Rare diseases present unique challenges in healthcare, often suffering from delayed diagnosis and fragmented information landscapes. The scarcity of reliable knowledge in these conditions poses a distinct challenge for Large Language Models (LLMs) in supporting clinical management and delivering precise patient information underscoring the need for focused training on these 'zebra' cases. We present Zebra-Llama, a specialized context-aware language model with high precision Retrieval Augmented Generation (RAG) capability, focusing on Ehlers-Danlos Syndrome (EDS) as our case study. EDS, affecting 1 in 5,000 individuals, exemplifies the complexities of rare diseases with its diverse symptoms, multiple subtypes, and evolving diagnostic criteria. By implementing a novel context-aware fine-tuning methodology trained on questions derived from medical literature, patient experiences, and clinical resources, along with expertly curated responses, Zebra-Llama demonstrates unprecedented capabilities in handling EDS-related queries. On a test set of real-world questions collected from EDS patients and clinicians, medical experts evaluated the responses generated by both models, revealing Zebra-Llama's substantial improvements over base model (Llama 3.1-8B-Instruct) in thoroughness (77.5% vs. 70.1%), accuracy (83.0% vs. 78.8%), clarity (74.7% vs. 72.0%) and citation reliability (70.6% vs. 52.3%). Released as an open-source resource, Zebra-Llama not only provides more accessible and reliable EDS information but also establishes a framework for developing specialized AI solutions for other rare conditions. This work represents a crucial step towards democratizing expert-level knowledge in rare disease management, potentially transforming how healthcare providers and patients navigate the complex landscape of rare diseases.
Large language models (LLMs) excel in tasks requiring processing and interpretation of input text. Abstract screening is a labour-intensive component of systematic review involving repetitive application of inclusion and exclusion criteria on a large volume of studies identified by a literature search. Here, LLMs (GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, Llama 3 70B, Gemini 1.5 Pro, and Claude Sonnet 3.5) were trialled on systematic reviews in a full issue of the Cochrane Library to evaluate their accuracy in zero-shot binary classification for abstract screening. Trials over a subset of 800 records identified optimal prompting strategies and demonstrated superior performance of LLMs to human researchers in terms of sensitivity (LLM-max = 1.000, human-max = 0.775), precision (LLM-max = 0.927, human-max = 0.911), and balanced accuracy (LLM-max = 0.904, human-max = 0.865). The best performing LLM-prompt combinations were trialled across every replicated search result (n = 119,691), and exhibited consistent sensitivity (range 0.756-1.000) but diminished precision (range 0.004-0.096). 66 LLM-human and LLM-LLM ensembles exhibited perfect sensitivity with a maximal precision of 0.458, with less observed performance drop in larger trials. Significant variation in performance was observed between reviews, highlighting the importance of domain-specific validation before deployment. LLMs may reduce the human labour cost of systematic review with maintained or improved accuracy and sensitivity. Systematic review is the foundation of evidence synthesis across academic disciplines, including evidence-based medicine, and LLMs may increase the efficiency and quality of this mode of research.
In recent years, advanced artificial intelligence technologies, such as ChatGPT, have significantly impacted various fields, including education and research. Developed by OpenAI, ChatGPT is a powerful language model that presents numerous opportunities for students and educators. It offers personalized feedback, enhances accessibility, enables interactive conversations, assists with lesson preparation and evaluation, and introduces new methods for teaching complex subjects. However, ChatGPT also poses challenges to traditional education and research systems. These challenges include the risk of cheating on online exams, the generation of human-like text that may compromise academic integrity, a potential decline in critical thinking skills, and difficulties in assessing the reliability of information generated by AI. This study examines both the opportunities and challenges ChatGPT brings to education from the perspectives of students and educators. Specifically, it explores the role of ChatGPT in helping students develop their subjective skills. To demonstrate its effectiveness, we conducted several subjective experiments using ChatGPT, such as generating solutions from subjective problem descriptions. Additionally, surveys were conducted with students and teachers to gather insights into how ChatGPT supports subjective learning and teaching. The results and analysis of these surveys are presented to highlight the impact of ChatGPT in this context.
