Writing a readme is a crucial aspect of software development as it plays a vital role in managing and reusing program code. Though it is a pain point for many developers, automatically creating one remains a challenge even with the recent advancements in large language models (LLMs), because it requires generating an abstract description from thousands of lines of code. In this demo paper, we show that LLMs are capable of generating a coherent and factually correct readmes if we can identify a code fragment that is representative of the repository. Building upon this finding, we developed LARCH (LLM-based Automatic Readme Creation with Heuristics) which leverages representative code identification with heuristics and weak supervision. Through human and automated evaluations, we illustrate that LARCH can generate coherent and factually correct readmes in the majority of cases, outperforming a baseline that does not rely on representative code identification. We have made LARCH open-source and provided a cross-platform Visual Studio Code interface and command-line interface, accessible at https://github.com/hitachi-nlp/larch. A demo video showcasing LARCH's capabilities is available at https://youtu.be/ZUKkh5ED-O4.

In any system that uses structured knowledge graph (KG) data as its underlying knowledge representation, KG-to-text generation is a useful tool for turning parts of the graph data into text that can be understood by humans. Recent work has shown that models that make use of pretraining on large amounts of text data can perform well on the KG-to-text task even with relatively small sets of training data on the specific graph-to-text task. In this paper, we build on this concept by using large language models to perform zero-shot generation based on nothing but the model's understanding of the triple structure from what it can read. We show that ChatGPT achieves near state-of-the-art performance on some measures of the WebNLG 2020 challenge, but falls behind on others. Additionally, we compare factual, counter-factual and fictional statements, and show that there is a significant connection between what the LLM already knows about the data it is parsing and the quality of the output text.

Given enough data, one can feel like it's possible to keep dead loved ones alive. With ChatGPT and other powerful large language models, it is feasible to create a more convincing chatbot of a dead person. But doing so, especially in the face of scarce resources and inevitable decay, ignores the massive amounts of labor that go into keeping the dead alive online. Someone always has to do the hard work of maintaining automated systems, as demonstrated by the overworked and underpaid annotators and content moderators behind generative AI, and this is also true where replicas of the dead are concerned. From managing a digital estate after gathering passwords and account information, to navigating a slowly-decaying inherited smart home, digital death care practices require significant upkeep.

ChatGPT may well revolutionize web search, streamline office chores, and remake education, but the smooth-talking chatbot has also found work as a social media crypto huckster. Researchers at Indiana University Bloomington discovered a botnet powered by ChatGPT operating on X--the social network formerly known as Twitter--in May of this year. The botnet, which the researchers dub Fox8 because of its connection to cryptocurrency websites bearing some variation of the same name, consisted of 1,140 accounts. Many of them seemed to use ChatGPT to craft social media posts and to reply to each other's posts. The auto-generated content was apparently designed to lure unsuspecting humans into clicking links through to the crypto-hyping sites.

When Elon Musk introduced the team behind his new artificial intelligence company xAI last month, the billionaire entrepreneur took a question from the rightwing media activist Alex Lorusso. ChatGPT had begun "editorializing the truth" by giving "weird answers like that there are more than two genders", Lorusso posited. Was that a driver behind Musk's decision to launch xAI, he wondered. "I do think there is significant danger in training AI to be politically correct, or in other words training AI to not say what it actually thinks is true," Musk replied. His own company's AI on the other hand, would be "maximally true" he had said earlier in the presentation.

By now you've no doubt heard of ChatGPT. But what if you could apply its AI powers to other platforms, like Google Sheets? SheetGPT is ChatGPT for Google Sheets, allowing you to simplify how you work with data in Google Sheets. With SheetGPT installed, all you have to do is call the function AI("Your Prompt Here") and you'll get an answer to your prompt in a second. You can use the prompt to combine cells, input URLs into SheetGPT and get the full page content back, connect prompts between different cells, automate work, and much more.

