Recent advancements in natural language and Large Language Models (LLMs) have enabled AI agents to simulate human-like interactions within virtual worlds. However, these interactions still face limitations in complexity and flexibility, particularly in scenarios involving multiple characters and novel objects. Pre-defining all interactable objects in the agent's world model presents challenges, and conveying implicit intentions to multiple characters through complex interactions remains difficult. To address these issues, we propose integrating virtual Game Masters (GMs) into the agent's world model, drawing inspiration from Tabletop Role-Playing Games (TRPGs). GMs play a crucial role in overseeing information, estimating players' intentions, providing environment descriptions, and offering feedback, compensating for current world model deficiencies. To facilitate future explorations for complex interactions, we introduce a benchmark named Tachikuma, comprising a Multiple character and novel Object based interaction Estimation (MOE) task and a supporting dataset. MOE challenges models to understand characters' intentions and accurately determine their actions within intricate contexts involving multi-character and novel object interactions. Besides, the dataset captures log data from real-time communications during gameplay, providing diverse, grounded, and complex interactions for further explorations. Finally, we present a simple prompting baseline and evaluate its performance, demonstrating its effectiveness in enhancing interaction understanding. We hope that our dataset and task will inspire further research in complex interactions with natural language, fostering the development of more advanced AI agents.

\emph{Circuit analysis} is a promising technique for understanding the internal mechanisms of language models. However, existing analyses are done in small models far from the state of the art. To address this, we present a case study of circuit analysis in the 70B Chinchilla model, aiming to test the scalability of circuit analysis. In particular, we study multiple-choice question answering, and investigate Chinchilla's capability to identify the correct answer \emph{label} given knowledge of the correct answer \emph{text}. We find that the existing techniques of logit attribution, attention pattern visualization, and activation patching naturally scale to Chinchilla, allowing us to identify and categorize a small set of `output nodes' (attention heads and MLPs). We further study the `correct letter' category of attention heads aiming to understand the semantics of their features, with mixed results. For normal multiple-choice question answers, we significantly compress the query, key and value subspaces of the head without loss of performance when operating on the answer labels for multiple-choice questions, and we show that the query and key subspaces represent an `Nth item in an enumeration' feature to at least some extent. However, when we attempt to use this explanation to understand the heads' behaviour on a more general distribution including randomized answer labels, we find that it is only a partial explanation, suggesting there is more to learn about the operation of `correct letter' heads on multiple choice question answering.

We assessed the performance of commercial Large Language Models (LLMs) GPT-3.5-Turbo and GPT-4 on tasks from the 2023 BioASQ challenge. In Task 11b Phase B, which is focused on answer generation, both models demonstrated competitive abilities with leading systems. Remarkably, they achieved this with simple zero-shot learning, grounded with relevant snippets. Even without relevant snippets, their performance was decent, though not on par with the best systems. Interestingly, the older and cheaper GPT-3.5-Turbo system was able to compete with GPT-4 in the grounded Q&A setting on factoid and list answers. In Task 11b Phase A, focusing on retrieval, query expansion through zero-shot learning improved performance, but the models fell short compared to other systems. The code needed to rerun these experiments is available through GitHub.

To enhance the quality of generated stories, recent story generation models have been investigating the utilization of higher-level attributes like plots or commonsense knowledge. The application of prompt-based learning with large language models (LLMs), exemplified by GPT-3, has exhibited remarkable performance in diverse natural language processing (NLP) tasks. This paper conducts a comprehensive investigation, utilizing both automatic and human evaluation, to compare the story generation capacity of LLMs with recent models across three datasets with variations in style, register, and length of stories. The results demonstrate that LLMs generate stories of significantly higher quality compared to other story generation models. Moreover, they exhibit a level of performance that competes with human authors, albeit with the preliminary observation that they tend to replicate real stories in situations involving world knowledge, resembling a form of plagiarism.

It's been quite a year for ChatGPT, with the large language model (LLM) now taking exams, churning out content, searching the web, writing code, and more. The AI chatbot can produce its own stories, though whether they're any good is another matter. If you're in any way involved in the business of writing, then tools like ChatGPT have the potential to complete up-end the way you work--but at this stage, it's not inevitable that journalists, authors, and copywriters will be replaced by generative AI bots. What we can say with certainty is that ChatGPT is a reliable writing assistant, provided you use it in the right way. If you have to put words in order as part of your job, here's how ChatGPT might be able to take your writing to the next level--at least until it replaces you, anyway.

