PyTorchKR Papers

최신 논문

총 1,975편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2410.16518

Residues in Partial Fraction Decomposition Applied to Pole Sensitivity Analysis and Root Locus Construction

The applications of the partial fraction decomposition in control and systems engineering are several. In this letter, we propose a new interpretation of residues in the partial fraction decomposition, which is employed for the following purposes: to address the pole sensitivity problem, namely to study the speed of variation of the system poles when the control parameter changes and when the system is subject to parameters variations, as well as to propose a new algorithm for the construction of the root locus. The new algorithm is proven to be more efficient in terms of execution time than the dedicated MATLAB function, while providing the same output results.

arXiv:2410.16983

Order Matters: Exploring Order Sensitivity in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) utilize multimodal contexts consisting of text, images, or videos to solve various multimodal tasks. However, we find that changing the order of multimodal input can cause the model's performance to fluctuate between advanced performance and random guessing. This phenomenon exists in both single-modality (text-only or image-only) and mixed-modality (image-text-pair) contexts. Furthermore, we demonstrate that popular MLLMs pay special attention to certain multimodal context positions, particularly the beginning and end. Leveraging this special attention, we place key video frames and important image/text content in special positions within the context and submit them to the MLLM for inference. This method results in average performance gains of 14.7% for video-caption matching and 17.8% for visual question answering tasks. Additionally, we propose a new metric, Position-Invariant Accuracy (PIA), to address order bias in MLLM evaluation. Our research findings contribute to a better understanding of Multi-Modal In-Context Learning (MMICL) and provide practical strategies for enhancing MLLM performance without increasing computational costs.

arXiv:2410.16139

A Psycholinguistic Evaluation of Language Models' Sensitivity to Argument Roles

We present a systematic evaluation of large language models' sensitivity to argument roles, i.e., who did what to whom, by replicating psycholinguistic studies on human argument role processing. In three experiments, we find that language models are able to distinguish verbs that appear in plausible and implausible contexts, where plausibility is determined through the relation between the verb and its preceding arguments. However, none of the models capture the same selective patterns that human comprehenders exhibit during real-time verb prediction. This indicates that language models' capacity to detect verb plausibility does not arise from the same mechanism that underlies human real-time sentence processing.

arXiv:2410.15939공식 코드 · Papers with Code

CausalGraph2LLM: Evaluating LLMs for Causal Queries

Causality is essential in scientific research, enabling researchers to interpret true relationships between variables. These causal relationships are often represented by causal graphs, which are directed acyclic graphs. With the recent advancements in Large Language Models (LLMs), there is an increasing interest in exploring their capabilities in causal reasoning and their potential use to hypothesize causal graphs. These tasks necessitate the LLMs to encode the causal graph effectively for subsequent downstream tasks. In this paper, we propose a comprehensive benchmark, \emph{CausalGraph2LLM}, encompassing a variety of causal graph settings to assess the causal graph understanding capability of LLMs. We categorize the causal queries into two types: graph-level and node-level queries. We benchmark both open-sourced and closed models for our study. Our findings reveal that while LLMs show promise in this domain, they are highly sensitive to the encoding used. Even capable models like GPT-4 and Gemini-1.5 exhibit sensitivity to encoding, with deviations of about $60\%$. We further demonstrate this sensitivity for downstream causal intervention tasks. Moreover, we observe that LLMs can often display biases when presented with contextual information about a causal graph, potentially stemming from their parametric memory.

arXiv:2410.15176

Beyond Pruning Criteria: The Dominant Role of Fine-Tuning and Adaptive Ratios in Neural Network Robustness

Deep neural networks (DNNs) excel in tasks like image recognition and natural language processing, but their increasing complexity complicates deployment in resource-constrained environments and increases susceptibility to adversarial attacks. While traditional pruning methods reduce model size, they often compromise the network's ability to withstand subtle perturbations. This paper challenges the conventional emphasis on weight importance scoring as the primary determinant of a pruned network's performance. Through extensive analysis, including experiments conducted on CIFAR, Tiny-ImageNet, and various network architectures, we demonstrate that effective fine-tuning plays a dominant role in enhancing both performance and adversarial robustness, often surpassing the impact of the chosen pruning criteria. To address this issue, we introduce Module Robust Sensitivity, a novel metric that adaptively adjusts the pruning ratio for each network layer based on its sensitivity to adversarial perturbations. By integrating this metric into the pruning process, we develop a stable algorithm that maintains accuracy and robustness simultaneously. Experimental results show that our approach enables the practical deployment of more robust and efficient neural networks.