Human-scene vision-language tasks are increasingly prevalent in diverse social applications, yet recent advancements predominantly rely on models specifically tailored to individual tasks. Emerging research indicates that large vision-language models (VLMs) can enhance performance across various downstream vision-language understanding tasks. However, general-domain models often underperform in specialized fields. This study introduces a domain-specific Large Vision-Language Model, Human-Scene Vision-Language Model (HumanVLM), designed to provide a foundation for human-scene Vision-Language tasks. Specifically, (1) we create a large-scale human-scene multimodal image-text dataset (HumanCaption-10M) sourced from the Internet to facilitate domain-specific alignment; (2) develop a captioning approach for human-centered images, capturing human faces, bodies, and backgrounds, and construct a high-quality Human-Scene image-text dataset (HumanCaptionHQ, about 311k pairs) that contain as much detailed information as possible about human; (3) Using HumanCaption-10M and HumanCaptionHQ, we train a HumanVLM. In the experiments, we then evaluate our HumanVLM across varous downstream tasks, where it demonstrates superior overall performance among multimodal models of comparable scale, particularly excelling in human-related tasks and significantly outperforming similar models, including Qwen2VL and ChatGPT-4o. HumanVLM, alongside the data introduced, will stimulate the research in human-around fields.
Causal understanding is a fundamental goal of evidence-based medicine. When randomization is impossible, causal inference methods allow the estimation of treatment effects from retrospective analysis of observational data. However, such analyses rely on a number of assumptions, often including that of no unobserved confounding. In many practical settings, this assumption is violated when important variables are not explicitly measured in the clinical record. Prior work has proposed to address unobserved confounding with machine learning by imputing unobserved variables and then correcting for the classifier's mismeasurement. When such a classifier can be trained and the necessary assumptions are met, this method can recover an unbiased estimate of a causal effect. However, such work has been limited to synthetic data, simple classifiers, and binary variables. This paper extends this methodology by using a large language model trained on clinical notes to predict patients' smoking status, which would otherwise be an unobserved confounder. We then apply a measurement error correction on the categorical predicted smoking status to estimate the causal effect of transthoracic echocardiography on mortality in the MIMIC dataset.
We present an outline of the first large language model (LLM) based chatbot application in the context of patient-reported outcome measures (PROMs) for diabetic retinopathy. By utilizing the capabilities of current LLMs, we enable patients to provide feedback about their quality of life and treatment progress via an interactive application. The proposed framework offers significant advantages over the current approach, which encompasses only qualitative collection of survey data or a static survey with limited answer options. Using the PROBot LLM-PROM application, patients will be asked tailored questions about their individual challenges, and can give more detailed feedback on the progress of their treatment. Based on this input, we will use machine learning to infer conventional PROM scores, which can be used by clinicians to evaluate the treatment status. The goal of the application is to improve adherence to the healthcare system and treatments, and thus ultimately reduce cases of subsequent vision impairment. The approach needs to be further validated using a survey and a clinical study.
Retrieval augmented generation (RAG) models, which integrate large-scale pre-trained generative models with external retrieval mechanisms, have shown significant success in various natural language processing (NLP) tasks. However, applying RAG models in Persian language as a low-resource language, poses distinct challenges. These challenges primarily involve the preprocessing, embedding, retrieval, prompt construction, language modeling, and response evaluation of the system. In this paper, we address the challenges towards implementing a real-world RAG system for Persian language called PersianRAG. We propose novel solutions to overcome these obstacles and evaluate our approach using several Persian benchmark datasets. Our experimental results demonstrate the capability of the PersianRAG framework to enhance question answering task in Persian.
This paper reviews the development of the Receptance Weighted Key Value (RWKV) architecture, emphasizing its advancements in efficient language modeling. RWKV combines the training efficiency of Transformers with the inference efficiency of RNNs through a novel linear attention mechanism. We examine its core innovations, adaptations across various domains, and performance advantages over traditional models. The paper also discusses challenges and future directions for RWKV as a versatile architecture in deep learning.
Large vision-language models (LVLMs) suffer from hallucination, resulting in misalignment between the output textual response and the input visual content. Recent research indicates that the over-reliance on the Large Language Model (LLM) backbone, as one cause of the LVLM hallucination, inherently introduces bias from language priors, leading to insufficient context attention to the visual inputs. We tackle this issue of hallucination by mitigating such over-reliance through preference learning. We propose Vision-guided Direct Preference Optimization (V-DPO) to enhance visual context learning at training time. To interpret the effectiveness and generalizability of V-DPO on different types of training data, we construct a synthetic dataset containing both response- and image-contrast preference pairs, compared against existing human-annotated hallucination samples. Our approach achieves significant improvements compared with baseline methods across various hallucination benchmarks. Our analysis indicates that V-DPO excels in learning from image-contrast preference data, demonstrating its superior ability to elicit and understand nuances of visual context. Our code is publicly available at https://github.com/YuxiXie/V-DPO.
