Automated sentiment analysis using Large Language Model (LLM)-based models like ChatGPT, Gemini or LLaMA2 is becoming widespread, both in academic research and in industrial applications. However, assessment and validation of their performance in case of ambiguous or ironic text is still poor. In this study, we constructed nuanced and ambiguous scenarios, we translated them in 10 languages, and we predicted their associated sentiment using popular LLMs. The results are validated against post-hoc human responses. Ambiguous scenarios are often well-coped by ChatGPT and Gemini, but we recognise significant biases and inconsistent performance across models and evaluated human languages. This work provides a standardised methodology for automated sentiment analysis evaluation and makes a call for action to further improve the algorithms and their underlying data, to improve their performance, interpretability and applicability.

Data-to-text (D2T) generation is a crucial task in many natural language understanding (NLU) applications and forms the foundation of task-oriented dialog systems. In the context of conversational AI solutions that can work directly with local data on the user's device, architectures utilizing large pre-trained language models (PLMs) are impractical for on-device deployment due to a high memory footprint. To this end, we propose TrICy, a novel lightweight framework for an enhanced D2T task that generates text sequences based on the intent in context and may further be guided by user-provided triggers. We leverage an attention-copy mechanism to predict out-of-vocabulary (OOV) words accurately. Performance analyses on E2E NLG dataset (BLEU: 66.43%, ROUGE-L: 70.14%), WebNLG dataset (BLEU: Seen 64.08%, Unseen 52.35%), and our Custom dataset related to text messaging applications, showcase our architecture's effectiveness. Moreover, we show that by leveraging an optional trigger input, data-to-text generation quality increases significantly and achieves the new SOTA score of 69.29% BLEU for E2E NLG. Furthermore, our analyses show that TrICy achieves at least 24% and 3% improvement in BLEU and METEOR respectively over LLMs like GPT-3, ChatGPT, and Llama 2. We also demonstrate that in some scenarios, performance improvement due to triggers is observed even when they are absent in training.

Objective: To enhance health literacy and accessibility of health information for a diverse patient population by developing a patient-centered artificial intelligence (AI) solution using large language models (LLMs) and Fast Healthcare Interoperability Resources (FHIR) application programming interfaces (APIs). Materials and Methods: The research involved developing LLM on FHIR, an open-source mobile application allowing users to interact with their health records using LLMs. The app is built on Stanford's Spezi ecosystem and uses OpenAI's GPT-4. A pilot study was conducted with the SyntheticMass patient dataset and evaluated by medical experts to assess the app's effectiveness in increasing health literacy. The evaluation focused on the accuracy, relevance, and understandability of the LLM's responses to common patient questions. Results: LLM on FHIR demonstrated varying but generally high degrees of accuracy and relevance in providing understandable health information to patients. The app effectively translated medical data into patient-friendly language and was able to adapt its responses to different patient profiles. However, challenges included variability in LLM responses and the need for precise filtering of health data. Discussion and Conclusion: LLMs offer significant potential in improving health literacy and making health records more accessible. LLM on FHIR, as a pioneering application in this field, demonstrates the feasibility and challenges of integrating LLMs into patient care. While promising, the implementation and pilot also highlight risks such as inconsistent responses and the importance of replicable output. Future directions include better resource identification mechanisms and executing LLMs on-device to enhance privacy and reduce costs.

This paper introduces a novel automated system for generating architecture schematic designs aimed at streamlining complex decision-making at the multifamily real estate development project's outset. Leveraging the combined strengths of generative AI (neuro reasoning) and mathematical program solvers (symbolic reasoning), the method addresses both the reliance on expert insights and technical challenges in architectural schematic design. To address the large-scale and interconnected nature of design decisions needed for designing a whole building, we proposed a novel sequential neuro-symbolic reasoning approach, emulating traditional architecture design processes from initial concept to detailed layout. To remove the need to hand-craft a cost function to approximate the desired objectives, we propose a solution that uses neuro reasoning to generate constraints and cost functions that the symbolic solvers can use to solve. We also incorporate feedback loops for each design stage to ensure a tight integration between neuro and symbolic reasoning. Developed using GPT-4 without further training, our method's effectiveness is validated through comparative studies with real-world buildings. Our method can generate various building designs in accordance with the understanding of the neighborhood, showcasing its potential to transform the realm of architectural schematic design.

Designing domain models and software architectures represents a significant challenge in software development, as the resulting architectures play a vital role in fulfilling the system's quality of service. Due to time pressure, architects often model only one architecture based on their known limited domain understanding, patterns, and experience instead of thoroughly analyzing the domain and evaluating multiple candidates, selecting the best fitting. Existing approaches try to generate domain models based on requirements, but still require time-consuming manual effort to achieve good results. Therefore, in this vision paper, we propose a method to generate software architecture candidates semi-automatically based on requirements using artificial intelligence techniques. We further envision an automatic evaluation and trade-off analysis of the generated architecture candidates using, e.g., the architecture trade-off analysis method combined with large language models and quantitative analyses. To evaluate this approach, we aim to analyze the quality of the generated architecture models and the efficiency and effectiveness of our proposed process by conducting qualitative studies.

