In this paper, we introduce SUTRA, multilingual Large Language Model architecture capable of understanding, reasoning, and generating text in over 50 languages. SUTRA's design uniquely decouples core conceptual understanding from language-specific processing, which facilitates scalable and efficient multilingual alignment and learning. Employing a Mixture of Experts framework both in language and concept processing, SUTRA demonstrates both computational efficiency and responsiveness. Through extensive evaluations, SUTRA is demonstrated to surpass existing models like GPT-3.5, Llama2 by 20-30% on leading Massive Multitask Language Understanding (MMLU) benchmarks for multilingual tasks. SUTRA models are also online LLMs that can use knowledge from the internet to provide hallucination-free, factual and up-to-date responses while retaining their multilingual capabilities. Furthermore, we explore the broader implications of its architecture for the future of multilingual AI, highlighting its potential to democratize access to AI technology globally and to improve the equity and utility of AI in regions with predominantly non-English languages. Our findings suggest that SUTRA not only fills pivotal gaps in multilingual model capabilities but also establishes a new benchmark for operational efficiency and scalability in AI applications.
Large Language Models (LLMs) have made great strides in areas such as language processing and computer vision. Despite the emergence of diverse techniques to improve few-shot learning capacity, current LLMs fall short in handling the languages in biology and chemistry. For example, they are struggling to capture the relationship between molecule structure and pharmacochemical properties. Consequently, the few-shot learning capacity of small-molecule drug modification remains impeded. In this work, we introduced DrugLLM, a LLM tailored for drug design. During the training process, we employed Group-based Molecular Representation (GMR) to represent molecules, arranging them in sequences that reflect modifications aimed at enhancing specific molecular properties. DrugLLM learns how to modify molecules in drug discovery by predicting the next molecule based on past modifications. Extensive computational experiments demonstrate that DrugLLM can generate new molecules with expected properties based on limited examples, presenting a powerful few-shot molecule generation capacity.
Social media aids disaster response but suffers from noise, hindering accurate impact assessment and decision making for resilient cities, which few studies considered. To address the problem, this study proposes the first domain-specific LLM model and an integrated method for rapid earthquake impact assessment. First, a few categories are introduced to classify and filter microblogs considering their relationship to the physical and social impacts of earthquakes, and a dataset comprising 7282 earthquake-related microblogs from twenty earthquakes in different locations is developed as well. Then, with a systematic analysis of various influential factors, QuakeBERT, a domain-specific large language model (LLM), is developed and fine-tuned for accurate classification and filtering of microblogs. Meanwhile, an integrated method integrating public opinion trend analysis, sentiment analysis, and keyword-based physical impact quantification is introduced to assess both the physical and social impacts of earthquakes based on social media texts. Experiments show that data diversity and data volume dominate the performance of QuakeBERT and increase the macro average F1 score by 27%, while the best classification model QuakeBERT outperforms the CNN- or RNN-based models by improving the macro average F1 score from 60.87% to 84.33%. Finally, the proposed approach is applied to assess two earthquakes with the same magnitude and focal depth. Results show that the proposed approach can effectively enhance the impact assessment process by accurate detection of noisy microblogs, which enables effective post-disaster emergency responses to create more resilient cities.
This paper presents the use of Retrieval Augmented Generation (RAG) to improve the feedback generated by Large Language Models for programming tasks. For this purpose, corresponding lecture recordings were transcribed and made available to the Large Language Model GPT-4 as external knowledge source together with timestamps as metainformation by using RAG. The purpose of this is to prevent hallucinations and to enforce the use of the technical terms and phrases from the lecture. In an exercise platform developed to solve programming problems for an introductory programming lecture, students can request feedback on their solutions generated by GPT-4. For this task GPT-4 receives the students' code solution, the compiler output, the result of unit tests and the relevant passages from the lecture notes available through the use of RAG as additional context. The feedback generated by GPT-4 should guide students to solve problems independently and link to the lecture content, using the time stamps of the transcript as meta-information. In this way, the corresponding lecture videos can be viewed immediately at the corresponding positions. For the evaluation, students worked with the tool in a workshop and decided for each feedback whether it should be extended by RAG or not. First results based on a questionnaire and the collected usage data show that the use of RAG can improve feedback generation and is preferred by students in some situations. Due to the slower speed of feedback generation, the benefits are situation dependent.
