FinanceBench is a first-of-its-kind test suite for evaluating the performance of LLMs on open book financial question answering (QA). It comprises 10,231 questions about publicly traded companies, with corresponding answers and evidence strings. The questions in FinanceBench are ecologically valid and cover a diverse set of scenarios. They are intended to be clear-cut and straightforward to answer to serve as a minimum performance standard. We test 16 state of the art model configurations (including GPT-4-Turbo, Llama2 and Claude2, with vector stores and long context prompts) on a sample of 150 cases from FinanceBench, and manually review their answers (n=2,400). The cases are available open-source. We show that existing LLMs have clear limitations for financial QA. Notably, GPT-4-Turbo used with a retrieval system incorrectly answered or refused to answer 81% of questions. While augmentation techniques such as using longer context window to feed in relevant evidence improve performance, they are unrealistic for enterprise settings due to increased latency and cannot support larger financial documents. We find that all models examined exhibit weaknesses, such as hallucinations, that limit their suitability for use by enterprises.
Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks. However, the adversarial examples generated by many mainstream word-level adversarial attack models are neither valid nor natural, leading to the loss of semantic maintenance, grammaticality, and human imperceptibility. Based on the exceptional capacity of language understanding and generation of large language models (LLMs), we propose LLM-Attack, which aims at generating both valid and natural adversarial examples with LLMs. The method consists of two stages: word importance ranking (which searches for the most vulnerable words) and word synonym replacement (which substitutes them with their synonyms obtained from LLMs). Experimental results on the Movie Review (MR), IMDB, and Yelp Review Polarity datasets against the baseline adversarial attack models illustrate the effectiveness of LLM-Attack, and it outperforms the baselines in human and GPT-4 evaluation by a significant margin. The model can generate adversarial examples that are typically valid and natural, with the preservation of semantic meaning, grammaticality, and human imperceptibility.
A realistic human kinematic model that satisfies anatomical constraints is essential for human-robot interaction, biomechanics and robot-assisted rehabilitation. Modeling realistic joint constraints, however, is challenging as human arm motion is constrained by joint limits, inter- and intra-joint dependencies, self-collisions, individual capabilities and muscular or neurological constraints which are difficult to represent. Hence, physicians and researchers have relied on simple box-constraints, ignoring important anatomical factors. In this paper, we propose a data-driven method to learn realistic anatomically constrained upper-limb range of motion (RoM) boundaries from motion capture data. This is achieved by fitting a one-class support vector machine to a dataset of upper-limb joint space exploration motions with an efficient hyper-parameter tuning scheme. Our approach outperforms similar works focused on valid RoM learning. Further, we propose an impairment index (II) metric that offers a quantitative assessment of capability/impairment when comparing healthy and impaired arms. We validate the metric on healthy subjects physically constrained to emulate hemiplegia and different disability levels as stroke patients.
Characterized by a cross-disciplinary nature, the bearing-based target localization task involves estimating the position of an entity of interest by a group of agents capable of collecting noisy bearing measurements. In this work, this problem is tackled by resting both on the weighted least square estimation approach and on the active-sensing control paradigm. Indeed, we propose an iterative algorithm that provides an estimate of the target position under the assumption of Gaussian noise distribution, which can be considered valid when more specific information is missing. Then, we present a seeker agents control law that aims at minimizing the localization uncertainty by optimizing the covariance matrix associated with the estimated target position. The validity of the designed bearing-based target localization solution is confirmed by the results of an extensive Monte Carlo simulation campaign.
Despite the success of chain of thought in enhancing language model reasoning, the underlying process remains less well understood. Although logically sound reasoning appears inherently crucial for chain of thought, prior studies surprisingly reveal minimal impact when using invalid demonstrations instead. Furthermore, the conventional chain of thought does not inform language models on what mistakes to avoid, which potentially leads to more errors. Hence, inspired by how humans can learn from both positive and negative examples, we propose contrastive chain of thought to enhance language model reasoning. Compared to the conventional chain of thought, our approach provides both valid and invalid reasoning demonstrations, to guide the model to reason step-by-step while reducing reasoning mistakes. To improve generalization, we introduce an automatic method to construct contrastive demonstrations. Our experiments on reasoning benchmarks demonstrate that contrastive chain of thought can serve as a general enhancement of chain-of-thought prompting.
