% in Wu & Palmer metric over eight baselines. Furthermore, we elucidate the strengths and weaknesses of FLAME through an extensive case study, error analysis and ablation studies on the benchmarks.

In the rapidly evolving landscape of social media, the introduction of new emojis in Unicode release versions presents a structured opportunity to explore digital language evolution. Analyzing a large dataset of sampled English tweets, we examine how newly released emojis gain traction and evolve in meaning. We find that community size of early adopters and emoji semantics are crucial in determining their popularity. Certain emojis experienced notable shifts in the meanings and sentiment associations during the diffusion process. Additionally, we propose a novel framework utilizing language models to extract words and pre-existing emojis with semantically similar contexts, which enhances interpretation of new emojis. The framework demonstrates its effectiveness in improving sentiment classification performance by substituting unknown new emojis with familiar ones. This study offers a new perspective in understanding how new language units are adopted, adapted, and integrated into the fabric of online communication.

Uncertainty estimation plays a pivotal role in ensuring the reliability of safety-critical human-AI interaction systems, particularly in the medical domain. However, a general method for quantifying the uncertainty of free-form answers has yet to be established in open-ended medical question-answering (QA) tasks, where irrelevant words and sequences with limited semantic information can be the primary source of uncertainty due to the presence of generative inequality. In this paper, we propose the Word-Sequence Entropy (WSE), which calibrates the uncertainty proportion at both the word and sequence levels according to the semantic relevance, with greater emphasis placed on keywords and more relevant sequences when performing uncertainty quantification. We compare WSE with 6 baseline methods on 5 free-form medical QA datasets, utilizing 7 "off-the-shelf" large language models (LLMs), and show that WSE exhibits superior performance on accurate uncertainty measurement under two standard criteria for correctness evaluation (e.g., WSE outperforms existing state-of-the-art method by 3.23% AUROC on the MedQA dataset). Additionally, in terms of the potential for real-world medical QA applications, we achieve a significant enhancement in the performance of LLMs when employing sequences with lower uncertainty, identified by WSE, as final answers (e.g., +6.36% accuracy improvement on the COVID-QA dataset), without requiring any additional task-specific fine-tuning or architectural modifications.

Humans perceive and comprehend different visual properties of an object based on specific contexts. For instance, we know that a banana turns brown ``when it becomes rotten,'' whereas it appears green ``when it is unripe.'' Previous studies on probing visual commonsense knowledge have primarily focused on examining language models' understanding of typical properties (e.g., colors and shapes) of objects. We present WinoViz, a text-only evaluation dataset, consisting of 1,380 examples that probe the reasoning abilities of language models regarding variant visual properties of objects under different contexts or states. Our task is challenging since it requires pragmatic reasoning (finding intended meanings) and visual knowledge reasoning. We also present multi-hop data, a more challenging version of our data, which requires multi-step reasoning chains to solve our task. In our experimental analysis, our findings are: a) Large language models such as GPT-4 demonstrate effective performance, but when it comes to multi-hop data, their performance is significantly degraded. b) Large models perform well on pragmatic reasoning, but visual knowledge reasoning is a bottleneck in our task. c) Vision-language models outperform their language-model counterparts. d) A model with machine-generated images performs poorly in our task. This is due to the poor quality of the generated images.

The integration of Large Language Models (LLMs) into Development Environments (IDEs) has become a focal point in modern software development. LLMs such as OpenAI GPT-3.5/4 and Code Llama offer the potential to significantly augment developer productivity by serving as intelligent, chat-driven programming assistants. However, utilizing LLMs out of the box is unlikely to be optimal for any given scenario. Rather, each system requires the LLM to be honed to its set of heuristics to ensure the best performance. In this paper, we introduce the Copilot evaluation harness: a set of data and tools for evaluating LLM-guided IDE interactions, covering various programming scenarios and languages. We propose our metrics as a more robust and information-dense evaluation than previous state of the art evaluation systems. We design and compute both static and execution based success metrics for scenarios encompassing a wide range of developer tasks, including code generation from natural language (generate), documentation generation from code (doc), test case generation (test), bug-fixing (fix), and workspace understanding and query resolution (workspace). These success metrics are designed to evaluate the performance of LLMs within a given IDE and its respective parameter space. Our learnings from evaluating three common LLMs using these metrics can inform the development and validation of future scenarios in LLM guided IDEs.

Foundation models like ChatGPT and GPT-4 have revolutionized artificial intelligence, exhibiting remarkable abilities to generalize across a wide array of tasks and applications beyond their initial training objectives. However, when this concept is applied to graph learning, a stark contrast emerges. Graph learning has predominantly focused on single-graph models, tailored to specific tasks or datasets, lacking the ability to transfer learned knowledge to different domains. This limitation stems from the inherent complexity and diversity of graph structures, along with the different feature and label spaces specific to graph data. In this paper, we present our UniGraph framework, designed to train a graph foundation model capable of generalizing to unseen graphs and tasks across diverse domains. Unlike single-graph models that use pre-computed node features of varying dimensions as input, our approach leverages Text-Attributed Graphs (TAGs) for unifying node representations. We propose a cascaded architecture of Language Models (LMs) and Graph Neural Networks (GNNs) as backbone networks with a self-supervised training objective based on Masked Graph Modeling (MGM). We introduce graph instruction tuning using Large Language Models (LLMs) to enable zero-shot prediction ability. Our comprehensive experiments across various graph learning tasks and domains demonstrate the model's effectiveness in self-supervised representation learning on unseen graphs, few-shot in-context transfer, and zero-shot transfer, even surpassing or matching the performance of GNNs that have undergone supervised training on target datasets.

Retrieval Augmented Generation (RAG) has introduced a new paradigm for Large Language Models (LLMs), aiding in the resolution of knowledge-intensive tasks. However, current RAG models position LLMs as passive knowledge receptors, thereby restricting their capacity for learning and comprehending external knowledge. In this paper, we present ActiveRAG, an innovative RAG framework that shifts from passive knowledge acquisition to an active learning mechanism. This approach utilizes the Knowledge Construction mechanism to develop a deeper understanding of external knowledge by associating it with previously acquired or memorized knowledge. Subsequently, it designs the Cognitive Nexus mechanism to incorporate the outcomes from both chains of thought and knowledge construction, thereby calibrating the intrinsic cognition of LLMs. Our experimental results demonstrate that ActiveRAG surpasses previous RAG models, achieving a 5% improvement on question-answering datasets. All data and codes are available at https://github.com/OpenMatch/ActiveRAG.

Large Language Models with transformer architecture have revolutionized the domain of text generation, setting unprecedented benchmarks. Despite their impressive capabilities, LLMs have been criticized for generating outcomes that deviate from factual accuracy or display logical inconsistencies, phenomena commonly referred to as hallucinations. This term, however, has often been misapplied to any results deviating from the instructor's expectations, which this paper defines as attention misdirection rather than true hallucinations. Understanding the distinction between hallucinations and attention misdirection becomes increasingly relevant in business contexts, where the ramifications of such errors can significantly impact the value extraction from these inherently pre-trained models. This paper highlights the best practices of the PGI, Persona, Grouping, and Intelligence, method, a strategic framework that achieved a remarkable error rate of only 3,15 percent across 4,000 responses generated by GPT in response to a real business challenge. It emphasizes that by equipping experimentation with knowledge, businesses can unlock opportunities for innovation through the use of these natively pre-trained models. This reinforces the notion that strategic application grounded in a skilled team can maximize the benefits of emergent technologies such as the LLMs.