While nationality is a pivotal demographic element that enhances the performance of language models, it has received far less scrutiny regarding inherent biases. This study investigates nationality bias in ChatGPT (GPT-3.5), a large language model (LLM) designed for text generation. The research covers 195 countries, 4 temperature settings, and 3 distinct prompt types, generating 4,680 discourses about nationality descriptions in Chinese and English. Automated metrics were used to analyze the nationality bias, and expert annotators alongside ChatGPT itself evaluated the perceived bias. The results show that ChatGPT's generated discourses are predominantly positive, especially compared to its predecessor, GPT-2. However, when prompted with negative inclinations, it occasionally produces negative content. Despite ChatGPT considering its generated text as neutral, it shows consistent self-awareness about nationality bias when subjected to the same pair-wise comparison annotation framework used by human annotators. In conclusion, while ChatGPT's generated texts seem friendly and positive, they reflect the inherent nationality biases in the real world. This bias may vary across different language versions of ChatGPT, indicating diverse cultural perspectives. The study highlights the subtle and pervasive nature of biases within LLMs, emphasizing the need for further scrutiny.
Current medical artificial intelligence systems are often limited to narrow applications, hindering their widespread adoption in clinical practice. To address this limitation, we propose MedVersa, a generalist learner that enables flexible learning and tasking for medical image interpretation. By leveraging a large language model as a learnable orchestrator, MedVersa can learn from both visual and linguistic supervision, support multimodal inputs, and perform real-time task specification. This versatility allows MedVersa to adapt to various clinical scenarios and perform multifaceted medical image analysis. We introduce MedInterp, the largest multimodal dataset to date for medical image interpretation, consisting of over 13 million annotated instances spanning 11 tasks across 3 modalities, to support the development of MedVersa. Our experiments demonstrate that MedVersa achieves state-of-the-art performance in 9 tasks, sometimes outperforming specialist counterparts by over 10%. MedVersa is the first to showcase the viability of multimodal generative medical AI in implementing multimodal outputs, inputs, and dynamic task specification, highlighting its potential as a multifunctional system for comprehensive medical image analysis. This generalist approach to medical image interpretation paves the way for more adaptable and efficient AI-assisted clinical decision-making.
Generative Artificial Intelligence (GAI) is taking the world by storm with its unparalleled content creation ability. Large Language Models (LLMs) are at the forefront of this movement. However, the significant resource demands of LLMs often require cloud hosting, which raises issues regarding privacy, latency, and usage limitations. Although edge intelligence has long been utilized to solve these challenges by enabling real-time AI computation on ubiquitous edge resources close to data sources, most research has focused on traditional AI models and has left a gap in addressing the unique characteristics of LLM inference, such as considerable model size, auto-regressive processes, and self-attention mechanisms. In this paper, we present an edge intelligence optimization problem tailored for LLM inference. Specifically, with the deployment of the batching technique and model quantization on resource-limited edge devices, we formulate an inference model for transformer decoder-based LLMs. Furthermore, our approach aims to maximize the inference throughput via batch scheduling and joint allocation of communication and computation resources, while also considering edge resource constraints and varying user requirements of latency and accuracy. To address this NP-hard problem, we develop an optimal Depth-First Tree-Searching algorithm with online tree-Pruning (DFTSP) that operates within a feasible time complexity. Simulation results indicate that DFTSP surpasses other batching benchmarks in throughput across diverse user settings and quantization techniques, and it reduces time complexity by over 45% compared to the brute-force searching method.