arXiv:2410.14838

Rank Suggestion in Non-negative Matrix Factorization: Residual Sensitivity to Initial Conditions (RSIC)

Determining the appropriate rank in Non-negative Matrix Factorization (NMF) is a critical challenge that often requires extensive parameter tuning and domain-specific knowledge. Traditional methods for rank determination focus on identifying a single optimal rank, which may not capture the complex structure inherent in real-world datasets. In this study, we introduce a novel approach called Residual Sensitivity to Intial Conditions (RSIC) that suggests potentially multiple ranks of interest by analyzing the sensitivity of the relative residuals (e.g. relative reconstruction error) to different initializations. By computing the Mean Coordinatewise Interquartile Range (MCI) of the residuals across multiple random initializations, our method identifies regions where the NMF solutions are less sensitive to initial conditions and potentially more meaningful. We evaluate RSIC on a diverse set of datasets, including single-cell gene expression data, image data, and text data, and compare it against current state-of-the-art existing rank determination methods. Our experiments demonstrate that RSIC effectively identifies relevant ranks consistent with the underlying structure of the data, outperforming traditional methods in scenarios where they are computationally infeasible or less accurate. This approach provides a more scalable and generalizable solution for rank determination in NMF that does not rely on domain-specific knowledge or assumptions.

arXiv:2410.16238

Deep Radiomics Detection of Clinically Significant Prostate Cancer on Multicenter MRI: Initial Comparison to PI-RADS Assessment

Objective: To develop and evaluate a deep radiomics model for clinically significant prostate cancer (csPCa, grade group >= 2) detection and compare its performance to Prostate Imaging Reporting and Data System (PI-RADS) assessment in a multicenter cohort. Materials and Methods: This retrospective study analyzed biparametric (T2W and DW) prostate MRI sequences of 615 patients (mean age, 63.1 +/- 7 years) from four datasets acquired between 2010 and 2020: PROSTATEx challenge, Prostate158 challenge, PCaMAP trial, and an in-house (NTNU/St. Olavs Hospital) dataset. With expert annotations as ground truth, a deep radiomics model was trained, including nnU-Net segmentation of the prostate gland, voxel-wise radiomic feature extraction, extreme gradient boost classification, and post-processing of tumor probability maps into csPCa detection maps. Training involved 5-fold cross-validation using the PROSTATEx (n=199), Prostate158 (n=138), and PCaMAP (n=78) datasets, and testing on the in-house (n=200) dataset. Patient- and lesion-level performance were compared to PI-RADS using area under ROC curve (AUROC [95% CI]), sensitivity, and specificity analysis. Results: On the test data, the radiologist achieved a patient-level AUROC of 0.94 [0.91-0.98] with 94% (75/80) sensitivity and 77% (92/120) specificity at PI-RADS >= 3. The deep radiomics model at a tumor probability cut-off >= 0.76 achieved 0.91 [0.86-0.95] AUROC with 90% (72/80) sensitivity and 73% (87/120) specificity, not significantly different (p = 0.068) from PI-RADS. On the lesion level, PI-RADS cut-off >= 3 had 84% (91/108) sensitivity at 0.2 (40/200) false positives per patient, while deep radiomics attained 68% (73/108) sensitivity at the same false positive rate. Conclusion: Deep radiomics machine learning model achieved comparable performance to PI-RADS assessment in csPCa detection at the patient-level but not at the lesion-level.

