Hallucination is often regarded as a major impediment for using large language models (LLMs), especially for knowledge-intensive tasks. Even when the training corpus consists solely of true statements, language models still generate hallucinations in the form of amalgamations of multiple facts. We coin this phenomenon as ``knowledge overshadowing'': when we query knowledge from a language model with multiple conditions, some conditions overshadow others, leading to hallucinated outputs. This phenomenon partially stems from training data imbalance, which we verify on both pretrained models and fine-tuned models, over a wide range of LM model families and sizes.From a theoretical point of view, knowledge overshadowing can be interpreted as over-generalization of the dominant conditions (patterns). We show that the hallucination rate grows with both the imbalance ratio (between the popular and unpopular condition) and the length of dominant condition description, consistent with our derived generalization bound. Finally, we propose to utilize overshadowing conditions as a signal to catch hallucination before it is produced, along with a training-free self-contrastive decoding method to alleviate hallucination during inference. Our proposed approach showcases up to 82% F1 for hallucination anticipation and 11.2% to 39.4% hallucination control, with different models and datasets.
Significant interests have recently risen in leveraging sequence-based large language models (LLMs) for drug design. However, most current applications of LLMs in drug discovery lack the ability to comprehend three-dimensional (3D) structures, thereby limiting their effectiveness in tasks that explicitly involve molecular conformations. In this study, we introduced Token-Mol, a token-only 3D drug design model. This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in drug discovery into probabilistic prediction problems, thereby enabling learning through a unified paradigm. Token-Mol is built on the transformer decoder architecture and trained using random causal masking techniques. Additionally, we proposed the Gaussian cross-entropy (GCE) loss function to overcome the challenges in regression tasks, significantly enhancing the capacity of LLMs to learn continuous numerical values. Through a combination of fine-tuning and reinforcement learning (RL), Token-Mol achieves performance comparable to or surpassing existing task-specific methods across various downstream tasks, including pocket-based molecular generation, conformation generation, and molecular property prediction. Compared to existing molecular pre-trained models, Token-Mol exhibits superior proficiency in handling a wider range of downstream tasks essential for drug design. Notably, our approach improves regression task accuracy by approximately 30% compared to similar token-only methods. Token-Mol overcomes the precision limitations of token-only models and has the potential to integrate seamlessly with general models such as ChatGPT, paving the way for the development of a universal artificial intelligence drug design model that facilitates rapid and high-quality drug design by experts.
Few-shot prompting and step-by-step reasoning have enhanced the capabilities of Large Language Models (LLMs) in tackling complex tasks including code generation. In this paper, we introduce a prompt selection and augmentation algorithm aimed at improving mathematical reasoning and robot arm operations. Our approach incorporates a multi-stage example augmentation scheme combined with an example selection scheme. This algorithm improves LLM performance by selecting a set of examples that increase diversity, minimize redundancy, and increase relevance to the question. When combined with the Program-of-Thought prompting, our algorithm demonstrates an improvement in performance on the GSM8K and SVAMP benchmarks, with increases of 0.3% and 1.1% respectively. Furthermore, in simulated tabletop environments, our algorithm surpasses the Code-as-Policies approach by achieving a 3.4% increase in successful task completions and a decrease of over 70% in the number of examples used. Its ability to discard examples that contribute little to solving the problem reduces the inferencing time of an LLM-powered robotics system. This algorithm also offers important benefits for industrial process automation by streamlining the development and deployment process, reducing manual programming effort, and enhancing code reusability.
CLIP, as a vision-language model, has significantly advanced Open-Vocabulary Semantic Segmentation (OVSS) with its zero-shot capabilities. Despite its success, its application to OVSS faces challenges due to its initial image-level alignment training, which affects its performance in tasks requiring detailed local context. Our study delves into the impact of CLIP's [CLS] token on patch feature correlations, revealing a dominance of "global" patches that hinders local feature discrimination. To overcome this, we propose CLIPtrase, a novel training-free semantic segmentation strategy that enhances local feature awareness through recalibrated self-correlation among patches. This approach demonstrates notable improvements in segmentation accuracy and the ability to maintain semantic coherence across objects.Experiments show that we are 22.3% ahead of CLIP on average on 9 segmentation benchmarks, outperforming existing state-of-the-art training-free methods.The code are made publicly available at: https://github.com/leaves162/CLIPtrase.
