In-Context Learning (ICL) and Instruction Tuning (IT) are two primary paradigms of adopting Large Language Models (LLMs) to downstream applications. However, they are significantly different. In ICL, a set of demonstrations are provided at inference time but the LLM's parameters are not updated. In IT, a set of demonstrations are used to tune LLM's parameters in training time but no demonstrations are used at inference time. Although a growing body of literature has explored ICL and IT, studies on these topics have largely been conducted in isolation, leading to a disconnect between these two paradigms. In this work, we explore the relationship between ICL and IT by examining how the hidden states of LLMs change in these two paradigms. Through carefully designed experiments conducted with LLaMA-2 (7B and 13B), we find that ICL is implicit IT. In other words, ICL changes an LLM's hidden states as if the demonstrations were used to instructionally tune the model. Furthermore, the convergence between ICL and IT is largely contingent upon several factors related to the provided demonstrations. Overall, this work offers a unique perspective to explore the connection between ICL and IT and sheds light on understanding the behaviors of LLM.
相關內容
Parameter-efficient tuning (PET) methods such as LoRA, Adapter, and Visual Prompt Tuning (VPT) have found success in enabling adaptation to new domains by tuning small modules within a transformer model. However, the number of domains encountered during test time can be very large, and the data is usually unlabeled. Thus, adaptation to new domains is challenging; it is also impractical to generate customized tuned modules for each such domain. Toward addressing these challenges, this work introduces PLUTO: a Plug-and-pLay modUlar Test-time domain adaptatiOn strategy. We pre-train a large set of modules, each specialized for different source domains, effectively creating a ``module store''. Given a target domain with few-shot unlabeled data, we introduce an unsupervised test-time adaptation (TTA) method to (1) select a sparse subset of relevant modules from this store and (2) create a weighted combination of selected modules without tuning their weights. This plug-and-play nature enables us to harness multiple most-relevant source domains in a single inference call. Comprehensive evaluations demonstrate that PLUTO uniformly outperforms alternative TTA methods and that selecting $\leq$5 modules suffice to extract most of the benefit. At a high level, our method equips pre-trained transformers with the capability to dynamically adapt to new domains, motivating a new paradigm for efficient and scalable domain adaptation.
In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations. Despite the great success of ICL, the limitation of the demonstration number may lead to demonstration bias, i.e. the input-label mapping induced by LLMs misunderstands the task's essence. Inspired by human experience, we attempt to mitigate such bias through the perspective of the inter-demonstration relationship. Specifically, we construct Comparable Demonstrations (CDs) by minimally editing the texts to flip the corresponding labels, in order to highlight the task's essence and eliminate potential spurious correlations through the inter-demonstration comparison. Through a series of experiments on CDs, we find that (1) demonstration bias does exist in LLMs, and CDs can significantly reduce such bias; (2) CDs exhibit good performance in ICL, especially in out-of-distribution scenarios. In summary, this study explores the ICL mechanisms from a novel perspective, providing a deeper insight into the demonstration selection strategy for ICL.
Knowledge Representation (KR) and facet-analytical Knowledge Organization (KO) have been the two most prominent methodologies of data and knowledge modelling in the Artificial Intelligence community and the Information Science community, respectively. KR boasts of a robust and scalable ecosystem of technologies to support knowledge modelling while, often, underemphasizing the quality of its models (and model-based data). KO, on the other hand, is less technology-driven but has developed a robust framework of guiding principles (canons) for ensuring modelling (and model-based data) quality. This paper elucidates both the KR and facet-analytical KO methodologies in detail and provides a functional mapping between them. Out of the mapping, the paper proposes an integrated KO-enriched KR methodology with all the standard components of a KR methodology plus the guiding canons of modelling quality provided by KO. The practical benefits of the methodological integration has been exemplified through a prominent case study of KR-based image annotation exercise.
Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community, impacting various SE tasks from code completion to test generation, from program repair to code summarization. Despite their promise, researchers must still be careful as numerous intricate factors can influence the outcomes of experiments involving LLMs. This paper initiates an open discussion on potential threats to the validity of LLM-based research including issues such as closed-source models, possible data leakage between LLM training data and research evaluation, and the reproducibility of LLM-based findings. In response, this paper proposes a set of guidelines tailored for SE researchers and Language Model (LM) providers to mitigate these concerns. The implications of the guidelines are illustrated using existing good practices followed by LLM providers and a practical example for SE researchers in the context of test case generation.