arXiv:2410.15229

Deep Learning-based Detection of Bacterial Swarm Motion Using a Single Image

Distinguishing between swarming and swimming, the two principal forms of bacterial movement, holds significant conceptual and clinical relevance. This is because bacteria that exhibit swarming capabilities often possess unique properties crucial to the pathogenesis of infectious diseases and may also have therapeutic potential. Here, we report a deep learning-based swarming classifier that rapidly and autonomously predicts swarming probability using a single blurry image. Compared with traditional video-based, manually-processed approaches, our method is particularly suited for high-throughput environments and provides objective, quantitative assessments of swarming probability. The swarming classifier demonstrated in our work was trained on Enterobacter sp. SM3 and showed good performance when blindly tested on new swarming (positive) and swimming (negative) test images of SM3, achieving a sensitivity of 97.44% and a specificity of 100%. Furthermore, this classifier demonstrated robust external generalization capabilities when applied to unseen bacterial species, such as Serratia marcescens DB10 and Citrobacter koseri H6. It blindly achieved a sensitivity of 97.92% and a specificity of 96.77% for DB10, and a sensitivity of 100% and a specificity of 97.22% for H6. This competitive performance indicates the potential to adapt our approach for diagnostic applications through portable devices or even smartphones. This adaptation would facilitate rapid, objective, on-site screening for bacterial swarming motility, potentially enhancing the early detection and treatment assessment of various diseases, including inflammatory bowel diseases (IBD) and urinary tract infections (UTI).

arXiv:2410.15460

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

As large language models (LLMs) are increasingly deployed across various industries, concerns regarding their reliability, particularly due to hallucinations - outputs that are factually inaccurate or irrelevant to user input - have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M - 12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce Sensitivity Dropout (SenD), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SenD achieves this by deterministically dropping embedding indices with significant variability, referred to as Sensitive Embedding Indices. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore at 2x speed. This efficient metric is integrated into our protocol, allowing SenD to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to Wikipedia, Medical, and LegalBench domains.

arXiv:2410.11976

Multiple Gaussian process models based global sensitivity analysis and efficient optimization of in vitro mRNA transcription process

The in vitro transcription (IVT) process is a critical step in RNA production. To ensure the efficiency of RNA manufacturing, it is essential to optimize and identify its key influencing factors. In this study, multiple Gaussian Process (GP) models are used to perform efficient optimization and global sensitivity analysis (GSA). Firstly, multiple GP models were constructed using the data from multiple experimental replicates, accurately capturing the complexities of the IVT process. Then GSA was conducted to determine the dominant reaction factors, specifically the concentrations of reactants NTP and Mg across all data-driven models. Concurrently, a multi-start optimization algorithm was applied to these GP models to identify optimal operational conditions that maximize RNA yields across all surrogate models. These optimized conditions are subsequently validated through additional experimental data.

arXiv:2410.11846

Sensitivity Analysis of Ruin of an Insurance Company in Ghana

An insurance company, as a risk bearer, is exposed to the likelihood of running into ruin. This is the situation where the initial surplus falls below zero. There is the need to find the required start-up capital to hedge against insolvency. Most researchers, irrespective of whether the test for claim dependency holds or not, assume claim independence in their computing of ruin probabilities to start up their initial capital. The objective of this study is to carry out comparative sensitivity analysis of ruin probability under both assumptions of dependence and independence, irrespective of whether the data exhibits independence or not, based on data from an insurance company in Ghana. Secondary data from an insurance company was obtained from the National Insurance Commission (NIC) for the period of 2013 to 2017. The study employed copulas to determine the claim dependence among the various insurance products and the company in general. The study concluded that when there is dependence in the claim data, computing the ruin probability based on the assumption of independence results in underestimation. Among the various insurance products, the most profitable insurance product was motor insurance, and Fire and Allied insurance exhibited the highest dependency. At a higher start-up capital, when claims are dependent, assuming independence in calculating the ruin probability results in a significant difference. Hence, it was recommended that insurance companies should adopt the assumption of dependence between the claims data as the initial reserves become larger, particularly for larger insurance companies, to avoid misleading results. Also, awareness of the perils and consequences of fire outbreaks and disasters should be raised to the general public to reduce the risk of frequent occurrence.

arXiv:2410.10911

Quantum-Enhanced Detection of Viral cDNA via Luminescence Resonance Energy Transfer Using Upconversion and Gold Nanoparticles

