Keeping track of how states of entities change as a text or dialog unfolds is a key prerequisite to discourse understanding. Yet, there have been few systematic investigations into the ability of large language models (LLMs) to track discourse entities. In this work, we present a task probing to what extent a language model can infer the final state of an entity given an English description of the initial state and a series of state-changing operations. We use this task to first investigate whether Flan-T5, GPT-3 and GPT-3.5 can track the state of entities, and find that only GPT-3.5 models, which have been pretrained on large amounts of code, exhibit this ability. We then investigate whether smaller models pretrained primarily on text can learn to track entities, through finetuning T5 on several training/evaluation splits. While performance degrades for more complex splits, we find that even when evaluated on a different set of entities from training or longer operation sequences, a finetuned model can perform non-trivial entity tracking. Taken together, these results suggest that language models can learn to track entities but pretraining on text corpora alone does not make this capacity surface.

To facilitate the research on intelligent and human-like chatbots with multi-modal context, we introduce a new video-based multi-modal dialogue dataset, called TikTalk. We collect 38K videos from a popular video-sharing platform, along with 367K conversations posted by users beneath them. Users engage in spontaneous conversations based on their multi-modal experiences from watching videos, which helps recreate real-world chitchat context. Compared to previous multi-modal dialogue datasets, the richer context types in TikTalk lead to more diverse conversations, but also increase the difficulty in capturing human interests from intricate multi-modal information to generate personalized responses. Moreover, external knowledge is more frequently evoked in our dataset. These facts reveal new challenges for multi-modal dialogue models. We quantitatively demonstrate the characteristics of TikTalk, propose a video-based multi-modal chitchat task, and evaluate several dialogue baselines. Experimental results indicate that the models incorporating large language models (LLM) can generate more diverse responses, while the model utilizing knowledge graphs to introduce external knowledge performs the best overall. Furthermore, no existing model can solve all the above challenges well. There is still a large room for future improvements, even for LLM with visual extensions. Our dataset is available at \url{https://ruc-aimind.github.io/projects/TikTalk/}.

Formality is one of the important characteristics of text documents. The automatic detection of the formality level of a text is potentially beneficial for various natural language processing tasks. Before, two large-scale datasets were introduced for multiple languages featuring formality annotation -- GYAFC and X-FORMAL. However, they were primarily used for the training of style transfer models. At the same time, the detection of text formality on its own may also be a useful application. This work proposes the first to our knowledge systematic study of formality detection methods based on statistical, neural-based, and Transformer-based machine learning methods and delivers the best-performing models for public usage. We conducted three types of experiments -- monolingual, multilingual, and cross-lingual. The study shows the overcome of Char BiLSTM model over Transformer-based ones for the monolingual and multilingual formality classification task, while Transformer-based classifiers are more stable to cross-lingual knowledge transfer.

What is unique about AI is also what is most feared and celebrated--its ability to match some of our own skills, and then to go further, accomplishing what humans cannot. AI's capacity to model itself on human behavior has become its defining feature. Yet behind every advance in machine learning and large language models are, in fact, people--both the often obscured human labor that makes large language models safer to use, and the individuals who make critical decisions on when and how to best use this technology. Reporting on people and influence is what TIME does best. That led us to the TIME100 AI.

You've likely heard of ChatGPT at this point. OpenAI's powerful chatbot has revolutionized how people do research, write blog posts, and more. But you can't really get the most out of ChatGPT if you're not sure what to ask it. And that's where The Ultimate ChatGPT Prompts Guide comes in. This comprehensive resource gives you more than 3,000 highly optimized prompts covering a wide range of topics.

At leading Swedish university Lund, teachers decide which students can use artificial intelligence to help them with assignments. At the University of Western Australia in Perth, staff have talked to students about the challenges and possible benefits of using generative AI in their work, while the University of Hong Kong is allowing ChatGPT within strict limits. Launched by Microsoft-backed OpenAI on Nov. 30, ChatGPT has become the world's fastest growing app to date and prompted the release of rivals like Google's Bard.

