Large language models (LLMs) are a transformational capability at the frontier of artificial intelligence and machine learning that can support decision-makers in addressing pressing societal challenges such as extreme natural hazard events. As generalized models, LLMs often struggle to provide context-specific information, particularly in areas requiring specialized knowledge. In this work, we propose a Retrieval-Augmented Generation (RAG)-based multi-agent LLM system to support analysis and decision-making in the context of natural hazards and extreme weather events. As a proof of concept, we present WildfireGPT, a specialized system focused on wildfire scenarios. The architecture employs a user-centered, multi-agent design to deliver tailored risk insights across diverse stakeholder groups. By integrating domain-specific projection data, observational datasets, and scientific literature through a RAG framework, the system ensures both accuracy and contextual relevance of the information it provides. Evaluation across ten expert-led case studies demonstrates that WildfireGPT significantly outperforms existing LLM-based solutions for decision support in natural hazard and extreme weather contexts.
Chunking information is a key step in Retrieval Augmented Generation (RAG). Current research primarily centers on paragraph-level chunking. This approach treats all texts as equal and neglects the information contained in the structure of documents. We propose an expanded approach to chunk documents by moving beyond mere paragraph-level chunking to chunk primary by structural element components of documents. Dissecting documents into these constituent elements creates a new way to chunk documents that yields the best chunk size without tuning. We introduce a novel framework that evaluates how chunking based on element types annotated by document understanding models contributes to the overall context and accuracy of the information retrieved. We also demonstrate how this approach impacts RAG assisted Question & Answer task performance. Our research includes a comprehensive analysis of various element types, their role in effective information retrieval, and the impact they have on the quality of RAG outputs. Findings support that element type based chunking largely improve RAG results on financial reporting. Through this research, we are also able to answer how to uncover highly accurate RAG.
Textbook question answering (TQA) is a challenging task in artificial intelligence due to the complex nature of context needed to answer complex questions. Although previous research has improved the task, there are still some limitations in textual TQA, including weak reasoning and inability to capture contextual information in the lengthy context. We propose a framework (PLRTQA) that incorporates the retrieval augmented generation (RAG) technique to handle the out-of-domain scenario where concepts are spread across different lessons, and utilize transfer learning to handle the long context and enhance reasoning abilities. Our architecture outperforms the baseline, achieving an accuracy improvement of 4. 12% in the validation set and 9. 84% in the test set for textual multiple-choice questions. While this paper focuses on solving challenges in the textual TQA, It provides a foundation for future work in multimodal TQA where the visual components are integrated to address more complex educational scenarios. Code: https://github.com/hessaAlawwad/PLR-TQA
Infineon has identified a need for engineers, account managers, and customers to rapidly obtain product information. This problem is traditionally addressed with retrieval-augmented generation (RAG) chatbots, but in this study, I evaluated the use of the newly popularized RAG-Fusion method. RAG-Fusion combines RAG and reciprocal rank fusion (RRF) by generating multiple queries, reranking them with reciprocal scores and fusing the documents and scores. Through manually evaluating answers on accuracy, relevance, and comprehensiveness, I found that RAG-Fusion was able to provide accurate and comprehensive answers due to the generated queries contextualizing the original query from various perspectives. However, some answers strayed off topic when the generated queries' relevance to the original query is insufficient. This research marks significant progress in artificial intelligence (AI) and natural language processing (NLP) applications and demonstrates transformations in a global and multi-industry context.
Importance: We introduce a novel Retrieval Augmented Generation (RAG)-Large Language Model (LLM) framework as a Clinical Decision Support Systems (CDSS) to support safe medication prescription. Objective: To evaluate the efficacy of LLM-based CDSS in correctly identifying medication errors in different patient case vignettes from diverse medical and surgical sub-disciplines, against a human expert panel derived ground truth. We compared performance for under 2 different CDSS practical healthcare integration modalities: LLM-based CDSS alone (fully autonomous mode) vs junior pharmacist + LLM-based CDSS (co-pilot, assistive mode). Design, Setting, and Participants: Utilizing a RAG model with state-of-the-art medically-related LLMs (GPT-4, Gemini Pro 1.0 and Med-PaLM 2), this study used 61 prescribing error scenarios embedded into 23 complex clinical vignettes across 12 different medical and surgical specialties. A multidisciplinary expert panel assessed these cases for Drug-Related Problems (DRPs) using the PCNE classification and graded severity / potential for harm using revised NCC MERP medication error index. We compared. Results RAG-LLM performed better compared to LLM alone. When employed in a co-pilot mode, accuracy, recall, and F1 scores were optimized, indicating effectiveness in identifying moderate to severe DRPs. The accuracy of DRP detection with RAG-LLM improved in several categories but at the expense of lower precision. Conclusions This study established that a RAG-LLM based CDSS significantly boosts the accuracy of medication error identification when used alongside junior pharmacists (co-pilot), with notable improvements in detecting severe DRPs. This study also illuminates the comparative performance of current state-of-the-art LLMs in RAG-based CDSS systems.
Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges, a fine-tuning process is employed, involving feedback and examples to refine models. The objective is to enhance AI models through continuous feedback loops, utilizing metrics such as cosine similarity, LLM evaluation and Rouge-L scores to evaluate the models. Leveraging LLMs like GPT-3.5, GPT4ALL, and LLaMA2, and Claude, this approach is benchmarked on financial datasets, including the FinanceBench and RAG Instruct Benchmark Tester Dataset, illustrating the necessity of fine-tuning. The results showcase the capability of fine-tuned models to surpass the accuracy of zero-shot LLMs, providing superior question and answering capabilities. Notably, the combination of fine-tuning the LLM with a process known as Retrieval Augmented Generation (RAG) proves to generate responses with improved accuracy.
Regulatory compliance in the pharmaceutical industry entails navigating through complex and voluminous guidelines, often requiring significant human resources. To address these challenges, our study introduces a chatbot model that utilizes generative AI and the Retrieval Augmented Generation (RAG) method. This chatbot is designed to search for guideline documents relevant to the user inquiries and provide answers based on the retrieved guidelines. Recognizing the inherent need for high reliability in this domain, we propose the Question and Answer Retrieval Augmented Generation (QA-RAG) model. In comparative experiments, the QA-RAG model demonstrated a significant improvement in accuracy, outperforming all other baselines including conventional RAG methods. This paper details QA-RAG's structure and performance evaluation, emphasizing its potential for the regulatory compliance domain in the pharmaceutical industry and beyond. We have made our work publicly available for further research and development.
Retrieving the most similar vector embeddings to a given query among a massive collection of vectors has long been a key component of countless real-world applications. The recently introduced Retrieval-Augmented Generation is one of the most prominent examples. For many of these applications, the database evolves over time by inserting new data and removing outdated data. In these cases, the retrieval problem is known as streaming similarity search. While Locally-Adaptive Vector Quantization (LVQ), a highly efficient vector compression method, yields state-of-the-art search performance for non-evolving databases, its usefulness in the streaming setting has not been yet established. In this work, we study LVQ in streaming similarity search. In support of our evaluation, we introduce two improvements of LVQ: Turbo LVQ and multi-means LVQ that boost its search performance by up to 28% and 27%, respectively. Our studies show that LVQ and its new variants enable blazing fast vector search, outperforming its closest competitor by up to 9.4x for identically distributed data and by up to 8.8x under the challenging scenario of data distribution shifts (i.e., where the statistical distribution of the data changes over time). We release our contributions as part of Scalable Vector Search, an open-source library for high-performance similarity search.
Large language models (LLMs) and foundation models have been recently touted as a game-changer for 6G systems. However, recent efforts on LLMs for wireless networks are limited to a direct application of existing language models that were designed for natural language processing (NLP) applications. To address this challenge and create wireless-centric foundation models, this paper presents a comprehensive vision on how to design universal foundation models that are tailored towards the deployment of artificial intelligence (AI)-native networks. Diverging from NLP-based foundation models, the proposed framework promotes the design of large multi-modal models (LMMs) fostered by three key capabilities: 1) processing of multi-modal sensing data, 2) grounding of physical symbol representations in real-world wireless systems using causal reasoning and retrieval-augmented generation (RAG), and 3) enabling instructibility from the wireless environment feedback to facilitate dynamic network adaptation thanks to logical and mathematical reasoning facilitated by neuro-symbolic AI. In essence, these properties enable the proposed LMM framework to build universal capabilities that cater to various cross-layer networking tasks and alignment of intents across different domains. Preliminary results from experimental evaluation demonstrate the efficacy of grounding using RAG in LMMs, and showcase the alignment of LMMs with wireless system designs. Furthermore, the enhanced rationale exhibited in the responses to mathematical questions by LMMs, compared to vanilla LLMs, demonstrates the logical and mathematical reasoning capabilities inherent in LMMs. Building on those results, we present a sequel of open questions and challenges for LMMs. We then conclude with a set of recommendations that ignite the path towards LMM-empowered AI-native systems.
