Utilizing Large Language Models (LLMs) as evaluators for evaluating the performance of LLMs has recently garnered attention. However, this kind of evaluation approach is affected by potential biases in LLMs, raising concerns about the accuracy and reliability of the evaluation results. To mitigate this issue, we propose and study two many-shot ICL prompts, which rely on two versions of many-shot ICL prompt templates for helping LLM evaluators to mitigate the potential biases in LLMs, \textbf{M}any-\textbf{S}hot \textbf{w}ith \textbf{R}eference (\textbf{MSwR}) and \textbf{M}any-\textbf{S}hot with\textbf{o}ut \textbf{R}eference (\textbf{MSoR}). Concretely, the former utilizes in-context examples with model-generated rationales as guidance, and the latter without. Based on the designed prompts, we investigate the impact of scaling the number of in-context examples on the consistency and quality of the evaluation results. Experimental results show that advanced LLMs, such as GPT-4o, perform better in the many-shot regime than in the zero-shot regime. Furthermore, we reveal the symbol bias hidden in the selection bias of LLMs and propose a simple yet effective approach to mitigate the bias. Experimental results further verify the effectiveness of the symbol bias mitigation approach.
相關內容
Large Language Models (LLMs), typified by OpenAI's GPT, have marked a significant advancement in artificial intelligence. Trained on vast amounts of text data, LLMs are capable of understanding and generating human-like text across a diverse range of topics. This study expands on the applications of LLMs, exploring their potential in data preprocessing, a critical stage in data mining and analytics applications. Aiming at tabular data, we delve into the applicability of state-of-the-art LLMs such as GPT-4 and GPT-4o for a series of preprocessing tasks, including error detection, data imputation, schema matching, and entity matching. Alongside showcasing the inherent capabilities of LLMs, we highlight their limitations, particularly in terms of computational expense and inefficiency. We propose an LLM-based framework for data preprocessing, which integrates cutting-edge prompt engineering techniques, coupled with traditional methods like contextualization and feature selection, to improve the performance and efficiency of these models. The effectiveness of LLMs in data preprocessing is evaluated through an experimental study spanning a variety of public datasets. GPT-4 emerged as a standout, achieving 100\% accuracy or F1 score on 4 of these datasets, suggesting LLMs' immense potential in these tasks. Despite certain limitations, our study underscores the promise of LLMs in this domain and anticipates future developments to overcome current hurdles.
The Transformer model has demonstrated success across a wide range of domains, including in Multi-Agent Reinforcement Learning (MARL) where the Multi-Agent Transformer (MAT) has emerged as a leading algorithm in the field. The Transformer model has demonstrated success across a wide range of domains, including in Multi-Agent Reinforcement Learning (MARL) where the Multi-Agent Transformer (MAT) has emerged as a leading algorithm in the field. However, a significant drawback of Transformer models is their quadratic computational complexity relative to input size, making them computationally expensive when scaling to larger inputs. This limitation restricts MAT's scalability in environments with many agents. Recently, State-Space Models (SSMs) have gained attention due to their computational efficiency, but their application in MARL remains unexplored. In this work, we investigate the use of Mamba, a recent SSM, in MARL and assess whether it can match the performance of MAT while providing significant improvements in efficiency. We introduce a modified version of MAT that incorporates standard and bi-directional Mamba blocks, as well as a novel "cross-attention" Mamba block. Extensive testing shows that our Multi-Agent Mamba (MAM) matches the performance of MAT across multiple standard multi-agent environments, while offering superior scalability to larger agent scenarios. This is significant for the MARL community, because it indicates that SSMs could replace Transformers without compromising performance, whilst also supporting more effective scaling to higher numbers of agents. Our project page is available at //sites.google.com/view/multi-agent-mamba .