The COVID-19 pandemic has profoundly impacted global economies and healthcare systems, revealing critical vulnerabilities in both. In response, our study introduces a groundbreaking method for the detection of SARS-CoV-2 cDNA, leveraging Luminescence resonance energy transfer (LRET) between upconversion nanoparticles (UCNPs) and gold nanoparticles (AuNPs) to achieve an unprecedented detection limit of 242 femtomolar (fM). This innovative sensing platform utilizes UCNPs conjugated with one primer and AuNPs with another, targeting the 5' and 3' ends of the SARS-CoV-2 cDNA, respectively, enabling precise differentiation of mismatched DNA sequences and significantly enhancing detection specificity. Through rigorous experimental analysis, we established a quenching efficiency range from 10.4\% to 73.6\%, with an optimal midpoint of 42\%, thereby demonstrating the superior sensitivity of our method. By comparing the quenching efficiency of mismatched DNAs to the target DNA, we identified an optimal DNA:UCNP:AuNP ratio that ensures accurate detection. Our comparative analysis with existing SARS-CoV-2 detection methods revealed that our approach not only provides a lower detection limit but also offers higher specificity and potential for rapid, on-site testing. This study demonstrates the superior sensitivity and specificity of using UCNPs and AuNPs for SARS-CoV-2 cDNA detection, offering a significant advancement in rapid, accessible diagnostic technologies. Our method, characterized by its low detection limit and high precision, represents a critical step forward in managing current and future viral outbreaks, contributing to the enhancement of global healthcare responsiveness and infectious disease control.

arXiv:2410.13030

Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts

Despite the significant influx of prompt-tuning techniques for generative vision-language models (VLMs), it remains unclear how sensitive these models are to lexical and semantic alterations in prompts. In this paper, we evaluate the ability of generative VLMs to understand lexical and semantic changes in text using the SugarCrepe++ dataset. We analyze the sensitivity of VLMs to lexical alterations in prompts without corresponding semantic changes. Our findings demonstrate that generative VLMs are highly sensitive to such alterations. Additionally, we show that this vulnerability affects the performance of techniques aimed at achieving consistency in their outputs.

arXiv:2410.12880공식 코드 · Papers with Code

Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models

As LLMs are increasingly deployed in global applications, the importance of cultural sensitivity becomes paramount, ensuring that users from diverse backgrounds feel respected and understood. Cultural harm can arise when these models fail to align with specific cultural norms, resulting in misrepresentations or violations of cultural values. This work addresses the challenges of ensuring cultural sensitivity in LLMs, especially in small-parameter models that often lack the extensive training data needed to capture global cultural nuances. We present two key contributions: (1) A cultural harm test dataset, created to assess model outputs across different cultural contexts through scenarios that expose potential cultural insensitivities, and (2) A culturally aligned preference dataset, aimed at restoring cultural sensitivity through fine-tuning based on feedback from diverse annotators. These datasets facilitate the evaluation and enhancement of LLMs, ensuring their ethical and safe deployment across different cultural landscapes. Our results show that integrating culturally aligned feedback leads to a marked improvement in model behavior, significantly reducing the likelihood of generating culturally insensitive or harmful content. Ultimately, this work paves the way for more inclusive and respectful AI systems, fostering a future where LLMs can safely and ethically navigate the complexities of diverse cultural landscapes.

arXiv:2410.12405공식 코드 · Papers with Code

ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but their performance is highly sensitive to the prompts utilized. This variability poses challenges for accurate assessment and user satisfaction. Current research frequently overlooks instance-level prompt variations and their implications on subjective evaluations. To address these shortcomings, we introduce ProSA, a framework designed to evaluate and comprehend prompt sensitivity in LLMs. ProSA incorporates a novel sensitivity metric, PromptSensiScore, and leverages decoding confidence to elucidate underlying mechanisms. Our extensive study, spanning multiple tasks, uncovers that prompt sensitivity fluctuates across datasets and models, with larger models exhibiting enhanced robustness. We observe that few-shot examples can alleviate this sensitivity issue, and subjective evaluations are also susceptible to prompt sensitivities, particularly in complex, reasoning-oriented tasks. Furthermore, our findings indicate that higher model confidence correlates with increased prompt robustness. We believe this work will serve as a helpful tool in studying prompt sensitivity of LLMs. The project is released at: https://github.com/open-compass/ProSA .