Purpose: Large Language Models (LLMs) hold significant promise for medical applications. Retrieval Augmented Generation (RAG) emerges as a promising approach for customizing domain knowledge in LLMs. This case study presents the development and evaluation of an LLM-RAG pipeline tailored for healthcare, focusing specifically on preoperative medicine. Methods: We developed an LLM-RAG model using 35 preoperative guidelines and tested it against human-generated responses, with a total of 1260 responses evaluated. The RAG process involved converting clinical documents into text using Python-based frameworks like LangChain and Llamaindex, and processing these texts into chunks for embedding and retrieval. Vector storage techniques and selected embedding models to optimize data retrieval, using Pinecone for vector storage with a dimensionality of 1536 and cosine similarity for loss metrics. Human-generated answers, provided by junior doctors, were used as a comparison. Results: The LLM-RAG model generated answers within an average of 15-20 seconds, significantly faster than the 10 minutes typically required by humans. Among the basic LLMs, GPT4.0 exhibited the best accuracy of 80.1%. This accuracy was further increased to 91.4% when the model was enhanced with RAG. Compared to the human-generated instructions, which had an accuracy of 86.3%, the performance of the GPT4.0 RAG model demonstrated non-inferiority (p=0.610). Conclusions: In this case study, we demonstrated a LLM-RAG model for healthcare implementation. The pipeline shows the advantages of grounded knowledge, upgradability, and scalability as important aspects of healthcare LLM deployment.
In this work, we present a comprehensive exploration of finetuning Malaysian language models, specifically Llama2 and Mistral, on embedding tasks involving negative and positive pairs. We release two distinct models tailored for Semantic Similarity and Retrieval-Augmented Generation (RAG). For Semantic Similarity, our 600 million parameter Llama2 model outperforms OpenAI text-embedding-ada-002 across all recall@k metrics for b.cari.com.my, c.cari.com.my, Malay news, and Malaysian Twitter test sets. In the realm of RAG models, our approach proves competitive with OpenAI text-embedding-ada-002 in the Malaysian context. Notably, our 2 billion parameter Llama2 model achieves superior Recall@5, Recall@10 for the "Melayu" keyword research papers dataset and excels in Recall@3, Recall@5, and Recall@10 for the lom.agc.gov.my dataset. These findings underscore the effectiveness of our finetuning strategy and highlight the performance gains in both Semantic Similarity and RAG tasks. All models released at https://huggingface.co/collections/mesolitica/malaysian-embedding-6523612bfe5881ad35f81b99
Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work. It is a tedious task which makes an automatic literature review generator appealing. Unfortunately, many existing works that generate such reviews using Large Language Models (LLMs) have significant limitations. They tend to hallucinate-generate non-factual information-and ignore the latest research they have not been trained on. To address these limitations, we propose a toolkit that operates on Retrieval Augmented Generation (RAG) principles, specialized prompting and instructing techniques with the help of LLMs. Our system first initiates a web search to retrieve relevant papers by summarizing user-provided abstracts into keywords using an off-the-shelf LLM. Authors can enhance the search by supplementing it with relevant papers or keywords, contributing to a tailored retrieval process. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Finally, the related work section is generated based on the re-ranked results and the abstract. There is a substantial reduction in time and effort for literature review compared to traditional methods, establishing our toolkit as an efficient alternative. Our project page including the demo and toolkit can be accessed here: https://litllm.github.io
Large language models (LLMs) are currently being used to answer medical questions across a variety of clinical domains. Recent top-performing commercial LLMs, in particular, are also capable of citing sources to support their responses. In this paper, we ask: do the sources that LLMs generate actually support the claims that they make? To answer this, we propose three contributions. First, as expert medical annotations are an expensive and time-consuming bottleneck for scalable evaluation, we demonstrate that GPT-4 is highly accurate in validating source relevance, agreeing 88% of the time with a panel of medical doctors. Second, we develop an end-to-end, automated pipeline called \textit{SourceCheckup} and use it to evaluate five top-performing LLMs on a dataset of 1200 generated questions, totaling over 40K pairs of statements and sources. Interestingly, we find that between ~50% to 90% of LLM responses are not fully supported by the sources they provide. We also evaluate GPT-4 with retrieval augmented generation (RAG) and find that, even still, around 30\% of individual statements are unsupported, while nearly half of its responses are not fully supported. Third, we open-source our curated dataset of medical questions and expert annotations for future evaluations. Given the rapid pace of LLM development and the potential harms of incorrect or outdated medical information, it is crucial to also understand and quantify their capability to produce relevant, trustworthy medical references.