This paper presents GeoDecoder, a dedicated multimodal model designed for processing geospatial information in maps. Built on the BeitGPT architecture, GeoDecoder incorporates specialized expert modules for image and text processing. On the image side, GeoDecoder utilizes GaoDe Amap as the underlying base map, which inherently encompasses essential details about road and building shapes, relative positions, and other attributes. Through the utilization of rendering techniques, the model seamlessly integrates external data and features such as symbol markers, drive trajectories, heatmaps, and user-defined markers, eliminating the need for extra feature engineering. The text module of GeoDecoder accepts various context texts and question prompts, generating text outputs in the style of GPT. Furthermore, the GPT-based model allows for the training and execution of multiple tasks within the same model in an end-to-end manner. To enhance map cognition and enable GeoDecoder to acquire knowledge about the distribution of geographic entities in Beijing, we devised eight fundamental geospatial tasks and conducted pretraining of the model using large-scale text-image samples. Subsequently, rapid fine-tuning was performed on three downstream tasks, resulting in significant performance improvements. The GeoDecoder model demonstrates a comprehensive understanding of map elements and their associated operations, enabling efficient and high-quality application of diverse geospatial tasks in different business scenarios.

As a fundamental task in computational chemistry, retrosynthesis prediction aims to identify a set of reactants to synthesize a target molecule. Existing template-free approaches only consider the graph structures of the target molecule, which often cannot generalize well to rare reaction types and large molecules. Here, we propose T-Rex, a text-assisted retrosynthesis prediction approach that exploits pre-trained text language models, such as ChatGPT, to assist the generation of reactants. T-Rex first exploits ChatGPT to generate a description for the target molecule and rank candidate reaction centers based both the description and the molecular graph. It then re-ranks these candidates by querying the descriptions for each reactants and examines which group of reactants can best synthesize the target molecule. We observed that T-Rex substantially outperformed graph-based state-of-the-art approaches on two datasets, indicating the effectiveness of considering text information. We further found that T-Rex outperformed the variant that only use ChatGPT-based description without the re-ranking step, demonstrate how our framework outperformed a straightforward integration of ChatGPT and graph information. Collectively, we show that text generated by pre-trained language models can substantially improve retrosynthesis prediction, opening up new avenues for exploiting ChatGPT to advance computational chemistry. And the codes can be found at https://github.com/lauyikfung/T-Rex.

Chinese Spelling Check (CSC) is a meaningful task in the area of Natural Language Processing (NLP) which aims at detecting spelling errors in Chinese texts and then correcting these errors. However, CSC models are based on pretrained language models, which are trained on a general corpus. Consequently, their performance may drop when confronted with downstream tasks involving domain-specific terms. In this paper, we conduct a thorough evaluation about the domain adaption ability of various typical CSC models by building three new datasets encompassing rich domain-specific terms from the financial, medical, and legal domains. Then we conduct empirical investigations in the corresponding domain-specific test datasets to ascertain the cross-domain adaptation ability of several typical CSC models. We also test the performance of the popular large language model ChatGPT. As shown in our experiments, the performances of the CSC models drop significantly in the new domains.

Large language models have demonstrated remarkable potential in various tasks, however, there remains a significant scarcity of open-source models and data for specific domains. Previous works have primarily focused on manually specifying resources and collecting high-quality data on specific domains, which significantly consume time and effort. To address this limitation, we propose an efficient data collection method~\textit{Query of CC} based on large language models. This method bootstraps seed information through a large language model and retrieves related data from public corpora. It not only collects knowledge-related data for specific domains but unearths the data with potential reasoning procedures. Through the application of this method, we have curated a high-quality dataset called~\textsc{Knowledge Pile}, encompassing four major domains, including stem and humanities sciences, among others. Experimental results demonstrate that~\textsc{Knowledge Pile} significantly improves the performance of large language models in mathematical and knowledge-related reasoning ability tests. To facilitate academic sharing, we open-source our dataset and code, providing valuable support to the academic community.

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved significant progress in the area of domain adaptation. However, in-domain data scarcity is common in translation settings, due to the lack of specialised datasets and terminology, or inconsistency and inaccuracy of available in-domain translations. In such scenarios where there is insufficient in-domain data to fine-tune MT models, producing translations that are consistent with the relevant context is challenging. While real-time adaptation can make use of smaller amounts of in-domain data to improve the translation on the fly, it remains challenging due to supported context limitations and efficiency constraints. Large language models (LLMs) have recently shown interesting capabilities of in-context learning, where they learn to replicate certain input-output text generation patterns, without further fine-tuning. Such capabilities have opened new horizons for domain-specific data augmentation and real-time adaptive MT. This work attempts to address two main relevant questions: 1) in scenarios involving human interaction and continuous feedback, can we employ language models to improve the quality of adaptive MT at inference time? and 2) in the absence of sufficient in-domain data, can we use pre-trained large-scale language models to improve the process of MT domain adaptation?