We propose an innovative token representation and update method in a new ultra-small language model: the Wave network. Specifically, we use a complex vector to represent each token, encoding both global and local semantics of the input text. A complex vector consists of two components: a magnitude vector representing the global semantics of the input text, and a phase vector capturing the relationships between individual tokens and global semantics. Experiments on the AG News text classification task demonstrate that, when generating complex vectors from randomly initialized token embeddings, our single-layer Wave Network achieves 90.91% accuracy with wave interference and 91.66% with wave modulation - outperforming a single Transformer layer using BERT pre-trained embeddings by 19.23% and 19.98%, respectively, and approaching the accuracy of the pre-trained and fine-tuned BERT base model (94.64%). Additionally, compared to BERT base, the Wave Network reduces video memory usage and training time by 77.34% and 85.62% during wave modulation. In summary, we used a 2.4-million-parameter small language model to achieve accuracy comparable to a 100-million-parameter BERT model in text classification.
We study the emergence of agency from scratch by using Large Language Model (LLM)-based agents. In previous studies of LLM-based agents, each agent's characteristics, including personality and memory, have traditionally been predefined. We focused on how individuality, such as behavior, personality, and memory, can be differentiated from an undifferentiated state. The present LLM agents engage in cooperative communication within a group simulation, exchanging context-based messages in natural language. By analyzing this multi-agent simulation, we report valuable new insights into how social norms, cooperation, and personality traits can emerge spontaneously. This paper demonstrates that autonomously interacting LLM-powered agents generate hallucinations and hashtags to sustain communication, which, in turn, increases the diversity of words within their interactions. Each agent's emotions shift through communication, and as they form communities, the personalities of the agents emerge and evolve accordingly. This computational modeling approach and its findings will provide a new method for analyzing collective artificial intelligence.
Per-example gradient norms are a vital ingredient for estimating gradient noise scale (GNS) with minimal variance. Observing the tensor contractions required to compute them, we propose a method with minimal FLOPs in 3D or greater tensor regimes by simultaneously computing the norms while computing the parameter gradients. Using this method we are able to observe the GNS of different layers at higher accuracy than previously possible. We find that the total GNS of contemporary transformer models is predicted well by the GNS of only the normalization layers. As a result, focusing only on the normalization layer, we develop a custom kernel to compute the per-example gradient norms while performing the LayerNorm backward pass with zero throughput overhead. Tracking GNS on only those layers, we are able to guide a practical batch size schedule that reduces training time by 18% on a Chinchilla-optimal language model.
Transformer-based autoregressive sampling has been the major bottleneck for slowing down large language model inferences. One effective way to accelerate inference is \emph{Speculative Decoding}, which employs a small model to sample a sequence of draft tokens and a large model to validate. Given its empirical effectiveness, the theoretical understanding of Speculative Decoding is falling behind. This paper tackles this gap by conceptualizing the decoding problem via markov chain abstraction and studying the key properties, \emph{output quality and inference acceleration}, from a theoretical perspective. Our analysis covers the theoretical limits of speculative decoding, batch algorithms, and output quality-inference acceleration tradeoffs. Our results reveal the fundamental connections between different components of LLMs via total variation distances and show how they jointly affect the efficiency of decoding algorithms.
Fact-checking long-form text is challenging, and it is therefore common practice to break it down into multiple atomic claims. The typical approach to fact-checking these atomic claims involves retrieving a fixed number of pieces of evidence, followed by a verification step. However, this method is usually not cost-effective, as it underutilizes the verification model's internal knowledge of the claim and fails to replicate the iterative reasoning process in human search strategies. To address these limitations, we propose FIRE, a novel agent-based framework that integrates evidence retrieval and claim verification in an iterative manner. Specifically, FIRE employs a unified mechanism to decide whether to provide a final answer or generate a subsequent search query, based on its confidence in the current judgment. We compare FIRE with other strong fact-checking frameworks and find that it achieves slightly better performance while reducing large language model (LLM) costs by an average of 7.6 times and search costs by 16.5 times. These results indicate that FIRE holds promise for application in large-scale fact-checking operations. Our code is available at https://github.com/mbzuai-nlp/fire.git.
Few-Shot Cross-Domain NER is the process of leveraging knowledge from data-rich source domains to perform entity recognition on data scarce target domains. Most previous state-of-the-art (SOTA) approaches use pre-trained language models (PLMs) for cross-domain NER. However, these models are often domain specific. To successfully use these models for new target domains, we need to modify either the model architecture or perform model finetuning using data from the new domains. Both of these result in the creation of entirely new NER models for each target domain which is infeasible for practical scenarios. Recently,several works have attempted to use LLMs to solve Few-Shot Cross-Domain NER. However, most of these are either too expensive for practical purposes or struggle to follow LLM prompt instructions. In this paper, we propose IF-WRANER (Instruction Finetuned Word-embedding based Retrieval Augmented large language model for Named Entity Recognition), a retrieval augmented LLM, finetuned for the NER task. By virtue of the regularization techniques used during LLM finetuning and the adoption of word-level embedding over sentence-level embedding during the retrieval of in-prompt examples, IF-WRANER is able to outperform previous SOTA Few-Shot Cross-Domain NER approaches. We have demonstrated the effectiveness of our model by benchmarking its performance on the open source CrossNER dataset, on which it shows more than 2% F1 score improvement over the previous SOTA model. We have deployed the model for multiple customer care domains of an enterprise. Accurate entity prediction through IF-WRANER helps direct customers to automated workflows for the domains, thereby reducing escalations to human agents by almost 15% and leading to millions of dollars in yearly savings for the company.