We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this paper, we apply SLM to speech dialog applications where the dialog states are inferred directly from the audio signal. Task-oriented dialogs often contain domain-specific entities, i.e., restaurants, hotels, train stations, and city names, which are difficult to recognize, however, critical for the downstream applications. Inspired by the RAG (retrieval-augmented generation) paradigm, we propose a retrieval augmented SLM (ReSLM) that overcomes this weakness. We first train a speech retriever to retrieve text entities mentioned in the audio. The retrieved entities are then added as text inputs to the underlying SLM to bias model predictions. We evaluated ReSLM on speech MultiWoz task (DSTC-11 challenge), and found that this retrieval augmentation boosts model performance, achieving joint goal accuracy (38.6% vs 32.7%), slot error rate (20.6% vs 24.8%) and ASR word error rate (5.5% vs 6.7%). While demonstrated on dialog state tracking, our approach is broadly applicable to other speech tasks requiring contextual information or domain-specific entities, such as contextual ASR with biasing capability.
The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval aims to capture the list-level contextual features to return a better list, mainly including reranking and truncation. Reranking finely re-scores the documents in the list. Truncation dynamically determines the cut-off point of the ranked list to achieve the trade-off between overall relevance and avoiding misinformation from irrelevant documents. Previous studies treat them as two separate tasks and model them separately. However, the separation is not optimal. First, it is hard to share the contextual information of the ranking list between the two tasks. Second, the separate pipeline usually meets the error accumulation problem, where the small error from the reranking stage can largely affect the truncation stage. To solve these problems, we propose a Reranking-Truncation joint model (GenRT) that can perform the two tasks concurrently. GenRT integrates reranking and truncation via generative paradigm based on encoder-decoder architecture. We also design the novel loss functions for joint optimization to make the model learn both tasks. Sharing parameters by the joint model is conducive to making full use of the common modeling information of the two tasks. Besides, the two tasks are performed concurrently and co-optimized to solve the error accumulation problem between separate stages. Experiments on public learning-to-rank benchmarks and open-domain Q\&A tasks show that our method achieves SOTA performance on both reranking and truncation tasks for web search and retrieval-augmented LLMs.
Large language models (LLMs) have gained significant attention in various fields but prone to hallucination, especially in knowledge-intensive (KI) tasks. To address this, retrieval-augmented generation (RAG) has emerged as a popular solution to enhance factual accuracy. However, traditional retrieval modules often rely on large document index and disconnect with generative tasks. With the advent of generative retrieval (GR), language models can retrieve by directly generating document identifiers (DocIDs), offering superior performance in retrieval tasks. However, the potential relationship between GR and downstream tasks remains unexplored. In this paper, we propose \textbf{CorpusLM}, a unified language model that leverages external corpus to tackle various knowledge-intensive tasks by integrating generative retrieval, closed-book generation, and RAG through a unified greedy decoding process. We design the following mechanisms to facilitate effective retrieval and generation, and improve the end-to-end effectiveness of KI tasks: (1) We develop a ranking-oriented DocID list generation strategy, which refines GR by directly learning from a DocID ranking list, to improve retrieval quality. (2) We design a continuous DocIDs-References-Answer generation strategy, which facilitates effective and efficient RAG. (3) We employ well-designed unsupervised DocID understanding tasks, to comprehend DocID semantics and their relevance to downstream tasks. We evaluate our approach on the widely used KILT benchmark with two variants of backbone models, i.e., T5 and Llama2. Experimental results demonstrate the superior performance of our models in both retrieval and downstream tasks.