Thermal infrared (TIR) tracking is pivotal in computer vision tasks due to its all-weather imaging capability. Traditional tracking methods predominantly rely on hand-crafted features, and while deep learning has introduced correlation filtering techniques, these are often constrained by rudimentary correlation operations. Furthermore, transformer-based approaches tend to overlook temporal and coordinate information, which is critical for TIR tracking that lacks texture and color information. In this paper, to address these issues, we apply natural language modeling to TIR tracking and propose a coordinate-aware thermal infrared tracking model called NLMTrack, which enhances the utilization of coordinate and temporal information. NLMTrack applies an encoder that unifies feature extraction and feature fusion, which simplifies the TIR tracking pipeline. To address the challenge of low detail and low contrast in TIR images, on the one hand, we design a multi-level progressive fusion module that enhances the semantic representation and incorporates multi-scale features. On the other hand, the decoder combines the TIR features and the coordinate sequence features using a causal transformer to generate the target sequence step by step. Moreover, we explore an adaptive loss aimed at elevating tracking accuracy and a simple template update strategy to accommodate the target's appearance variations. Experiments show that NLMTrack achieves state-of-the-art performance on multiple benchmarks. The Code is publicly available at \url{https://github.com/ELOESZHANG/NLMTrack}.
Understanding of video creativity and content often varies among individuals, with differences in focal points and cognitive levels across different ages, experiences, and genders. There is currently a lack of research in this area, and most existing benchmarks suffer from several drawbacks: 1) a limited number of modalities and answers with restrictive length; 2) the content and scenarios within the videos are excessively monotonous, transmitting allegories and emotions that are overly simplistic. To bridge the gap to real-world applications, we introduce a large-scale Subjective Response Indicators for Advertisement Videos dataset, namely SRI-ADV. Specifically, we collected real changes in Electroencephalographic (EEG) and eye-tracking regions from different demographics while they viewed identical video content. Utilizing this multi-modal dataset, we developed tasks and protocols to analyze and evaluate the extent of cognitive understanding of video content among different users. Along with the dataset, we designed a Hypergraph Multi-modal Large Language Model (HMLLM) to explore the associations among different demographics, video elements, EEG, and eye-tracking indicators. HMLLM could bridge semantic gaps across rich modalities and integrate information beyond different modalities to perform logical reasoning. Extensive experimental evaluations on SRI-ADV and other additional video-based generative performance benchmarks demonstrate the effectiveness of our method. The codes and dataset will be released at https://github.com/mininglamp-MLLM/HMLLM.
The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws forth an urgent demand for an effective training paradigm and a large-scale, comprehensive dataset with detailed CoT rationales, which is challenging to collect and costly to annotate manually. To tackle this issue, we propose MAVIS, a MAthematical VISual instruction tuning pipeline for MLLMs, featuring an automatic data engine to efficiently create mathematical visual datasets. We design the data generation process to be entirely independent of human intervention or GPT API usage, while ensuring the diagram-caption correspondence, question-answer correctness, and CoT reasoning quality. With this approach, we curate two datasets, MAVIS-Caption (558K diagram-caption pairs) and MAVIS-Instruct (834K visual math problems with CoT rationales), and propose four progressive stages for training MLLMs from scratch. First, we utilize MAVIS-Caption to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Second, we also leverage MAVIS-Caption to align the CLIP-Math with a large language model (LLM) by a projection layer, enhancing vision-language alignment in mathematical domains. Third, we adopt MAVIS-Instruct to perform the instruction tuning for robust problem-solving skills, and term the resulting model as MAVIS-7B. Fourth, we apply Direct Preference Optimization (DPO) to enhance the CoT capabilities of our model, further refining its step-wise reasoning performance. Code and data will be released at https://github.com/ZrrSkywalker/MAVIS
With the remarkable advancements in image generation and open-form text generation, the creation of interleaved image-text content has become an increasingly intriguing field. Multimodal story generation, characterized by producing narrative texts and vivid images in an interleaved manner, has emerged as a valuable and practical task with broad applications. However, this task poses significant challenges, as it necessitates the comprehension of the complex interplay between texts and images, and the ability to generate long sequences of coherent, contextually relevant texts and visuals. In this work, we propose SEED-Story, a novel method that leverages a Multimodal Large Language Model (MLLM) to generate extended multimodal stories. Our model, built upon the powerful comprehension capability of MLLM, predicts text tokens as well as visual tokens, which are subsequently processed with an adapted visual de-tokenizer to produce images with consistent characters and styles. We further propose multimodal attention sink mechanism to enable the generation of stories with up to 25 sequences (only 10 for training) in a highly efficient autoregressive manner. Additionally, we present a large-scale and high-resolution dataset named StoryStream for training our model and quantitatively evaluating the task of multimodal story generation in various aspects.