Large Language Model (LLM)-based applications are graduating from research prototypes to products serving millions of users, influencing how people write and consume information. A prominent example is the appearance of Answer Engines: LLM-based generative search engines supplanting traditional search engines. Answer engines not only retrieve relevant sources to a user query but synthesize answer summaries that cite the sources. To understand these systems' limitations, we first conducted a study with 21 participants, evaluating interactions with answer vs. traditional search engines and identifying 16 answer engine limitations. From these insights, we propose 16 answer engine design recommendations, linked to 8 metrics. An automated evaluation implementing our metrics on three popular engines (You.com, Perplexity.ai, BingChat) quantifies common limitations (e.g., frequent hallucination, inaccurate citation) and unique features (e.g., variation in answer confidence), with results mirroring user study insights. We release our Answer Engine Evaluation benchmark (AEE) to facilitate transparent evaluation of LLM-based applications.
The evaluation of layer importance in deep learning has been an active area of research, with significant implications for model optimization and interpretability. Recently, large language models (LLMs) have gained prominence across various domains, yet limited studies have explored the functional importance and performance contributions of individual layers within LLMs, especially from the perspective of activation distribution. In this work, we propose the Activation Variance-Sparsity Score (AVSS), a novel metric combining normalized activation variance and sparsity to assess each layer's contribution to model performance. By identifying and removing approximately the lowest 25% of layers based on AVSS, we achieve over 90% of original model performance across tasks such as question answering, language modeling, and sentiment classification, indicating that these layers may be non-essential. Our approach provides a systematic method for identifying less critical layers, contributing to efficient large language model architectures.
Analogical reasoning, particularly in multimodal contexts, is the foundation of human perception and creativity. Multimodal Large Language Model (MLLM) has recently sparked considerable discussion due to its emergent capabilities. In this paper, we delve into the multimodal analogical reasoning capability of MLLM. Specifically, we explore two facets: \textit{MLLM as an explainer} and \textit{MLLM as a predictor}. In \textit{MLLM as an explainer}, we primarily focus on whether MLLM can deeply comprehend multimodal analogical reasoning problems. We propose a unified prompt template and a method for harnessing the comprehension capabilities of MLLM to augment existing models. In \textit{MLLM as a predictor}, we aim to determine whether MLLM can directly solve multimodal analogical reasoning problems. The experiments show that our approach outperforms existing methods on popular datasets, providing preliminary evidence for the analogical reasoning capability of MLLM.
We introduce {\bf Swan}, a family of embedding models centred around the Arabic language, addressing both small-scale and large-scale use cases. Swan includes two variants: Swan-Small, based on ARBERTv2, and Swan-Large, built on ArMistral, a pretrained Arabic large language model. To evaluate these models, we propose ArabicMTEB, a comprehensive benchmark suite that assesses cross-lingual, multi-dialectal, multi-domain, and multi-cultural Arabic text embedding performance, covering eight diverse tasks and spanning 94 datasets. Swan-Large achieves state-of-the-art results, outperforming Multilingual-E5-large in most Arabic tasks, while the Swan-Small consistently surpasses Multilingual-E5-base. Our extensive evaluations demonstrate that Swan models are both dialectally and culturally aware, excelling across various Arabic domains while offering significant monetary efficiency. This work significantly advances the field of Arabic language modelling and provides valuable resources for future research and applications in Arabic natural language processing. Our models and benchmark will be made publicly accessible for research.
Code-mixing (CM), where speakers blend languages within a single expression, is prevalent in multilingual societies but poses challenges for natural language processing due to its complexity and limited data. We propose using a large language model to generate synthetic CM data, which is then used to enhance the performance of task-specific models for CM sentiment analysis. Our results show that in Spanish-English, synthetic data improved the F1 score by 9.32%, outperforming previous augmentation techniques. However, in Malayalam-English, synthetic data only helped when the baseline was low; with strong natural data, additional synthetic data offered little benefit. Human evaluation confirmed that this approach is a simple, cost-effective way to generate natural-sounding CM sentences, particularly beneficial for low baselines. Our findings suggest that few-shot prompting of large language models is a promising method for CM data augmentation and has significant impact on improving sentiment analysis, an important element in the development of social influence systems.