Large Language Models (LLMs) has made significant progress in a number of professional fields, including medicine, law, and finance. However, in traditional Chinese medicine (TCM), there are challenges such as the essential differences between theory and modern medicine, the lack of specialized corpus resources, and the fact that relying only on supervised fine-tuning may lead to overconfident predictions. To address these challenges, we propose a two-stage training approach that combines continuous pre-training and supervised fine-tuning. A notable contribution of our study is the processing of a 2GB corpus dedicated to TCM, constructing pre-training and instruction fine-tuning datasets for TCM, respectively. In addition, we have developed Qibo-Benchmark, a tool that evaluates the performance of LLM in the TCM on multiple dimensions, including subjective, objective, and three TCM NLP tasks. The medical LLM trained with our pipeline, named $\textbf{Qibo}$, exhibits significant performance boosts. Compared to the baselines, the average subjective win rate is 63%, the average objective accuracy improved by 23% to 58%, and the Rouge-L scores for the three TCM NLP tasks are 0.72, 0.61, and 0.55. Finally, we propose a pipline to apply Qibo to TCM consultation and demonstrate the model performance through the case study.

Travel choice analysis is crucial for understanding individual travel behavior to develop appropriate transport policies and recommendation systems in Intelligent Transportation Systems (ITS). Despite extensive research, this domain faces two critical challenges: a) modeling with limited survey data, and b) simultaneously achieving high model explainability and accuracy. In this paper, we introduce a novel prompt-learning-based Large Language Model(LLM) framework that significantly improves prediction accuracy and provides explicit explanations for individual predictions. This framework involves three main steps: transforming input variables into textual form; building of demonstrations similar to the object, and applying these to a well-trained LLM. We tested the framework's efficacy using two widely used choice datasets: London Passenger Mode Choice (LPMC) and Optima-Mode collected in Switzerland. The results indicate that the LLM significantly outperforms state-of-the-art deep learning methods and discrete choice models in predicting people's choices. Additionally, we present a case of explanation illustrating how the LLM framework generates understandable and explicit explanations at the individual level.

Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating execution results into the next action prediction. Despite their progress, these methods suffer from performance degradation when addressing practical tasks due to: (1) the pre-defined pipeline with restricted flexibility to calibrate incorrect actions, and (2) the struggle to adapt a general LLM-based agent to perform a variety of specialized actions. To mitigate these problems, we propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. ConAgents introduces two communication protocols to enable the flexible cooperation of agents. To effectively generalize the ConAgents into open-source models, we also propose specialized action distillation, enhancing their ability to perform specialized actions in our framework. Our extensive experiments on three datasets show that the LLMs, when equipped with the ConAgents, outperform baselines with substantial improvement (i.e., up to 14% higher success rate).

Since it was first proposed in 1950, passing the'Turing test' has been seen as one of the highest goals in AI. But now, researchers claim that ChatGPT has become the first AI to pass this famous test for human intelligence. Proposed by computer pioneer Alan Turing, it claims that an AI should be considered truly intelligent if people can't tell if they are speaking to a human or machine. In a pre-print paper, cognitive scientists from UC San Diego argue that the ChatGPT-4 can fool human test subjects more than half of the time. However, the researchers say this might say more about the Turing test than it does about the intelligence of modern AI.

Retrieval-augmented generation (RAG) effectively addresses issues of static knowledge and hallucination in large language models. Existing studies mostly focus on question scenarios with clear user intents and concise answers. However, it is prevalent that users issue broad, open-ended queries with diverse sub-intents, for which they desire rich and long-form answers covering multiple relevant aspects. To tackle this important yet underexplored problem, we propose a novel RAG framework, namely RichRAG. It includes a sub-aspect explorer to identify potential sub-aspects of input questions, a multi-faceted retriever to build a candidate pool of diverse external documents related to these sub-aspects, and a generative list-wise ranker, which is a key module to provide the top-k most valuable documents for the final generator. These ranked documents sufficiently cover various query aspects and are aware of the generator's preferences, hence incentivizing it to produce rich and comprehensive responses for users. The training of our ranker involves a supervised fine-tuning stage to ensure the basic coverage of documents, and a reinforcement learning stage to align downstream LLM's preferences to the ranking of documents. Experimental results on two publicly available datasets prove that our framework effectively and efficiently provides comprehensive and satisfying responses to users.

