The year 2023 marked a significant surge in the exploration of applying large language model (LLM) chatbots, notably ChatGPT, across various disciplines. We surveyed the applications of ChatGPT in bioinformatics and biomedical informatics throughout the year, covering omics, genetics, biomedical text mining, drug discovery, biomedical image understanding, bioinformatics programming, and bioinformatics education. Our survey delineates the current strengths and limitations of this chatbot in bioinformatics and offers insights into potential avenues for future developments.
This research explores the integration of chatbot technology powered by GPT-3.5 and GPT-4 Turbo into higher education to enhance internationalization and leverage digital transformation. It delves into the design, implementation, and application of Large Language Models (LLMs) for improving student engagement, information access, and support. Utilizing technologies like Python 3, GPT API, LangChain, and Chroma Vector Store, the research emphasizes creating a high-quality, timely, and relevant transcript dataset for chatbot testing. Findings indicate the chatbot's efficacy in providing comprehensive responses, its preference over traditional methods by users, and a low error rate. Highlighting the chatbot's real-time engagement, memory capabilities, and critical data access, the study demonstrates its potential to elevate accessibility, efficiency, and satisfaction. Concluding, the research suggests the chatbot significantly aids higher education internationalization, proposing further investigation into digital technology's role in educational enhancement and strategy development.
Current language models are unable to quickly learn new concepts on the fly, often requiring a more involved finetuning process to learn robustly. Prompting in-context is not robust to context distractions, and often fails to confer much information about the new concepts. Classic methods for few-shot word learning in NLP, relying on global word vectors, are less applicable to large language models. In this paper, we introduce a novel approach named CoLLEGe (Concept Learning with Language Embedding Generation) to modernize few-shot concept learning. CoLLEGe is a meta-learning framework capable of generating flexible embeddings for new concepts using a small number of example sentences or definitions. Our primary meta-learning objective is simply to facilitate a language model to make next word predictions in forthcoming sentences, making it compatible with language model pretraining. We design a series of tasks to test new concept learning in challenging real-world scenarios, including new word acquisition, definition inference, and verbal reasoning, and demonstrate that our method succeeds in each setting without task-specific training. Code and data for our project can be found at https://college-concept-learning.github.io/
We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a language model or human expertise, we develop an automated closed-loop system which involves two feedback mechanisms. The first mechanism uses feedback from a given supervised model and finds adversarial prompts that result in image generations that maximize the model loss. While these adversarial prompts result in diverse data informed by the model, they are not informed of the target distribution, which can be inefficient. Therefore, we introduce the second feedback mechanism that guides the generation process towards a certain target distribution. We call the method combining these two mechanisms Guided Adversarial Prompts. We perform our evaluations on different tasks, datasets and architectures, with different types of distribution shifts (spuriously correlated data, unseen domains) and demonstrate the efficiency of the proposed feedback mechanisms compared to open-loop approaches.
Does the training of large language models potentially infringe upon code licenses? Furthermore, are there any datasets available that can be safely used for training these models without violating such licenses? In our study, we assess the current trends in the field and the importance of incorporating code into the training of large language models. Additionally, we examine publicly available datasets to see whether these models can be trained on them without the risk of legal issues in the future. To accomplish this, we compiled a list of 53 large language models trained on file-level code. We then extracted their datasets and analyzed how much they overlap with a dataset we created, consisting exclusively of strong copyleft code. Our analysis revealed that every dataset we examined contained license inconsistencies, despite being selected based on their associated repository licenses. We analyzed a total of 514 million code files, discovering 38 million exact duplicates present in our strong copyleft dataset. Additionally, we examined 171 million file-leading comments, identifying 16 million with strong copyleft licenses and another 11 million comments that discouraged copying without explicitly mentioning a license. Based on the findings of our study, which highlights the pervasive issue of license inconsistencies in large language models trained on code, our recommendation for both researchers and the community is to prioritize the development and adoption of best practices for dataset creation and management.
Language model-based code completion models have quickly grown in use, helping thousands of developers write code in many different programming languages. However, research on code completion models typically focuses on imperative languages such as Python and JavaScript, which results in a lack of representation for functional programming languages. Consequently, these models often perform poorly on functional languages such as Haskell. To investigate whether this can be alleviated, we evaluate the performance of two language models for code, CodeGPT and UniXcoder, on the functional programming language Haskell. We fine-tune and evaluate the models on Haskell functions sourced from a publicly accessible Haskell dataset on HuggingFace. Additionally, we manually evaluate the models using our novel translated HumanEval dataset. Our automatic evaluation shows that knowledge of imperative programming languages in the pre-training of LLMs may not transfer well to functional languages, but that code completion on functional languages is feasible. Consequently, this shows the need for more high-quality Haskell datasets. A manual evaluation on HumanEval-Haskell indicates CodeGPT frequently generates empty predictions and extra comments, while UniXcoder more often produces incomplete or incorrect predictions. Finally, we release HumanEval-Haskell, along with the fine-tuned models and all code required to reproduce our experiments on GitHub (https://github.com/AISE-TUDelft/HaskellCCEval).
Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the selection of textual embeddings and clustering algorithms. This study argues that recent advancements in large language models (LLMs) have the potential to enhance this task. The research investigates how different textual embeddings, particularly those utilised in LLMs, and various clustering algorithms influence the clustering of text datasets. A series of experiments were conducted to evaluate the impact of embeddings on clustering results, the role of dimensionality reduction through summarisation, and the adjustment of model size. The findings indicate that LLM embeddings are superior at capturing subtleties in structured language. OpenAI's GPT-3.5 Turbo model yields better results in three out of five clustering metrics across most tested datasets. Most LLM embeddings show improvements in cluster purity and provide a more informative silhouette score, reflecting a refined structural understanding of text data compared to traditional methods. Among the more lightweight models, BERT demonstrates leading performance. Additionally, it was observed that increasing model dimensionality and employing summarisation techniques do not consistently enhance clustering efficiency, suggesting that these strategies require careful consideration for practical application. These results highlight a complex balance between the need for refined text representation and computational feasibility in text clustering applications. This study extends traditional text clustering frameworks by integrating embeddings from LLMs, offering improved methodologies and suggesting new avenues for future research in various types of textual analysis.
Leveraging large-scale Text-to-Image (TTI) models have become a common technique for generating exemplar or training dataset in the fields of image synthesis, video editing, 3D reconstruction. However, semantic structural visual hallucinations involving perceptually severe defects remain a concern, especially in the domain of non-photorealistic rendering (NPR) such as cartoons and pixelization-style character. To detect these hallucinations in NPR, We propose a novel semantic structural hallucination detection system using Vision-Language Model (VLM). Our approach is to leverage the emerging capability of large language model, in-context learning which denotes that VLM has seen some examples by user for specific downstream task, here hallucination detection. Based on in-context learning, we introduce pose-aware in-context visual learning (PA-ICVL) which improve the overall performance of VLM by further inputting visual data beyond prompts, RGB images and pose information. By incorporating pose guidance, we enable VLMs to make more accurate decisions. Experimental results demonstrate significant improvements in identifying visual hallucinations compared to baseline methods relying solely on RGB images. Within selected two VLMs, GPT-4v, Gemini pro vision, our proposed PA-ICVL improves the hallucination detection with 50% to 78%, 57% to 80%, respectively. This research advances a capability of TTI models toward real-world applications by mitigating visual hallucinations via in-context visual learning, expanding their potential in non-photorealistic domains. In addition, it showcase how users can boost the downstream-specialized capability of open VLM by harnessing additional conditions. We collect synthetic cartoon-hallucination dataset with TTI models, this dataset and final tuned VLM will be publicly available.
Social media platforms are rich sources of opinionated content. Stance detection allows the automatic extraction of users' opinions on various topics from such content. We focus on zero-shot stance detection, where the model's success relies on (a) having knowledge about the target topic; and (b) learning general reasoning strategies that can be employed for new topics. We present Stance Reasoner, an approach to zero-shot stance detection on social media that leverages explicit reasoning over background knowledge to guide the model's inference about the document's stance on a target. Specifically, our method uses a pre-trained language model as a source of world knowledge, with the chain-of-thought in-context learning approach to generate intermediate reasoning steps. Stance Reasoner outperforms the current state-of-the-art models on 3 Twitter datasets, including fully supervised models. It can better generalize across targets, while at the same time providing explicit and interpretable explanations for its predictions.
In this paper, we propose VidLA, an approach for video-language alignment at scale. There are two major limitations of previous video-language alignment approaches. First, they do not capture both short-range and long-range temporal dependencies and typically employ complex hierarchical deep network architectures that are hard to integrate with existing pretrained image-text foundation models. To effectively address this limitation, we instead keep the network architecture simple and use a set of data tokens that operate at different temporal resolutions in a hierarchical manner, accounting for the temporally hierarchical nature of videos. By employing a simple two-tower architecture, we are able to initialize our video-language model with pretrained image-text foundation models, thereby boosting the final performance. Second, existing video-language alignment works struggle due to the lack of semantically aligned large-scale training data. To overcome it, we leverage recent LLMs to curate the largest video-language dataset to date with better visual grounding. Furthermore, unlike existing video-text datasets which only contain short clips, our dataset is enriched with video clips of varying durations to aid our temporally hierarchical data tokens in extracting better representations at varying temporal scales. Overall, empirical results show that our proposed approach surpasses state-of-the-art methods on multiple retrieval benchmarks, especially on longer videos, and performs competitively on classification benchmarks.