Large language models (LLMs) are not amenable to frequent re-training, due to high training costs arising from their massive scale. However, updates are necessary to endow LLMs with new skills and keep them up-to-date with rapidly evolving human knowledge. This paper surveys recent works on continual learning for LLMs. Due to the unique nature of LLMs, we catalog continue learning techniques in a novel multi-staged categorization scheme, involving continual pretraining, instruction tuning, and alignment. We contrast continual learning for LLMs with simpler adaptation methods used in smaller models, as well as with other enhancement strategies like retrieval-augmented generation and model editing. Moreover, informed by a discussion of benchmarks and evaluation, we identify several challenges and future work directions for this crucial task.
Recent advancements in artificial intelligence (AI), especially large language models (LLMs), have significantly advanced healthcare applications and demonstrated potentials in intelligent medical treatment. However, there are conspicuous challenges such as vast data volumes and inconsistent symptom characterization standards, preventing full integration of healthcare AI systems with individual patients' needs. To promote professional and personalized healthcare, we propose an innovative framework, Heath-LLM, which combines large-scale feature extraction and medical knowledge trade-off scoring. Compared to traditional health management applications, our system has three main advantages: (1) It integrates health reports and medical knowledge into a large model to ask relevant questions to large language model for disease prediction; (2) It leverages a retrieval augmented generation (RAG) mechanism to enhance feature extraction; (3) It incorporates a semi-automated feature updating framework that can merge and delete features to improve accuracy of disease prediction. We experiment on a large number of health reports to assess the effectiveness of Health-LLM system. The results indicate that the proposed system surpasses the existing ones and has the potential to significantly advance disease prediction and personalized health management.
Federated search, which involves integrating results from multiple independent search engines, will become increasingly pivotal in the context of Retrieval-Augmented Generation pipelines empowering LLM-based applications such as chatbots. These systems often distribute queries among various search engines, ranging from specialized (e.g., PubMed) to general (e.g., Google), based on the nature of user utterances. A critical aspect of federated search is resource selection - the selection of appropriate resources prior to issuing the query to ensure high-quality and rapid responses, and contain costs associated with calling the external search engines. However, current SOTA resource selection methodologies primarily rely on feature-based learning approaches. These methods often involve the labour intensive and expensive creation of training labels for each resource. In contrast, LLMs have exhibited strong effectiveness as zero-shot methods across NLP and IR tasks. We hypothesise that in the context of federated search LLMs can assess the relevance of resources without the need for extensive predefined labels or features. In this paper, we propose ReSLLM. Our ReSLLM method exploits LLMs to drive the selection of resources in federated search in a zero-shot setting. In addition, we devise an unsupervised fine tuning protocol, the Synthetic Label Augmentation Tuning (SLAT), where the relevance of previously logged queries and snippets from resources is predicted using an off-the-shelf LLM and then in turn used to fine-tune ReSLLM with respect to resource selection. Our empirical evaluation and analysis details the factors influencing the effectiveness of LLMs in this context. The results showcase the merits of ReSLLM for resource selection: not only competitive effectiveness in the zero-shot setting, but also obtaining large when fine-tuned using SLAT-protocol.
Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and the tendency to produce inaccurate "hallucinated" content. However, the evaluation of RAG systems is challenging, as existing benchmarks are limited in scope and diversity. Most of the current benchmarks predominantly assess question-answering applications, overlooking the broader spectrum of situations where RAG could prove advantageous. Moreover, they only evaluate the performance of the LLM component of the RAG pipeline in the experiments, and neglect the influence of the retrieval component and the external knowledge database. To address these issues, this paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios. Specifically, we have categorized the range of RAG applications into four distinct types-Create, Read, Update, and Delete (CRUD), each representing a unique use case. "Create" refers to scenarios requiring the generation of original, varied content. "Read" involves responding to intricate questions in knowledge-intensive situations. "Update" focuses on revising and rectifying inaccuracies or inconsistencies in pre-existing texts. "Delete" pertains to the task of summarizing extensive texts into more concise forms. For each of these CRUD categories, we have developed comprehensive datasets to evaluate the performance of RAG systems. We also analyze the effects of various components of the RAG system, such as the retriever, the context length, the knowledge base construction, and the LLM. Finally, we provide useful insights for optimizing the RAG technology for different scenarios.