The increasing attention given to AI Generated Content (AIGC) has brought a profound impact on various aspects of daily life, industrial manufacturing, and the academic sector. Recognizing the global trends and competitiveness in AIGC development, this study aims to analyze China's current status in the field. The investigation begins with an overview of the foundational technologies and current applications of AIGC. Subsequently, the study delves into the market status, policy landscape, and development trajectory of AIGC in China, utilizing keyword searches to identify relevant scholarly papers. Furthermore, the paper provides a comprehensive examination of AIGC products and their corresponding ecosystem, emphasizing the ecological construction of AIGC. Finally, this paper discusses the challenges and risks faced by the AIGC industry while presenting a forward-looking perspective on the industry's future based on competitive insights in AIGC.

Deep neural networks often learn unintended bias during training, which might have harmful effects when deployed in real-world settings. This work surveys 214 papers related to sociodemographic bias in natural language processing (NLP). In this study, we aim to provide a more comprehensive understanding of the similarities and differences among approaches to sociodemographic bias in NLP. To better understand the distinction between bias and real-world harm, we turn to ideas from psychology and behavioral economics to propose a definition for sociodemographic bias. We identify three main categories of NLP bias research: types of bias, quantifying bias, and debiasing techniques. We highlight the current trends in quantifying bias and debiasing techniques, offering insights into their strengths and weaknesses. We conclude that current approaches on quantifying bias face reliability issues, that many of the bias metrics do not relate to real-world bias, and that debiasing techniques need to focus more on training methods. Finally, we provide recommendations for future work.

Numerical reasoning is vital for natural language processing models to understand and process numerical information in real-world scenarios. Most current methods first generate the Intermediate Meaning Representations (IMRs) of questions and then generate answers. Current SOTA methods generate programs as IMRs with large language models (LLMs). Intuitively, equations have fewer restrictions and closer semantics to the question than programs, leading to higher generation accuracy. However, current LLMs generate equations worse than programs, where we assume that the equation data is rare in pre-training data compared to programs. So in this paper, we try to use equations as IMRs to solve the numerical reasoning task by addressing two problems: (1) Theoretically, how to prove that the equation is an IMR with higher generation accuracy than programs; (2) Empirically, how to improve the generation accuracy of equations with LLMs. For the first problem, we propose and prove a proposition to theoretically compare the generation accuracy of different IMRs. For the second problem, we present a method called Boosting Numerical Reason\textbfing by Decomposing the Generation of Equations (Bridge), which can improve the accuracy of LLMs in generating equations as IMRs by reducing the tendency of generating constant expressions and programs. Our method improves the performance by 2.2%, 0.9%, and 1.7% on GSM8K, SVAMP, and Algebra datasets compared to the previous state-of-the-art methods under the single reasoning path setting. Our codes and prompts are released in https://github.com/zirui-HIT/Bridge_for_Numerical_Reasoning.

Large language models (LLMs) have shown impressive ability for open-domain NLP tasks. However, LLMs are sometimes too footloose for natural language understanding (NLU) tasks which always have restricted output and input format. Their performances on NLU tasks are highly related to prompts or demonstrations and are shown to be poor at performing several representative NLU tasks, such as event extraction and entity typing. To this end, we present SeqGPT, a bilingual (i.e., English and Chinese) open-source autoregressive model specially enhanced for open-domain natural language understanding. We express all NLU tasks with two atomic tasks, which define fixed instructions to restrict the input and output format but still ``open'' for arbitrarily varied label sets. The model is first instruction-tuned with extremely fine-grained labeled data synthesized by ChatGPT and then further fine-tuned by 233 different atomic tasks from 152 datasets across various domains. The experimental results show that SeqGPT has decent classification and extraction ability, and is capable of performing language understanding tasks on unseen domains. We also conduct empirical studies on the scaling of data and model size as well as on the transfer across tasks. Our model is accessible at https://github.com/Alibaba-NLP/SeqGPT.