Objectives: To describe the development and validation of a zero-shot learning natural language processing (NLP) tool for abstracting data from unstructured text contained within PDF documents, such as those found within electronic health records. Materials and Methods: A data abstraction tool based on the GPT-3.5 model from OpenAI was developed and compared to three physician human abstractors in terms of time to task completion and accuracy for abstracting data on 14 unique variables from a set of 199 de-identified radical prostatectomy pathology reports. The reports were processed by the software tool in vectorized and scanned formats to establish the impact of optical character recognition on data abstraction. The tool was assessed for superiority for data abstraction speed and non-inferiority for accuracy. Results: The human abstractors required a mean of 101s per report for data abstraction, with times varying from 15 to 284 s. In comparison, the software tool required a mean of 12.8 s to process the vectorized reports and a mean of 15.8 to process the scanned reports (P < 0.001). The overall accuracies of the three human abstractors were 94.7%, 97.8%, and 96.4% for the combined set of 2786 datapoints. The software tool had an overall accuracy of 94.2% for the vectorized reports, proving to be non-inferior to the human abstractors at a margin of -10% ($\alpha$=0.025). The tool had a slightly lower accuracy of 88.7% using the scanned reports, proving to be non-inferiority to 2 out of 3 human abstractors. Conclusion: The developed zero-shot learning NLP tool affords researchers comparable levels of accuracy to that of human abstractors, with significant time savings benefits. Because of the lack of need for task-specific model training, the developed tool is highly generalizable and can be used for a wide variety of data abstraction tasks, even outside the field of medicine.

Knowledge-intensive tasks (e.g., open-domain question answering (QA)) require a substantial amount of factual knowledge and often rely on external information for assistance. Recently, large language models (LLMs) (e.g., ChatGPT), have demonstrated impressive prowess in solving a wide range of tasks with world knowledge, including knowledge-intensive tasks. However, it remains unclear how well LLMs are able to perceive their factual knowledge boundaries, particularly how they behave when incorporating retrieval augmentation. In this study, we present an initial analysis of the factual knowledge boundaries of LLMs and how retrieval augmentation affects LLMs on open-domain QA. Specially, we focus on three primary research questions and analyze them by examining QA performance, priori judgement and posteriori judgement of LLMs. We show evidence that LLMs possess unwavering confidence in their capabilities to respond to questions and the accuracy of their responses. Furthermore, retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries, thereby improving their judgemental abilities. Additionally, we also find that LLMs have a propensity to rely on the provided retrieval results when formulating answers, while the quality of these results significantly impacts their reliance. The code to reproduce this work is available at https://github.com/RUCAIBox/LLM-Knowledge-Boundary.

This study presents a thorough examination of various Generative Pretrained Transformer (GPT) methodologies in sentiment analysis, specifically in the context of Task 4 on the SemEval 2017 dataset. Three primary strategies are employed: 1) prompt engineering using the advanced GPT-3.5 Turbo, 2) fine-tuning GPT models, and 3) an inventive approach to embedding classification. The research yields detailed comparative insights among these strategies and individual GPT models, revealing their unique strengths and potential limitations. Additionally, the study compares these GPT-based methodologies with other current, high-performing models previously used with the same dataset. The results illustrate the significant superiority of the GPT approaches in terms of predictive performance, more than 22\% in F1-score compared to the state-of-the-art. Further, the paper sheds light on common challenges in sentiment analysis tasks, such as understanding context and detecting sarcasm. It underscores the enhanced capabilities of the GPT models to effectively handle these complexities. Taken together, these findings highlight the promising potential of GPT models in sentiment analysis, setting the stage for future research in this field. The code can be found at https://github.com/DSAatUSU/SentimentGPT

Launchpad is a musical instrument that allows users to create and perform music by pressing illuminated buttons. To assist and inspire the design of the Launchpad light effect, and provide a more accessible approach for beginners to create music visualization with this instrument, we proposed the LaunchpadGPT model to generate music visualization designs on Launchpad automatically. Based on the language model with excellent generation ability, our proposed LaunchpadGPT takes an audio piece of music as input and outputs the lighting effects of Launchpad-playing in the form of a video (Launchpad-playing video). We collect Launchpad-playing videos and process them to obtain music and corresponding video frame of Launchpad-playing as prompt-completion pairs, to train the language model. The experiment result shows the proposed method can create better music visualization than random generation methods and hold the potential for a broader range of music visualization applications. Our code is available at https://github.com/yunlong10/LaunchpadGPT/.

In the field of visual scene understanding, deep neural networks have made impressive advancements in various core tasks like segmentation, tracking, and detection. However, most approaches operate on the close-set assumption, meaning that the model can only identify pre-defined categories that are present in the training set. Recently, open vocabulary settings were proposed due to the rapid progress of vision language pre-training. These new approaches seek to locate and recognize categories beyond the annotated label space. The open vocabulary approach is more general, practical, and effective compared to weakly supervised and zero-shot settings. This paper provides a thorough review of open vocabulary learning, summarizing and analyzing recent developments in the field. In particular, we begin by comparing it to related concepts such as zero-shot learning, open-set recognition, and out-of-distribution detection. Then, we review several closely related tasks in the case of segmentation and detection, including long-tail problems, few-shot, and zero-shot settings. For the method survey, we first present the basic knowledge of detection and segmentation in close-set as the preliminary knowledge. Next, we examine various scenarios in which open vocabulary learning is used, identifying common design elements and core ideas. Then, we compare the recent detection and segmentation approaches in commonly used datasets and benchmarks. Finally, we conclude with insights, issues, and discussions regarding future research directions. To our knowledge, this is the first comprehensive literature review of open vocabulary learning. We keep tracing related works at https://github.com/jianzongwu/Awesome-Open-Vocabulary.