The rapid development of large language models has revolutionized code intelligence in software development. However, the predominance of closed-source models has restricted extensive research and development. To address this, we introduce the DeepSeek-Coder series, a range of open-source code models with sizes from 1.3B to 33B, trained from scratch on 2 trillion tokens. These models are pre-trained on a high-quality project-level code corpus and employ a fill-in-the-blank task with a 16K window to enhance code generation and infilling. Our extensive evaluations demonstrate that DeepSeek-Coder not only achieves state-of-the-art performance among open-source code models across multiple benchmarks but also surpasses existing closed-source models like Codex and GPT-3.5. Furthermore, DeepSeek-Coder models are under a permissive license that allows for both research and unrestricted commercial use.

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.

A Large Language Model~(LLM) is considered consistent if semantically equivalent prompts produce semantically equivalent responses. Despite recent advancements showcasing the impressive capabilities of LLMs in conversational systems, we show that even state-of-the-art LLMs are highly inconsistent in their generations, questioning their reliability. Prior research has tried to measure this with task-specific accuracies. However, this approach is unsuitable for moral scenarios, such as the trolley problem, with no ``correct'' answer. To address this issue, we propose a novel information-theoretic measure called Semantic Graph Entropy~(SGE) to measure the consistency of an LLM in moral scenarios. We leverage ``Rules of Thumb''~(RoTs) to explain a model's decision-making strategies and further enhance our metric. Compared to existing consistency metrics, SGE correlates better with human judgments across five LLMs. In the future, we aim to investigate the root causes of LLM inconsistencies and propose improvements.

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.

We have described a novel approach for training tabular data using the TabTransformer model with self-supervised learning. Traditional machine learning models for tabular data, such as GBDT are being widely used though our paper examines the effectiveness of the TabTransformer which is a Transformer based model optimised specifically for tabular data. The TabTransformer captures intricate relationships and dependencies among features in tabular data by leveraging the self-attention mechanism of Transformers. We have used a self-supervised learning approach in this study, where the TabTransformer learns from unlabelled data by creating surrogate supervised tasks, eliminating the need for the labelled data. The aim is to find the most effective TabTransformer model representation of categorical and numerical features. To address the challenges faced during the construction of various input settings into the Transformers. Furthermore, a comparative analysis is also been conducted to examine performance of the TabTransformer model against baseline models such as MLP and supervised TabTransformer. The research has presented with a novel approach by creating various variants of TabTransformer model namely, Binned-TT, Vanilla-MLP-TT, MLP- based-TT which has helped to increase the effective capturing of the underlying relationship between various features of the tabular dataset by constructing optimal inputs. And further we have employed a self-supervised learning approach in the form of a masking-based unsupervised setting for tabular data. The findings shed light on the best way to represent categorical and numerical features, emphasizing the TabTransormer performance when compared to established machine learning models and other self-supervised learning methods.

This paper presents an innovative large language model (LLM)-based robotic system for enhancing multi-modal human-robot interaction (HRI). Traditional HRI systems relied on complex designs for intent estimation, reasoning, and behavior generation, which were resource-intensive. In contrast, our system empowers researchers and practitioners to regulate robot behavior through three key aspects: providing high-level linguistic guidance, creating "atomics" for actions and expressions the robot can use, and offering a set of examples. Implemented on a physical robot, it demonstrates proficiency in adapting to multi-modal inputs and determining the appropriate manner of action to assist humans with its arms, following researchers' defined guidelines. Simultaneously, it coordinates the robot's lid, neck, and ear movements with speech output to produce dynamic, multi-modal expressions. This showcases the system's potential to revolutionize HRI by shifting from conventional, manual state-and-flow design methods to an intuitive, guidance-based, and example-driven approach.