This paper presents the development and comparative evaluation of three voice command pipelines for controlling a Tello drone, using speech recognition and deep learning techniques. The aim is to enhance human-machine interaction by enabling intuitive voice control of drone actions. The pipelines developed include: (1) a traditional Speech-to-Text (STT) followed by a Large Language Model (LLM) approach, (2) a direct voice-to-function mapping model, and (3) a Siamese neural network-based system. Each pipeline was evaluated based on inference time, accuracy, efficiency, and flexibility. Detailed methodologies, dataset preparation, and evaluation metrics are provided, offering a comprehensive analysis of each pipeline's strengths and applicability across different scenarios.
This paper introduces a novel approach to integrating large language model (LLM) agents into automated production systems, aimed at enhancing task automation and flexibility. We organize production operations within a hierarchical framework based on the automation pyramid. Atomic operation functionalities are modeled as microservices, which are executed through interface invocation within a dedicated digital twin system. This allows for a scalable and flexible foundation for orchestrating production processes. In this digital twin system, low-level, hardware-specific data is semantically enriched and made interpretable for LLMs for production planning and control tasks. Large language model agents are systematically prompted to interpret these production-specific data and knowledge. Upon receiving a user request or identifying a triggering event, the LLM agents generate a process plan. This plan is then decomposed into a series of atomic operations, executed as microservices within the real-world automation system. We implement this overall approach on an automated modular production facility at our laboratory, demonstrating how the LLMs can handle production planning and control tasks through a concrete case study. This results in an intuitive production facility with higher levels of task automation and flexibility. Finally, we reveal the several limitations in realizing the full potential of the large language models in autonomous systems and point out promising benefits. Demos of this series of ongoing research series can be accessed at: https://github.com/YuchenXia/GPT4IndustrialAutomation
This study applies Natural Language Processing techniques, including Latent Dirichlet Allocation, to analyse anonymised maternity incident investigation reports from the Healthcare Safety Investigation Branch. The reports underwent preprocessing, annotation using the Safety Intelligence Research taxonomy, and topic modelling to uncover prevalent topics and detect differences in maternity care across ethnic groups. A combination of offline and online methods was utilised to ensure data protection whilst enabling advanced analysis, with offline processing for sensitive data and online processing for non-sensitive data using the `Claude 3 Opus' language model. Interactive topic analysis and semantic network visualisation were employed to extract and display thematic topics and visualise semantic relationships among keywords. The analysis revealed disparities in care among different ethnic groups, with distinct focus areas for the Black, Asian, and White British ethnic groups. The study demonstrates the effectiveness of topic modelling and NLP techniques in analysing maternity incident investigation reports and highlighting disparities in care. The findings emphasise the crucial role of advanced data analysis in improving maternity care quality and equity.
Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices. Visual models that are continually updated through supervised learning are often prone to overfitting, catastrophic forgetting, and biased representations. On the other hand, large language models contain knowledge about multiple concepts and their relations, which can foster a more robust, informed and coherent learning process. This work proposes Continual Visual Mapping (CVM), an approach that continually ground vision representations to a knowledge space extracted from a fixed Language model. Specifically, CVM continually trains a small and efficient visual model to map its representations into a conceptual space established by a fixed Large Language Model. Due to their smaller nature, CVM can be used when directly adapting large visual pre-trained models is unfeasible due to computational or data constraints. CVM overcome state-of-the-art continual learning methods on five benchmarks and offers a promising avenue for addressing generalization capabilities in continual learning, even in computationally constrained devices.
Communication network engineering in enterprise environments is traditionally a complex, time-consuming, and error-prone manual process. Most research on network engineering automation has concentrated on configuration synthesis, often overlooking changes in the physical network topology. This paper introduces GeNet, a multimodal co-pilot for enterprise network engineers. GeNet is a novel framework that leverages a large language model (LLM) to streamline network design workflows. It uses visual and textual modalities to interpret and update network topologies and device configurations based on user intents. GeNet was evaluated on enterprise network scenarios adapted from Cisco certification exercises. Our results demonstrate GeNet's ability to interpret network topology images accurately, potentially reducing network engineers' efforts and accelerating network design processes in enterprise environments. Furthermore, we show the importance of precise topology understanding when handling intents that require modifications to the network's topology.