Spike Timing-Dependent Plasticity (STDP) is a promising substitute to backpropagation for local training of Spiking Neural Networks (SNNs) on neuromorphic hardware. STDP allows SNNs to address classification tasks by combining unsupervised STDP for feature extraction and supervised STDP for classification. Unsupervised STDP is usually employed with Winner-Takes-All (WTA) competition to learn distinct patterns. However, WTA for supervised STDP classification faces unbalanced competition challenges. In this paper, we propose a method to effectively implement WTA competition in a spiking classification layer employing first-spike coding and supervised STDP training. We introduce the Neuronal Competition Group (NCG), an architecture that improves classification capabilities by promoting the learning of various patterns per class. An NCG is a group of neurons mapped to a specific class, implementing intra-class WTA and a novel competition regulation mechanism based on two-compartment thresholds. We incorporate our proposed architecture into spiking classification layers trained with state-of-the-art supervised STDP rules. On top of two different unsupervised feature extractors, we obtain significant accuracy improvements on image recognition datasets such as CIFAR-10 and CIFAR-100. We show that our competition regulation mechanism is crucial for ensuring balanced competition and improved class separation.
Geospatial Knowledge Graphs (GeoKGs) have become integral to the growing field of Geospatial Artificial Intelligence. Initiatives like the U.S. National Science Foundation's Open Knowledge Network program aim to create an ecosystem of nation-scale, cross-disciplinary GeoKGs that provide AI-ready geospatial data aligned with FAIR principles. However, building this infrastructure presents key challenges, including 1) managing large volumes of data, 2) the computational complexity of discovering topological relations via SPARQL, and 3) conflating multi-scale raster and vector data. Discrete Global Grid Systems (DGGS) help tackle these issues by offering efficient data integration and representation strategies. The KnowWhereGraph utilizes Google's S2 Geometry -- a DGGS framework -- to enable efficient multi-source data processing, qualitative spatial querying, and cross-graph integration. This paper outlines the implementation of S2 within KnowWhereGraph, emphasizing its role in topologically enriching and semantically compressing data. Ultimately, this work demonstrates the potential of DGGS frameworks, particularly S2, for building scalable GeoKGs.
Sparse Principal Component Analysis (Sparse PCA) is a pivotal tool in data analysis and dimensionality reduction. However, Sparse PCA is a challenging problem in both theory and practice: it is known to be NP-hard and current exact methods generally require exponential runtime. In this paper, we propose a novel framework to efficiently approximate Sparse PCA by (i) approximating the general input covariance matrix with a re-sorted block-diagonal matrix, (ii) solving the Sparse PCA sub-problem in each block, and (iii) reconstructing the solution to the original problem. Our framework is simple and powerful: it can leverage any off-the-shelf Sparse PCA algorithm and achieve significant computational speedups, with a minor additive error that is linear in the approximation error of the block-diagonal matrix. Suppose $g(k, d)$ is the runtime of an algorithm (approximately) solving Sparse PCA in dimension $d$ and with sparsity value $k$. Our framework, when integrated with this algorithm, reduces the runtime to $\mathcal{O}\left(\frac{d}{d^\star} \cdot g(k, d^\star) + d^2\right)$, where $d^\star \leq d$ is the largest block size of the block-diagonal matrix. For instance, integrating our framework with the Branch-and-Bound algorithm reduces the complexity from $g(k, d) = \mathcal{O}(k^3\cdot d^k)$ to $\mathcal{O}(k^3\cdot d \cdot (d^\star)^{k-1})$, demonstrating exponential speedups if $d^\star$ is small. We perform large-scale evaluations on many real-world datasets: for exact Sparse PCA algorithm, our method achieves an average speedup factor of 93.77, while maintaining an average approximation error of 2.15%; for approximate Sparse PCA algorithm, our method achieves an average speedup factor of 6.77 and an average approximation error of merely 0.37%.