Qualitative coding, or content analysis, extracts meaning from text to discern quantitative patterns across a corpus of texts. Recently, advances in the interpretive abilities of large language models (LLMs) offer potential for automating the coding process (applying category labels to texts), thereby enabling human researchers to concentrate on more creative research aspects, while delegating these interpretive tasks to AI. Our case study comprises a set of socio-historical codes on dense, paragraph-long passages representative of a humanistic study. We show that GPT-4 is capable of human-equivalent interpretations, whereas GPT-3.5 is not. Compared to our human-derived gold standard, GPT-4 delivers excellent intercoder reliability (Cohen's $\kappa \geq 0.79$) for 3 of 9 codes, and substantial reliability ($\kappa \geq 0.6$) for 8 of 9 codes. In contrast, GPT-3.5 greatly underperforms for all codes ($mean(\kappa) = 0.34$; $max(\kappa) = 0.55$). Importantly, we find that coding fidelity improves considerably when the LLM is prompted to give rationale justifying its coding decisions (chain-of-thought reasoning). We present these and other findings along with a set of best practices for adapting traditional codebooks for LLMs. Our results indicate that for certain codebooks, state-of-the-art LLMs are already adept at large-scale content analysis. Furthermore, they suggest the next generation of models will likely render AI coding a viable option for a majority of codebooks.

Knowledge sharing about emerging threats is crucial in the rapidly advancing field of cybersecurity and forms the foundation of Cyber Threat Intelligence. In this context, Large Language Models are becoming increasingly significant in the field of cybersecurity, presenting a wide range of opportunities. This study explores the capability of chatbots such as ChatGPT, GPT4all, Dolly,Stanford Alpaca, Alpaca-LoRA, and Falcon to identify cybersecurity-related text within Open Source Intelligence. We assess the capabilities of existing chatbot models for Natural Language Processing tasks. We consider binary classification and Named Entity Recognition as tasks. This study analyzes well-established data collected from Twitter, derived from previous research efforts. Regarding cybersecurity binary classification, Chatbot GPT-4 as a commercial model achieved an acceptable F1-score of 0.94, and the open-source GPT4all model achieved an F1-score of 0.90. However, concerning cybersecurity entity recognition, chatbot models have limitations and are less effective. This study demonstrates the capability of these chatbots only for specific tasks, such as cybersecurity binary classification, while highlighting the need for further refinement in other tasks, such as Named Entity Recognition tasks.

Self-supervised methods have gained prominence in time series anomaly detection due to the scarcity of available annotations. Nevertheless, they typically demand extensive training data to acquire a generalizable representation map, which conflicts with scenarios of a few available samples, thereby limiting their performance. To overcome the limitation, we propose \textbf{AnomalyLLM}, a knowledge distillation-based time series anomaly detection approach where the student network is trained to mimic the features of the large language model (LLM)-based teacher network that is pretrained on large-scale datasets. During the testing phase, anomalies are detected when the discrepancy between the features of the teacher and student networks is large. To circumvent the student network from learning the teacher network's feature of anomalous samples, we devise two key strategies. 1) Prototypical signals are incorporated into the student network to consolidate the normal feature extraction. 2) We use synthetic anomalies to enlarge the representation gap between the two networks. AnomalyLLM demonstrates state-of-the-art performance on 15 datasets, improving accuracy by at least 14.5\% in the UCR dataset.

Objective: The reading level of health educational materials significantly influences information understandability and accessibility, particularly for minoritized populations. Many patient educational resources surpass the reading level and complexity of widely accepted standards. There is a critical need for high-performing text simplification models in health information to enhance dissemination and literacy. This need is particularly acute in cancer education, where effective prevention and screening education can substantially reduce morbidity and mortality. Methods: We introduce Simplified Digestive Cancer (SimpleDC), a parallel corpus of cancer education materials tailored for health text simplification research. Utilizing SimpleDC alongside the existing Med-EASi corpus, we explore Large Language Model (LLM)-based simplification methods, including fine-tuning, reinforcement learning (RL), reinforcement learning with human feedback (RLHF), domain adaptation, and prompt-based approaches. Our experimentation encompasses Llama 2 and GPT-4. A novel RLHF reward function is introduced, featuring a lightweight model adept at distinguishing between original and simplified texts, thereby enhancing the model's effectiveness with unlabeled data. Results: Fine-tuned Llama 2 models demonstrated high performance across various metrics. Our innovative RLHF reward function surpassed existing RL text simplification reward functions in effectiveness. The results underscore that RL/RLHF can augment fine-tuning, facilitating model training on unlabeled text and improving performance. Additionally, these methods effectively adapt out-of-domain text simplification models to targeted domains.