Training language models becomes increasingly expensive with scale, prompting numerous attempts to improve optimization efficiency. Despite these efforts, the Adam optimizer remains the most widely used, due to a prevailing view that it is the most effective approach. We aim to compare several optimization algorithms, including SGD, Adafactor, Adam, and Lion, in the context of autoregressive language modeling across a range of model sizes, hyperparameters, and architecture variants. Our findings indicate that, except for SGD, these algorithms all perform comparably both in their optimal performance and also in terms of how they fare across a wide range of hyperparameter choices. Our results suggest to practitioners that the choice of optimizer can be guided by practical considerations like memory constraints and ease of implementation, as no single algorithm emerged as a clear winner in terms of performance or stability to hyperparameter misspecification. Given our findings, we further dissect these approaches, examining two simplified versions of Adam: a) signed momentum (Signum) which we see recovers both the performance and hyperparameter stability of Adam and b) Adalayer, a layerwise variant of Adam which we introduce to study Adam's preconditioning. Examining Adalayer leads us to the conclusion that the largest impact of Adam's preconditioning is restricted to the last layer and LayerNorm parameters, and, perhaps surprisingly, the remaining layers can be trained with SGD.
Novice researchers often face difficulties in understanding a multitude of academic papers and grasping the fundamentals of a new research field. To solve such problems, the knowledge graph supporting research survey is gradually being developed. Existing keyword-based knowledge graphs make it difficult for researchers to deeply understand abstract concepts. Meanwhile, novice researchers may find it difficult to use ChatGPT effectively for research surveys due to their limited understanding of the research field. Without the ability to ask proficient questions that align with key concepts, obtaining desired and accurate answers from this large language model (LLM) could be inefficient. This study aims to help novice researchers by providing a fish-bone diagram that includes causal relationships, offering an overview of the research topic. The diagram is constructed using the issue ontology from academic papers, and it offers a broad, highly generalized perspective of the research field, based on relevance and logical factors. Furthermore, we evaluate the strengths and improvable points of the fish-bone diagram derived from this study's development pattern, emphasizing its potential as a viable tool for supporting research survey.
In this work, we introduce LokiLM, a 1.4B parameter large language model trained on 500B tokens. Our model performs strongly in natural language reasoning tasks and achieves state-of-the-art performance among models with 1.5B parameters or less. LokiLM is trained using multi-teacher knowledge distillation and high-quality training data to achieve benchmark results competitive with larger models trained on significantly more tokens. We support these findings by introducing steps to avoid benchmark contamination and overfitting throughout our development process. Despite its promising performance, LokiLM exhibits a concerning amount of hallucinations and scores poorly on the TruthfulQA benchmark, so we do not release the model publicly.
Recently, vision-language pre-trained models have emerged in computational pathology. Previous works generally focused on the alignment of image-text pairs via the contrastive pre-training paradigm. Such pre-trained models have been applied to pathology image classification in zero-shot learning or transfer learning fashion. Herein, we hypothesize that the pre-trained vision-language models can be utilized for quantitative histopathology image analysis through a simple image-to-text retrieval. To this end, we propose a Text-based Quantitative and Explainable histopathology image analysis, which we call TQx. Given a set of histopathology images, we adopt a pre-trained vision-language model to retrieve a word-of-interest pool. The retrieved words are then used to quantify the histopathology images and generate understandable feature embeddings due to the direct mapping to the text description. To evaluate the proposed method, the text-based embeddings of four histopathology image datasets are utilized to perform clustering and classification tasks. The results demonstrate that TQx is able to quantify and analyze histopathology images that are comparable to the prevalent visual models in computational pathology.
This technical report presents the implementation of a state-of-the-art video encoder for video-text modal alignment and a video conversation framework called HiLight, which features dual visual towers. The work is divided into two main parts: 1.alignment of video and text modalities; 2.convenient and efficient way to interact with users. Our goal is to address the task of video comprehension in the context of billiards. The report includes a discussion of the concepts and the final solution developed during the task's implementation.
We study a fundamental problem in the evaluation of large language models that we call training on the test task. Unlike wrongful practices like training on the test data, leakage, or data contamination, training on the test task is not a malpractice. Rather, the term describes a growing set of practices that utilize knowledge about evaluation tasks at training time. We demonstrate that training on the test task confounds both relative model evaluations and claims about emergent capabilities. We argue that the seeming superiority of one model family over another may be explained by a different degree of training on the test task. To this end, we propose an effective method to adjust for the effect of training on the test task on benchmark evaluations. Put simply, to fine-tune each model under comparison on the same task-relevant data prior to evaluation. We then show that instances of emergent behavior disappear gradually as models train on the test task. Our work promotes a new perspective on the evaluation of large language models, with broad implications for benchmarking and the study of emergent capabilities.
PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly knowledgeable base model that is effective to transfer. It achieves strong performance on a wide variety of open-world tasks. We evaluate PaliGemma on almost 40 diverse tasks including standard VLM benchmarks, but also more specialized tasks such as remote-sensing and segmentation.