In the pursuit of advancing natural language processing for the Italian language, we introduce a state-of-the-art Large Language Model (LLM) based on the novel Meta LLaMA-3 model: LLaMAntino-3-ANITA-8B-Inst-DPO-ITA. We fine-tuned the original 8B parameters instruction tuned model using the Supervised Fine-tuning (SFT) technique on the English and Italian language datasets in order to improve the original performance. Consequently, a Dynamic Preference Optimization (DPO) process has been used to align preferences, avoid dangerous and inappropriate answers, and limit biases and prejudices. Our model leverages the efficiency of QLoRA to fine-tune the model on a smaller portion of the original model weights and then adapt the model specifically for the Italian linguistic structure, achieving significant improvements in both performance and computational efficiency. Concurrently, DPO is employed to refine the model's output, ensuring that generated content aligns with quality answers. The synergy between SFT, QLoRA's parameter efficiency and DPO's user-centric optimization results in a robust LLM that excels in a variety of tasks, including but not limited to text completion, zero-shot classification, and contextual understanding. The model has been extensively evaluated over standard benchmarks for the Italian and English languages, showing outstanding results. The model is freely available over the HuggingFace hub and, examples of use can be found in our GitHub repository. https://huggingface.co/swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA
Large Language Models (LLMs) enable a new ecosystem with many downstream applications, called LLM applications, with different natural language processing tasks. The functionality and performance of an LLM application highly depend on its system prompt, which instructs the backend LLM on what task to perform. Therefore, an LLM application developer often keeps a system prompt confidential to protect its intellectual property. As a result, a natural attack, called prompt leaking, is to steal the system prompt from an LLM application, which compromises the developer's intellectual property. Existing prompt leaking attacks primarily rely on manually crafted queries, and thus achieve limited effectiveness. In this paper, we design a novel, closed-box prompt leaking attack framework, called PLeak, to optimize an adversarial query such that when the attacker sends it to a target LLM application, its response reveals its own system prompt. We formulate finding such an adversarial query as an optimization problem and solve it with a gradient-based method approximately. Our key idea is to break down the optimization goal by optimizing adversary queries for system prompts incrementally, i.e., starting from the first few tokens of each system prompt step by step until the entire length of the system prompt. We evaluate PLeak in both offline settings and for real-world LLM applications, e.g., those on Poe, a popular platform hosting such applications. Our results show that PLeak can effectively leak system prompts and significantly outperforms not only baselines that manually curate queries but also baselines with optimized queries that are modified and adapted from existing jailbreaking attacks. We responsibly reported the issues to Poe and are still waiting for their response. Our implementation is available at this repository: https://github.com/BHui97/PLeak.
This study explores the innovative use of Large Language Models (LLMs) as analytical tools for interpreting complex financial regulations. The primary objective is to design effective prompts that guide LLMs in distilling verbose and intricate regulatory texts, such as the Basel III capital requirement regulations, into a concise mathematical framework that can be subsequently translated into actionable code. This novel approach aims to streamline the implementation of regulatory mandates within the financial reporting and risk management systems of global banking institutions. A case study was conducted to assess the performance of various LLMs, demonstrating that GPT-4 outperforms other models in processing and collecting necessary information, as well as executing mathematical calculations. The case study utilized numerical simulations with asset holdings -- including fixed income, equities, currency pairs, and commodities -- to demonstrate how LLMs can effectively implement the Basel III capital adequacy requirements. Keywords: Large Language Models, Prompt Engineering, LLMs in Finance, Basel III, Minimum Capital Requirements, LLM Ethics
Category fluency is a widely studied cognitive phenomenon, yet two conflicting accounts have been proposed as the underlying retrieval mechanism -- an optimal foraging process deliberately searching through memory (Hills et al., 2012) and a random walk sampling from a semantic network (Abbott et al., 2015). Evidence for both accounts has centered around predicting human patch switches, where both existing models of category fluency produce paradoxically identical results. We begin by peeling back the assumptions made by existing models, namely that each named example only depends on the previous example, by (i) adding an additional bias to model the category transition probability directly and (ii) relying on a large language model to predict based on the entire existing sequence. Then, we present evidence towards resolving the disagreement between each account of foraging by reformulating models as sequence generators. To evaluate, we compare generated category fluency runs to a bank of human-written sequences by proposing a metric based on n-gram overlap. We find category switch predictors do not necessarily produce human-like sequences, in fact the additional biases used by the Hills et al. (2012) model are required to improve generation quality, which are later improved by our category modification. Even generating exclusively with an LLM requires an additional global cue to trigger the patch switching behavior during production. Further tests on only the search process on top of the semantic network highlight the importance of deterministic search to replicate human behavior.
