This demo paper presents ImmiGo, an adaptive multilingual chatbot designed to effectively address user needs by providing accurate and timely responses to visa and immigration inquiries in users’ preferred languages. A system supporting such important inquiries relies on being up-to-date and accurate. To this end, ImmiGo is built on a sophisticated agentic Retrieval-Augmented Generation (RAG) pipeline, seamlessly integrating the Groq-accelerated OpenAI GPT-OSS-120B model for faster inference. The system also incorporates an advanced embedding model and a dynamic storage mechanism, leveraging a vector database to ensure efficient real-time retrieval, contextual accuracy, and robust handling of out-of-knowledge-base queries. Additionally, an ensemble document retrieval method and composite grading mechanism refine response quality by filtering less relevant context, ensuring that the language model generates precise, reliable, and factually accurate responses. The system underwent rigorous evaluation and testing for its multi-turn, multilingual, and conversational capabilities, demonstrating its ability to perform consistently across multiple scenarios.

Textual descriptions for multimodal inputs entail recurrent refinement of queries to produce relevant output images. Despite efforts to address challenges such as scaling model size and data volume, the cost associated with pre-training and fine-tuning remains substantial. However, pre-trained large multimodal models (LMMs) encounter a modality gap, characterised by a misalignment between textual and visual representations within a common embedding space. Although fine-tuning can potentially mitigate this gap, it is typically expensive and impractical due to the requirement for extensive domain-driven data. To overcome this challenge, we propose a lightweight training-free approach utilising Retrieval-Augmented Generation (RAG) to extend across the modality using a linear mapping, which can be computed efficiently. Our reproducible code can be found in https://github.com/amitkumarj441/mRAG-gim. During inference, this mapping is applied to images embedded by an LMM enabling retrieval of closest textual descriptions from the training set. These textual descriptions, in conjunction with an instruction, cater as an input prompt for the language model to generate new textual descriptions. In addition, we introduce an iterative technique for distilling the mapping by generating synthetic descriptions via the language model facilitating optimisation for standard utilised image description measures. Experimental results on two benchmark multimodal datasets demonstrate significant improvements.

Abstract The goal of information extraction is to extract structural knowledge (such as entities, relations and events) from plain and unstructured texts. Information extraction in legal documents has recently gained a lot of attention in the natural language processing (NLP) community due to the high demand for efficient information extraction for legal practitioners and companies. Given that the legal documents are unique and their processing is challenging, there is a pressing need for applications of NLP techniques to tackle these challenges. In this research, we present a survey on the recent advancements in legal information extraction focusing on three tasks: named entity recognition, relationship extraction and event detection. We report language resources and systems in multiple jurisdictions and languages for each task. Based on the thorough review conducted, we identify insights into the techniques employed and promising research directions that merit further exploration in future studies. We maintain a public repository and consistently update related resources at https://github.com/DamithDR/legalinformationextraction .

This demo paper presents JayBot, an LLM-based chatbot system aimed at enhancing the user experience of prospective and current students, faculty, and staff at a UK university. The objective of JayBot is to provide information to users on general enquiries regarding course modules, duration, fees, entry requirements, lecturers, internship, career paths, course employability and other related aspects. Leveraging the use cases of generative artificial intelligence (AI), the chatbot application was built using OpenAI’s advanced large language model (GPT-3.5 turbo); to tackle issues such as hallucination as well as focus and timeliness of results, an embedding transformer model has been combined with a vector database and vector search. Prompt engineering techniques were employed to enhance the chatbot’s response abilities. Preliminary user studies indicate JayBot’s effectiveness and efficiency. The demo will showcase JayBot in a university admission use case and discuss further application scenarios.

No abstract available.

The BIRDS workshop aimed to foster the cross-fertilization of Information Science (IS), Information Retrieval (IR) and Data Science (DS). Recognising the commonalities and differences between these communities, the proposed full-day workshop brought together experts and researchers in IS, IR and DS to discuss how they can learn from each other to provide more user-driven data and infor- mation exploration and retrieval solutions. Therefore, the papers aimed to convey ideas on how to utilise, for instance, IS concepts and theories in DS and IR or DS approaches to support users in data and information exploration.

Books only represented by brief metadata (book records) are particularly hard to retrieve. One way of improving their retrieval is by extracting retrieval enhancing features from them. This work focusses on scientific (physics) book records. We ask if their technical terminology can be used as a retrieval enhancing feature. A study of 18,443 book records shows a strong correlation between their technical terminology and their likelihood of relevance. Using this finding for retrieval yields >+5% precision and recall gains.

The probabilistic formalism of quantum physics is said to provide a sound basis for building a principled information retrieval framework. Such a framework can be based on the notion of information need vector spaces where events, such as document relevance or observed user interactions, correspond to subspaces. As in quantum theory, a probability distribution over these subspaces is defined through weighted sets of state vectors (density operators), and used to represent the current view of the retrieval system on the user information need. Tensor spaces can be used to capture different aspects of information needs. Our evaluation shows that the framework can lead to acceptable performance in an ad-hoc retrieval task. Going beyond this, we discuss the potential of the framework for three active challenges in information retrieval, namely, interaction, novelty and diversity.