Artificial intelligence has been around for a while, but suddenly it has received more attention than ever before. Thanks to innovations from companies like Google, Microsoft, Meta, and other major brands in technology. OpenAI, though, has triggered the button with its ground-breaking invention ChatGPT. ChatGPT is a Large Language Model (LLM) based on Transformer architecture that has the ability to generate human-like responses in a conversational context. It uses deep learning algorithms to generate natural language responses to input text. Its large number of parameters, contextual generation, and open-domain training make it a versatile and effective tool for a wide range of applications, from chatbots to customer service to language translation. It has the potential to revolutionize various industries and transform the way we interact with technology. However, the use of ChatGPT has also raised several concerns, including ethical, social, and employment challenges, which must be carefully considered to ensure the responsible use of this technology. The article provides an overview of ChatGPT, delving into its architecture and training process. It highlights the potential impacts of ChatGPT on the society. In this paper, we suggest some approaches involving technology, regulation, education, and ethics in an effort to maximize ChatGPT's benefits while minimizing its negative impacts. This study is expected to contribute to a greater understanding of ChatGPT and aid in predicting the potential changes it may bring about.
Watermarking approaches are proposed to identify if text being circulated is human or large language model (LLM) generated. The state-of-the-art watermarking strategy of Kirchenbauer et al. (2023a) biases the LLM to generate specific (``green'') tokens. However, determining the robustness of this watermarking method is an open problem. Existing attack methods fail to evade detection for longer text segments. We overcome this limitation, and propose {\em Self Color Testing-based Substitution (SCTS)}, the first ``color-aware'' attack. SCTS obtains color information by strategically prompting the watermarked LLM and comparing output tokens frequencies. It uses this information to determine token colors, and substitutes green tokens with non-green ones. In our experiments, SCTS successfully evades watermark detection using fewer number of edits than related work. Additionally, we show both theoretically and empirically that SCTS can remove the watermark for arbitrarily long watermarked text.
In the context of online education, designing an automatic solver for geometric problems has been considered a crucial step towards general math Artificial Intelligence (AI), empowered by natural language understanding and traditional logical inference. In most instances, problems are addressed by adding auxiliary components such as lines or points. However, adding auxiliary components automatically is challenging due to the complexity in selecting suitable auxiliary components especially when pivotal decisions have to be made. The state-of-the-art performance has been achieved by exhausting all possible strategies from the category library to identify the one with the maximum likelihood. However, an extensive strategy search have to be applied to trade accuracy for ef-ficiency. To add auxiliary components automatically and efficiently, we present deep reinforcement learning framework based on the language model, such as BERT. We firstly apply the graph attention mechanism to reduce the strategy searching space, called AttnStrategy, which only focus on the conclusion-related components. Meanwhile, a novel algorithm, named Automatically Adding Auxiliary Components using Reinforcement Learning framework (A3C-RL), is proposed by forcing an agent to select top strategies, which incorporates the AttnStrategy and BERT as the memory components. Results from extensive experiments show that the proposed A3C-RL algorithm can substantially enhance the average precision by 32.7% compared to the traditional MCTS. In addition, the A3C-RL algorithm outperforms humans on the geometric questions from the annual University Entrance Mathematical Examination of China.
Automated teaching assistants and chatbots have significant potential to reduce the workload of human instructors, especially for logistics-related question answering, which is important to students yet repetitive for instructors. However, due to privacy concerns, there is a lack of publicly available datasets. We introduce SyllabusQA, an open-source dataset with 63 real course syllabi covering 36 majors, containing 5,078 open-ended course logistics-related question-answer pairs that are diverse in both question types and answer formats. Since many logistics-related questions contain critical information like the date of an exam, it is important to evaluate the factuality of answers. We benchmark several strong baselines on this task, from large language model prompting to retrieval-augmented generation. We introduce Fact-QA, an LLM-based (GPT-4) evaluation metric to evaluate the factuality of predicted answers. We find that despite performing close to humans on traditional metrics of textual similarity, there remains a significant gap between automated approaches and humans in terms of fact precision.