Autonomous agents have long been a prominent research focus in both academic and industry communities. Previous research in this field often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and thus makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of web knowledge, large language models (LLMs) have demonstrated remarkable potential in achieving human-level intelligence. This has sparked an upsurge in studies investigating LLM-based autonomous agents. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of LLM-based autonomous agents from a holistic perspective. More specifically, we first discuss the construction of LLM-based autonomous agents, for which we propose a unified framework that encompasses a majority of the previous work. Then, we present a comprehensive overview of the diverse applications of LLM-based autonomous agents in the fields of social science, natural science, and engineering. Finally, we delve into the evaluation strategies commonly used for LLM-based autonomous agents. Based on the previous studies, we also present several challenges and future directions in this field.

Recent popularity surrounds large AI language models due to their impressive natural language capabilities. They contribute significantly to language-related tasks, including prompt-based learning, making them valuable for various specific tasks. This approach unlocks their full potential, enhancing precision and generalization. Research communities are actively exploring their applications, with ChatGPT receiving recognition. Despite extensive research on large language models, their potential in recommendation scenarios still needs to be explored. This study aims to fill this gap by investigating ChatGPT's capabilities as a zero-shot recommender system. Our goals include evaluating its ability to use user preferences for recommendations, reordering existing recommendation lists, leveraging information from similar users, and handling cold-start situations. We assess ChatGPT's performance through comprehensive experiments using three datasets (MovieLens Small, Last.FM, and Facebook Book). We compare ChatGPT's performance against standard recommendation algorithms and other large language models, such as GPT-3.5 and PaLM-2. To measure recommendation effectiveness, we employ widely-used evaluation metrics like Mean Average Precision (MAP), Recall, Precision, F1, normalized Discounted Cumulative Gain (nDCG), Item Coverage, Expected Popularity Complement (EPC), Average Coverage of Long Tail (ACLT), Average Recommendation Popularity (ARP), and Popularity-based Ranking-based Equal Opportunity (PopREO). Through thoroughly exploring ChatGPT's abilities in recommender systems, our study aims to contribute to the growing body of research on the versatility and potential applications of large language models. Our experiment code is available on the GitHub repository: https://github.com/sisinflab/Recommender-ChatGPT

Gene set analysis is a mainstay of functional genomics, but it relies on manually curated databases of gene functions that are incomplete and unaware of biological context. Here we evaluate the ability of OpenAI's GPT-4, a Large Language Model (LLM), to develop hypotheses about common gene functions from its embedded biomedical knowledge. We created a GPT-4 pipeline to label gene sets with names that summarize their consensus functions, substantiated by analysis text and citations. Benchmarking against named gene sets in the Gene Ontology, GPT-4 generated very similar names in 50% of cases, while in most remaining cases it recovered the name of a more general concept. In gene sets discovered in 'omics data, GPT-4 names were more informative than gene set enrichment, with supporting statements and citations that largely verified in human review. The ability to rapidly synthesize common gene functions positions LLMs as valuable functional genomics assistants.

This paper investigates how large language models (LLMs) can enhance recommender systems, with a specific focus on Conversational Recommender Systems that leverage user preferences and personalised candidate selections from existing ranking models. We introduce VideolandGPT, a recommender system for a Video-on-Demand (VOD) platform, Videoland, which uses ChatGPT to select from a predetermined set of contents, considering the additional context indicated by users' interactions with a chat interface. We evaluate ranking metrics, user experience, and fairness of recommendations, comparing a personalised and a non-personalised version of the system, in a between-subject user study. Our results indicate that the personalised version outperforms the non-personalised in terms of accuracy and general user satisfaction, while both versions increase the visibility of items which are not in the top of the recommendation lists. However, both versions present inconsistent behavior in terms of fairness, as the system may generate recommendations which are not available on Videoland.