We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpart by a large margin in the recent large language model (LLM) literature. However, existing open-source RLHF projects are still largely confined to the offline learning setting. In this technical report, we aim to fill in this gap and provide a detailed recipe that is easy to reproduce for online iterative RLHF. In particular, since online human feedback is usually infeasible for open-source communities with limited resources, we start by constructing preference models using a diverse set of open-source datasets and use the constructed proxy preference model to approximate human feedback. Then, we discuss the theoretical insights and algorithmic principles behind online iterative RLHF, followed by a detailed practical implementation. Our trained LLM achieves impressive performance on LLM chatbot benchmarks, including AlpacaEval-2, Arena-Hard, and MT-Bench, as well as other academic benchmarks such as HumanEval and TruthfulQA. We have shown that supervised fine-tuning (SFT) and iterative RLHF can obtain state-of-the-art performance with fully open-source datasets. Further, we have made our models, curated datasets, and comprehensive step-by-step code guidebooks publicly available. Please refer to https://github.com/RLHFlow/RLHF-Reward-Modeling and https://github.com/RLHFlow/Online-RLHF for more detailed information.
The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curriculum learning-inspired, data-centric training strategy that begins with simpler tasks and progresses to more complex ones, using criteria such as prompt length, attention scores, and loss values to structure the training data. Experiments with Mistral-7B (Jiang et al., 2023) and Gemma-7B (Team et al., 2024) models demonstrate that curriculum learning slightly improves performance compared to traditional random data shuffling. Notably, we observed that sorting data based on our proposed attention criteria generally led to better performance. This approach offers a sustainable method to enhance LLM performance without increasing model size or dataset volume, addressing scalability challenges in LLM training.
In this paper, we introduce SaudiBERT, a monodialect Arabic language model pretrained exclusively on Saudi dialectal text. To demonstrate the model's effectiveness, we compared SaudiBERT with six different multidialect Arabic language models across 11 evaluation datasets, which are divided into two groups: sentiment analysis and text classification. SaudiBERT achieved average F1-scores of 86.15\% and 87.86\% in these groups respectively, significantly outperforming all other comparative models. Additionally, we present two novel Saudi dialectal corpora: the Saudi Tweets Mega Corpus (STMC), which contains over 141 million tweets in Saudi dialect, and the Saudi Forums Corpus (SFC), which includes 15.2 GB of text collected from five Saudi online forums. Both corpora are used in pretraining the proposed model, and they are the largest Saudi dialectal corpora ever reported in the literature. The results confirm the effectiveness of SaudiBERT in understanding and analyzing Arabic text expressed in Saudi dialect, achieving state-of-the-art results in most tasks and surpassing other language models included in the study. SaudiBERT model is publicly available on \url{https://huggingface.co/faisalq/SaudiBERT}.
Recent advancements in large language models (LLMs) are propelling us toward artificial general intelligence with their remarkable emergent abilities and reasoning capabilities. However, the substantial computational and memory requirements limit the widespread adoption. Quantization, a key compression technique, can effectively mitigate these demands by compressing and accelerating LLMs, albeit with potential risks to accuracy. Numerous studies have aimed to minimize the accuracy loss associated with quantization. However, their quantization configurations vary from each other and cannot be fairly compared. In this paper, we present LLMC, a plug-and-play compression toolkit, to fairly and systematically explore the impact of quantization. LLMC integrates dozens of algorithms, models, and hardwares, offering high extensibility from integer to floating-point quantization, from LLM to vision-language (VLM) model, from fixed-bit to mixed precision, and from quantization to sparsification. Powered by this versatile toolkit, our benchmark covers three key aspects: calibration data, algorithms (three strategies), and data formats, providing novel insights and detailed analyses for further research and practical guidance for users. Our toolkit is available at https://github.com/ModelTC/llmc.