Emotional states, as indicators of affect, are pivotal to overall health, making their accurate prediction before onset crucial. Current studies are primarily centered on immediate short-term affect detection using data from wearable and mobile devices. These studies typically focus on objective sensory measures, often neglecting other forms of self-reported information like diaries and notes. In this paper, we propose a multimodal deep learning model for affect status forecasting. This model combines a transformer encoder with a pre-trained language model, facilitating the integrated analysis of objective metrics and self-reported diaries. To validate our model, we conduct a longitudinal study, enrolling college students and monitoring them over a year, to collect an extensive dataset including physiological, environmental, sleep, metabolic, and physical activity parameters, alongside open-ended textual diaries provided by the participants. Our results demonstrate that the proposed model achieves predictive accuracy of 82.50% for positive affect and 82.76% for negative affect, a full week in advance. The effectiveness of our model is further elevated by its explainability.
This paper proposes PE-GPT, a custom-tailored large language model uniquely adapted for power converter modulation design. By harnessing in-context learning and specialized tiered physics-informed neural networks, PE-GPT guides users through text-based dialogues, recommending actionable modulation parameters. The effectiveness of PE-GPT is validated through a practical design case involving dual active bridge converters, supported by hardware experimentation. This research underscores the transformative potential of large language models in power converter modulation design, offering enhanced accessibility, explainability, and efficiency, thereby setting a new paradigm in the field.
Researchers and developers increasingly rely on toxicity scoring to moderate generative language model outputs, in settings such as customer service, information retrieval, and content generation. However, toxicity scoring may render pertinent information inaccessible, rigidify or "value-lock" cultural norms, and prevent language reclamation processes, particularly for marginalized people. In this work, we extend the concept of algorithmic recourse to generative language models: we provide users a novel mechanism to achieve their desired prediction by dynamically setting thresholds for toxicity filtering. Users thereby exercise increased agency relative to interactions with the baseline system. A pilot study ($n = 30$) supports the potential of our proposed recourse mechanism, indicating improvements in usability compared to fixed-threshold toxicity-filtering of model outputs. Future work should explore the intersection of toxicity scoring, model controllability, user agency, and language reclamation processes -- particularly with regard to the bias that many communities encounter when interacting with generative language models.
Distilling large, unstructured text into a structured, condensed form such as tables is an open research problem. One of the primary challenges in automatically generating tables is ensuring their syntactic validity. Prior approaches address this challenge by including additional parameters in the Transformer's attention mechanism to attend to specific rows and column headers. In contrast to this single-stage method, this paper presents a two-stage approach called Generative Tables (gTBLS). The first stage infers table structure (row and column headers) from the text. The second stage formulates questions using these headers and fine-tunes a causal language model to answer them. Furthermore, the gTBLS approach is amenable to the utilization of pre-trained Large Language Models in a zero-shot configuration, presenting a solution for table generation in situations where fine-tuning is not feasible. gTBLS improves prior approaches by up to 10% in BERTScore on the table construction task and up to 20% on the table content generation task of the E2E, WikiTableText, WikiBio, and RotoWire datasets.
Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explore whether it is feasible to drop the requirement that users must begin each command with a trigger phrase. We explore this task in three ways: First, we train classifiers using only acoustic information obtained from the audio waveform. Second, we take the decoder outputs of an automatic speech recognition (ASR) system, such as 1-best hypotheses, as input features to a large language model (LLM). Finally, we explore a multimodal system that combines acoustic and lexical features, as well as ASR decoder signals in an LLM. Using multimodal information yields relative equal-error-rate improvements over text-only and audio-only models of up to 39% and 61%. Increasing the size of the LLM and training with low-rank adaption leads to further relative EER reductions of up to 18% on our dataset.
We propose a Regularized Adaptive Momentum Dual Averaging (RAMDA) algorithm for training structured neural networks. Similar to existing regularized adaptive methods, the subproblem for computing the update direction of RAMDA involves a nonsmooth regularizer and a diagonal preconditioner, and therefore does not possess a closed-form solution in general. We thus also carefully devise an implementable inexactness condition that retains convergence guarantees similar to the exact versions, and propose a companion efficient solver for the subproblems of both RAMDA and existing methods to make them practically feasible. We leverage the theory of manifold identification in variational analysis to show that, even in the presence of such inexactness, the iterates of RAMDA attain the ideal structure induced by the regularizer at the stationary point of asymptotic convergence. This structure is locally optimal near the point of convergence, so RAMDA is guaranteed to obtain the best structure possible among all methods converging to the same point, making it the first regularized adaptive method outputting models that possess outstanding predictive performance while being (locally) optimally structured. Extensive numerical experiments in large-scale modern computer vision, language modeling, and speech tasks show that the proposed RAMDA is efficient and consistently outperforms state of the art for training structured neural network. Implementation of our algorithm is available at https://www.github.com/ismoptgroup/RAMDA/.