Bioinformatics and Computational Biology are two fields that have been exploiting GPUs for more than two decades, being CUDA the most used programming language for them. However, as CUDA is an NVIDIA proprietary language, it implies a strong portability restriction to a wide range of heterogeneous architectures, like AMD or Intel GPUs. To face this issue, the Khronos Group has recently proposed the SYCL standard, which is an open, royalty-free, cross-platform abstraction layer, that enables the programming of a heterogeneous system to be written using standard, single-source C++ code. Over the past few years, several implementations of this SYCL standard have emerged, being oneAPI the one from Intel. This paper presents the migration process of the SW\# suite, a biological sequence alignment tool developed in CUDA, to SYCL using Intel's oneAPI ecosystem. The experimental results show that SW\# was completely migrated with a small programmer intervention in terms of hand-coding. In addition, it was possible to port the migrated code between different architectures (considering multiple vendor GPUs and also CPUs), with no noticeable performance degradation on 5 different NVIDIA GPUs. Moreover, performance remained stable when switching to another SYCL implementation. As a consequence, SYCL and its implementations can offer attractive opportunities for the Bioinformatics community, especially considering the vast existence of CUDA-based legacy codes.
Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months. The prevailing trend involves adopting data-driven methodologies, wherein diverse instruction-following datasets are collected. However, a prevailing challenge persists in these approaches, specifically in relation to the limited visual perception ability, as CLIP-like encoders employed for extracting visual information from inputs. Though these encoders are pre-trained on billions of image-text pairs, they still grapple with the information loss dilemma, given that textual captions only partially capture the contents depicted in images. To address this limitation, this paper proposes to improve the visual perception ability of MLLMs through a mixture-of-experts knowledge enhancement mechanism. Specifically, we introduce a novel method that incorporates multi-task encoders and visual tools into the existing MLLMs training and inference pipeline, aiming to provide a more comprehensive and accurate summarization of visual inputs. Extensive experiments have evaluated its effectiveness of advancing MLLMs, showcasing improved visual perception achieved through the integration of visual experts.
In this paper, we conducted a comparative evaluation of three RGB-D SLAM (Simultaneous Localization and Mapping) algorithms: RTAB-Map, ORB-SLAM3, and OpenVSLAM for SURENA-V humanoid robot localization and mapping. Our test involves the robot to follow a full circular pattern, with an Intel RealSense D435 RGB-D camera installed on its head. In assessing localization accuracy, ORB-SLAM3 outperformed the others with an ATE of 0.1073, followed by RTAB-Map at 0.1641 and OpenVSLAM at 0.1847. However, it should be noted that both ORB-SLAM3 and OpenVSLAM faced challenges in maintaining accurate odometry when the robot encountered a wall with limited feature points. Nevertheless, OpenVSLAM demonstrated the ability to detect loop closures and successfully relocalize itself within the map when the robot approached its initial location. The investigation also extended to mapping capabilities, where RTAB-Map excelled by offering diverse mapping outputs, including dense, OctoMap, and occupancy grid maps. In contrast, both ORB-SLAM3 and OpenVSLAM provided only sparse maps.
In the realm of computer systems, efficient utilisation of the CPU (Central Processing Unit) has always been a paramount concern. Researchers and engineers have long sought ways to optimise process execution on the CPU, leading to the emergence of CPU scheduling as a field of study. This research proposes a novel algorithm for batch processing that operates on a preemptive model, dynamically assigning priorities based on a robust ratio, employing a dynamic time slice, and utilising periodic sorting technique to achieve fairness. By engineering this responsive and fair model, the proposed algorithm strikes a delicate balance between efficiency and fairness, providing an optimised solution for batch scheduling while ensuring system responsiveness.
Automated Planning and Scheduling is among the growing areas in Artificial Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive review of 126 papers, this paper investigates eight categories based on the unique applications of LLMs in addressing various aspects of planning problems: language translation, plan generation, model construction, multi-agent planning, interactive planning, heuristics optimization, tool integration, and brain-inspired planning. For each category, we articulate the issues considered and existing gaps. A critical insight resulting from our review is that the true potential of LLMs unfolds when they are integrated with traditional symbolic planners, pointing towards a promising neuro-symbolic approach. This approach effectively combines the generative aspects of LLMs with the precision of classical planning methods. By synthesizing insights from existing literature, we underline the potential of this integration to address complex planning challenges. Our goal is to encourage the ICAPS community to recognize the complementary strengths of LLMs and symbolic planners, advocating for a direction in automated planning that leverages these synergistic capabilities to develop more advanced and intelligent planning systems.
Explainable Artificial Intelligence (XAI) is transforming the field of Artificial Intelligence (AI) by enhancing the trust of end-users in machines. As the number of connected devices keeps on growing, the Internet of Things (IoT) market needs to be trustworthy for the end-users. However, existing literature still lacks a systematic and comprehensive survey work on the use of XAI for IoT. To bridge this lacking, in this paper, we address the XAI frameworks with a focus on their characteristics and support for IoT. We illustrate the widely-used XAI services for IoT applications, such as security enhancement, Internet of Medical Things (IoMT), Industrial IoT (IIoT), and Internet of City Things (IoCT). We also suggest the implementation choice of XAI models over IoT systems in these applications with appropriate examples and summarize the key inferences for future works. Moreover, we present the cutting-edge development in edge XAI structures and the support of sixth-generation (6G) communication services for IoT applications, along with key inferences. In a nutshell, this paper constitutes the first holistic compilation on the development of XAI-based frameworks tailored for the demands of future IoT use cases.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191