The article presents some current observations (as of April 10, 2024) on the integration of AI-generated images within processes of media convergence. It draws on two different concepts of intermediality. Primary intermediality concepts are motivated by the object when a new type of technology develops the potential to become socially relevant as a media form and thus a socially, politically, or culturally important communicative factor. Due to their uncertain 'measurements' within the wider media ecology, however, the new, still potential media form appears hybrid. The "inter-" or "between-" of this initial intermediality moment thus refers to the questionable "site" and the questionable description of the potential media form between already existing technologies and cultural forms and their conceptual measurements. For secondary concepts of intermediality, in contrast, it can be assumed that the boundaries of media forms and their application have already been drawn and are reasonably undisputed. This then raises the question of intentional and staged references to AI imagery within other media forms and pictures. The article discusses indicators of both intermediality moments using current examples and controversies surrounding AI images. The thesis is that there can be no talk of a seamless 'integration' of AI images into the wider media landscape at the moment (within films, comic books, or video games, for example) - as one of countless other image production techniques - and that the medial 'site' of AI image circulation - at least where it is not a matter of deception, but rather their conscious use as AI images - especially in social media communication and in fan cultures, but with repercussions for the more general media ecology and image interpretation, insofar as the suspicion that an image could be AI-generated is now increasingly present as a "hermeneutics of suspicion".

Large language models (LLMs) have revolutionized lots of fields of research. Although it is well-known that fine-tuning is essential for enhancing the capabilities of LLMs, existing research suggests that there is potential redundancy in the fine-tuning process and therefore proposes to update only a subset of parameters. However, these methods fail to leverage the task-specific information to identify important parameters during training. Based on the insight that gradients inherently contain information on task-specific data, we propose Gradient-Mask Tuning (GMT), a method that selectively updates parameters during training based on their gradient information. Specifically, we compute the absolute values of the gradients and apply masking to those with relatively smaller magnitudes. Our empirical results across various tasks demonstrate that GMT not only outperforms traditional fine-tuning methods but also elevates the upper limits of LLM performance. Further analysis indicates that GMT exhibits insensitivity to mask ratio and possesses computational efficiency comparable to vanilla SFT.

Fact knowledge memorization is crucial for Large Language Models (LLM) to generate factual and reliable responses. However, the behaviors of LLM fact memorization remain under-explored. In this paper, we analyze the scaling laws for LLM's fact knowledge and LLMs' behaviors of memorizing different types of facts. We find that LLMs' fact knowledge capacity has a linear and negative exponential law relationship with model size and training epochs, respectively. Estimated by the built scaling law, memorizing the whole Wikidata's facts requires training an LLM with 1000B non-embed parameters for 100 epochs, suggesting that using LLMs to memorize all public facts is almost implausible for a general pre-training setting. Meanwhile, we find that LLMs can generalize on unseen fact knowledge and its scaling law is similar to general pre-training. Additionally, we analyze the compatibility and preference of LLMs' fact memorization. For compatibility, we find LLMs struggle with memorizing redundant facts in a unified way. Only when correlated facts have the same direction and structure, the LLM can compatibly memorize them. This shows the inefficiency of LLM memorization for redundant facts. For preference, the LLM pays more attention to memorizing more frequent and difficult facts, and the subsequent facts can overwrite prior facts' memorization, which significantly hinders low-frequency facts memorization. Our findings reveal the capacity and characteristics of LLMs' fact knowledge learning, which provide directions for LLMs' fact knowledge augmentation.

Agriculture, vital for global sustenance, necessitates innovative solutions due to a lack of organized domain experts, particularly in developing countries where many farmers are impoverished and cannot afford expert consulting. Initiatives like Farmers Helpline play a crucial role in such countries, yet challenges such as high operational costs persist. Automating query resolution can alleviate the burden on traditional call centers, providing farmers with immediate and contextually relevant information. The integration of Agriculture and Artificial Intelligence (AI) offers a transformative opportunity to empower farmers and bridge information gaps. Language models like transformers, the rising stars of AI, possess remarkable language understanding capabilities, making them ideal for addressing information gaps in agriculture. This work explores and demonstrates the transformative potential of Large Language Models (LLMs) in automating query resolution for agricultural farmers, leveraging their expertise in deciphering natural language and understanding context. Using a subset of a vast dataset of real-world farmer queries collected in India, our study focuses on approximately 4 million queries from the state of Tamil Nadu, spanning various sectors, seasonal crops, and query types.

The development of human-robot collaboration has the ability to improve manufacturing system performance by leveraging the unique strengths of both humans and robots. On the shop floor, human operators contribute with their adaptability and flexibility in dynamic situations, while robots provide precision and the ability to perform repetitive tasks. However, the communication gap between human operators and robots limits the collaboration and coordination of human-robot teams in manufacturing systems. Our research presents a human-robot collaborative assembly framework that utilizes a large language model for enhancing communication in manufacturing environments. The framework facilitates human-robot communication by integrating voice commands through natural language for task management. A case study for an assembly task demonstrates the framework's ability to process natural language inputs and address real-time assembly challenges, emphasizing adaptability to language variation and efficiency in error resolution. The results suggest that large language models have the potential to improve human-robot interaction for collaborative manufacturing assembly applications.