arXiv:2410.12380

Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models

Attributing answers to source documents is an approach used to enhance the verifiability of a model's output in retrieval augmented generation (RAG). Prior work has mainly focused on improving and evaluating the attribution quality of large language models (LLMs) in RAG, but this may come at the expense of inducing biases in the attribution of answers. We define and examine two aspects in the evaluation of LLMs in RAG pipelines, namely attribution sensitivity and bias with respect to authorship information. We explicitly inform an LLM about the authors of source documents, instruct it to attribute its answers, and analyze (i) how sensitive the LLM's output is to the author of source documents, and (ii) whether the LLM exhibits a bias towards human-written or AI-generated source documents. We design an experimental setup in which we use counterfactual evaluation to study three LLMs in terms of their attribution sensitivity and bias in RAG pipelines. Our results show that adding authorship information to source documents can significantly change the attribution quality of LLMs by 3% to 18%. Moreover, we show that LLMs can have an attribution bias towards explicit human authorship, which can serve as a competing hypothesis for findings of prior work that shows that LLM-generated content may be preferred over human-written contents. Our findings indicate that metadata of source documents can influence LLMs' trust, and how they attribute their answers. Furthermore, our research highlights attribution bias and sensitivity as a novel aspect of brittleness in LLMs.

arXiv:2410.10927공식 코드 · Papers with Code

Cultural Heritage 3D Reconstruction with Diffusion Networks

This article explores the use of recent generative AI algorithms for repairing cultural heritage objects, leveraging a conditional diffusion model designed to reconstruct 3D point clouds effectively. Our study evaluates the model's performance across general and cultural heritage-specific settings. Results indicate that, with considerations for object variability, the diffusion model can accurately reproduce cultural heritage geometries. Despite encountering challenges like data diversity and outlier sensitivity, the model demonstrates significant potential in artifact restoration research. This work lays groundwork for advancing restoration methodologies for ancient artifacts using AI technologies.

arXiv:2410.11348공식 코드 · Papers with Code

RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals

Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what, exactly, they are actually rewarding. In this paper we develop Rewrite-based Attribute Treatment Estimator (RATE) as an effective method for measuring the sensitivity of a reward model to high-level attributes of responses, such as sentiment, helpfulness, or complexity. Importantly, RATE measures the causal effect of an attribute on the reward. RATE uses LLMs to rewrite responses to produce imperfect counterfactuals examples that can be used to measure causal effects. A key challenge is that these rewrites are imperfect in a manner that can induce substantial bias in the estimated sensitivity of the reward model to the attribute. The core idea of RATE is to adjust for this imperfect-rewrite effect by rewriting twice. We establish the validity of the RATE procedure and show empirically that it is an effective estimator.

arXiv:2410.09933

FedECADO: A Dynamical System Model of Federated Learning

Federated learning harnesses the power of distributed optimization to train a unified machine learning model across separate clients. However, heterogeneous data distributions and computational workloads can lead to inconsistent updates and limit model performance. This work tackles these challenges by proposing FedECADO, a new algorithm inspired by a dynamical system representation of the federated learning process. FedECADO addresses non-IID data distribution through an aggregate sensitivity model that reflects the amount of data processed by each client. To tackle heterogeneous computing, we design a multi-rate integration method with adaptive step-size selections that synchronizes active client updates in continuous time. Compared to prominent techniques, including FedProx and FedNova, FedECADO achieves higher classification accuracies in numerous heterogeneous scenarios.

arXiv:2410.09600공식 코드 · Papers with Code

The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning

Fairness metrics are a core tool in the fair machine learning literature (FairML), used to determine that ML models are, in some sense, "fair". Real-world data, however, are typically plagued by various measurement biases and other violated assumptions, which can render fairness assessments meaningless. We adapt tools from causal sensitivity analysis to the FairML context, providing a general framework which (1) accommodates effectively any combination of fairness metric and bias that can be posed in the "oblivious setting"; (2) allows researchers to investigate combinations of biases, resulting in non-linear sensitivity; and (3) enables flexible encoding of domain-specific constraints and assumptions. Employing this framework, we analyze the sensitivity of the most common parity metrics under 3 varieties of classifier across 14 canonical fairness datasets. Our analysis reveals the striking fragility of fairness assessments to even minor dataset biases. We show that causal sensitivity analysis provides a powerful and necessary toolkit for gauging the informativeness of parity metric evaluations. Our repository is available here: https://github.com/Jakefawkes/fragile_fair.