Autism Spectrum Disorder (ASD) is a neurodivergent condition with a wide range of characteristics and support levels. Individuals with ASD can exhibit various combinations of traits such as difficulties in social interaction, communication, and language, alongside restricted interests and repetitive activities. Many adults with ASD live independently due to increased awareness and late diagnoses, which help them manage long-standing challenges. Predictability, clarity, and minimized sensory stimuli are crucial for the daily comfort of autistic individuals. In mobile applications, autistic users face significant cognitive overload compared to neurotypicals, resulting in higher effort and time to complete tasks. Urban mobility apps, essential for daily routines, often overlook the needs of autistic users, leading to cognitive overload issues. This study investigates the accessibility of urban mobility apps for autistic individuals using the Interfaces Accessibility Guide for Autism (GAIA). By evaluating various apps, we have identified a common gap regarding accessibility for people with Autism Spectrum Disorder (ASD). This limitation relates to the absence of a functionality that allows users on the autism spectrum to customize the characteristics of the textual and visual elements of the software, such as changing the text font, altering the font type, and adjusting text colors, as well as native audio guidance within the applications themselves. Currently, the only function in this context is for visually impaired people, which completely changes the user experience in terms of navigation.
The following contribution introduces a concept that employs Large Language Models (LLMs) and a chatbot interface to enhance SPARQL query generation for ontologies, thereby facilitating intuitive access to formalized knowledge. Utilizing natural language inputs, the system converts user inquiries into accurate SPARQL queries that strictly query the factual content of the ontology, effectively preventing misinformation or fabrication by the LLM. To enhance the quality and precision of outcomes, additional textual information from established domain-specific standards is integrated into the ontology for precise descriptions of its concepts and relationships. An experimental study assesses the accuracy of generated SPARQL queries, revealing significant benefits of using LLMs for querying ontologies and highlighting areas for future research.
Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms prevalent in Western-centric datasets, and safety protocols frequently fail to extend to multilingual settings. In this work, we explore model merging in a diverse multi-task setting, combining safety and general-purpose tasks within a multilingual context. Each language introduces unique and varied learning challenges across tasks. We find that objective-based merging is more effective than mixing data, with improvements of up to 8% and 10% in general performance and safety respectively. We also find that language-based merging is highly effective -- by merging monolingually fine-tuned models, we achieve a 4% increase in general performance and 7% reduction in harm across all languages on top of the data mixtures method using the same available data. Overall, our comprehensive study of merging approaches provides a useful framework for building strong and safe multilingual models.
The rise of Large Language Models (LLMs) has revolutionized natural language processing across numerous languages and tasks. However, evaluating LLM performance in a consistent and meaningful way across multiple European languages remains challenging, especially due to the scarcity of multilingual benchmarks. We introduce a cross-lingual evaluation approach tailored for European languages. We employ translated versions of five widely-used benchmarks to assess the capabilities of 40 LLMs across 21 European languages. Our contributions include examining the effectiveness of translated benchmarks, assessing the impact of different translation services, and offering a multilingual evaluation framework for LLMs that includes newly created datasets: EU20-MMLU, EU20-HellaSwag, EU20-ARC, EU20-TruthfulQA, and EU20-GSM8K. The benchmarks and results are made publicly available to encourage further research in multilingual LLM evaluation.
With the bomb ignited by ChatGPT, Transformer-based Large Language Models (LLMs) have paved a revolutionary path toward Artificial General Intelligence (AGI) and have been applied in diverse areas as knowledge bases, human interfaces, and dynamic agents. However, a prevailing limitation exists: many current LLMs, constrained by resources, are primarily pre-trained on shorter texts, rendering them less effective for longer-context prompts, commonly encountered in real-world settings. In this paper, we present a comprehensive survey focusing on the advancement of model architecture in Transformer-based LLMs to optimize long-context capabilities across all stages from pre-training to inference. We firstly delineate and analyze the problems of handling long-context input and output with the current Transformer-based models. Then, we mainly offer a holistic taxonomy to navigate the landscape of Transformer upgrades on architecture to solve these problems. Afterward, we provide the investigation on wildly used evaluation necessities tailored for long-context LLMs, including datasets, metrics, and baseline models, as well as some amazing optimization toolkits like libraries, systems, and compilers to augment LLMs' efficiency and efficacy across different stages. Finally, we further discuss the predominant challenges and potential avenues for future research in this domain. Additionally, we have established a repository where we curate relevant literature with real-time updates at //github.com/Strivin0311/long-llms-learning.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191