Evolutionary algorithms excel in solving complex optimization problems, especially those with multiple objectives. However, their stochastic nature can sometimes hinder rapid convergence to the global optima, particularly in scenarios involving constraints. In this study, we employ a large language model (LLM) to enhance evolutionary search for solving constrained multi-objective optimization problems. Our aim is to speed up the convergence of the evolutionary population. To achieve this, we finetune the LLM through tailored prompt engineering, integrating information concerning both objective values and constraint violations of solutions. This process enables the LLM to grasp the relationship between well-performing and poorly performing solutions based on the provided input data. Solution's quality is assessed based on their constraint violations and objective-based performance. By leveraging the refined LLM, it can be used as a search operator to generate superior-quality solutions. Experimental evaluations across various test benchmarks illustrate that LLM-aided evolutionary search can significantly accelerate the population's convergence speed and stands out competitively against cutting-edge evolutionary algorithms.
Aspect-based sentiment analysis (ABSA) is an important subtask of sentiment analysis, which aims to extract the aspects and predict their sentiments. Most existing studies focus on improving the performance of the target domain by fine-tuning domain-specific models (trained on source domains) based on the target domain dataset. Few works propose continual learning tasks for ABSA, which aim to learn the target domain's ability while maintaining the history domains' abilities. In this paper, we propose a Large Language Model-based Continual Learning (\texttt{LLM-CL}) model for ABSA. First, we design a domain knowledge decoupling module to learn a domain-invariant adapter and separate domain-variant adapters dependently with an orthogonal constraint. Then, we introduce a domain knowledge warmup strategy to align the representation between domain-invariant and domain-variant knowledge. In the test phase, we index the corresponding domain-variant knowledge via domain positioning to not require each sample's domain ID. Extensive experiments over 19 datasets indicate that our \texttt{LLM-CL} model obtains new state-of-the-art performance.
To reduce environmental risks and impacts from orphaned wells (abandoned oil and gas wells), it is essential to first locate and then plug these wells. Although some historical documents are available, they are often unstructured, not cleaned, and outdated. Additionally, they vary widely by state and type. Manual reading and digitizing this information from historical documents are not feasible, given the high number of wells. Here, we propose a new computational approach for rapidly and cost-effectively locating these wells. Specifically, we leverage the advanced capabilities of large language models (LLMs) to extract vital information including well location and depth from historical records of orphaned wells. In this paper, we present an information extraction workflow based on open-source Llama 2 models and test them on a dataset of 160 well documents. Our results show that the developed workflow achieves excellent accuracy in extracting location and depth from clean, PDF-based reports, with a 100% accuracy rate. However, it struggles with unstructured image-based well records, where accuracy drops to 70%. The workflow provides significant benefits over manual human digitization, including reduced labor and increased automation. In general, more detailed prompting leads to improved information extraction, and those LLMs with more parameters typically perform better. We provided a detailed discussion of the current challenges and the corresponding opportunities/approaches to address them. Additionally, a vast amount of geoscientific information is locked up in old documents, and this work demonstrates that recent breakthroughs in LLMs enable us to unlock this information more broadly.
The disconnect between tokenizer creation and model training in language models allows for specific inputs, such as the infamous SolidGoldMagikarp token, to induce unwanted model behaviour. Although such `glitch tokens', tokens present in the tokenizer vocabulary but that are nearly or entirely absent during model training, have been observed across various models, a reliable method to identify and address them has been missing. We present a comprehensive analysis of Large Language Model tokenizers, specifically targeting this issue of detecting under-trained tokens. Through a combination of tokenizer analysis, model weight-based indicators, and prompting techniques, we develop novel and effective methods for automatically detecting these problematic tokens. Our findings demonstrate the prevalence of such tokens across a diverse set of models and provide insights into improving the efficiency and safety of language models.
Pre-trained large language models (LLM) have emerged as a powerful tool for simulating various scenarios and generating output given specific instructions and multimodal input. In this work, we analyze the specific use of LLM to enhance a classical supervised machine learning method for classification problems. We propose a few approaches to integrate LLM into a classical machine learning estimator to further enhance the prediction performance. We examine the performance of the proposed approaches through both standard supervised learning binary classification tasks, and a transfer learning task where the test data observe distribution changes compared to the training data. Numerical experiments using four publicly available datasets are conducted and suggest that using LLM to enhance classical machine learning estimators can provide significant improvement on prediction performance.