Can large language models (LLMs) express their uncertainty in situations where they lack sufficient parametric knowledge to generate reasonable responses? This work aims to systematically investigate LLMs' behaviors in such situations, emphasizing the trade-off between honesty and helpfulness. To tackle the challenge of precisely determining LLMs' knowledge gaps, we diagnostically create unanswerable questions containing non-existent concepts or false premises, ensuring that they are outside the LLMs' vast training data. By compiling a benchmark, UnknownBench, which consists of both unanswerable and answerable questions, we quantitatively evaluate the LLMs' performance in maintaining honesty while being helpful. Using a model-agnostic unified confidence elicitation approach, we observe that most LLMs fail to consistently refuse or express uncertainty towards questions outside their parametric knowledge, although instruction fine-tuning and alignment techniques can provide marginal enhancements. Moreover, LLMs' uncertainty expression does not always stay consistent with the perceived confidence of their textual outputs.
Protected natural areas are regions that have been minimally affected by human activities such as urbanization, agriculture, and other human interventions. To better understand and map the naturalness of these areas, machine learning models can be used to analyze satellite imagery. Specifically, explainable machine learning methods show promise in uncovering patterns that contribute to the concept of naturalness within these protected environments. Additionally, addressing the uncertainty inherent in machine learning models is crucial for a comprehensive understanding of this concept. However, existing approaches have limitations. They either fail to provide explanations that are both valid and objective or struggle to offer a quantitative metric that accurately measures the contribution of specific patterns to naturalness, along with the associated confidence. In this paper, we propose a novel framework called the Confident Naturalness Explanation (CNE) framework. This framework combines explainable machine learning and uncertainty quantification to assess and explain naturalness. We introduce a new quantitative metric that describes the confident contribution of patterns to the concept of naturalness. Furthermore, we generate an uncertainty-aware segmentation mask for each input sample, highlighting areas where the model lacks knowledge. To demonstrate the effectiveness of our framework, we apply it to a study site in Fennoscandia using two open-source satellite datasets.
There has been significant progress in improving the accuracy and quality of consumer-level dense depth sensors. Nevertheless, there remains a common depth pixel artifact which we call smeared points. These are points not on any 3D surface and typically occur as interpolations between foreground and background objects. As they cause fictitious surfaces, these points have the potential to harm applications dependent on the depth maps. Statistical outlier removal methods fare poorly in removing these points as they tend also to remove actual surface points. Trained network-based point removal faces difficulty in obtaining sufficient annotated data. To address this, we propose a fully self-annotated method to train a smeared point removal classifier. Our approach relies on gathering 3D geometric evidence from multiple perspectives to automatically detect and annotate smeared points and valid points. To validate the effectiveness of our method, we present a new benchmark dataset: the Real Azure-Kinect dataset. Experimental results and ablation studies show that our method outperforms traditional filters and other self-annotated methods. Our work is publicly available at https://github.com/wangmiaowei/wacv2024_smearedremover.git.
Natural protected areas are vital for biodiversity, climate change mitigation, and supporting ecological processes. Despite their significance, comprehensive mapping is hindered by a lack of understanding of their characteristics and a missing land cover class definition. This paper aims to advance the explanation of the designating patterns forming protected and wild areas. To this end, we propose a novel framework that uses activation maximization and a generative adversarial model. With this, we aim to generate satellite images that, in combination with domain knowledge, are capable of offering complete and valid explanations for the spatial and spectral patterns that define the natural authenticity of these regions. Our proposed framework produces more precise attribution maps pinpointing the designating patterns forming the natural authenticity of protected areas. Our approach fosters our understanding of the ecological integrity of the protected natural areas and may contribute to future monitoring and preservation efforts.
We study sequential mean estimation in $\mathbb{R}^d$. In particular, we derive time-uniform confidence spheres -- confidence sphere sequences (CSSs) -- which contain the mean of random vectors with high probability simultaneously across all sample sizes. Our results include a dimension-free CSS for log-concave random vectors, a dimension-free CSS for sub-Gaussian random vectors, and CSSs for sub-$\psi$ random vectors (which includes sub-gamma, sub-Poisson, and sub-exponential distributions). Many of our results are optimal. For sub-Gaussian distributions we also provide a CSS which tracks a time-varying mean, generalizing Robbins' mixture approach to the multivariate setting. Finally, we provide several CSSs for heavy-tailed random vectors (two moments only). Our bounds hold under a martingale assumption on the mean and do not require that the observations be iid. Our work is based on PAC-Bayesian theory and inspired by an approach of Catoni and Giulini.
In order to improve the simulation effect of electronic communication data link encryption, the author proposes a solution based on wireless communication. The main content of this technology is based on the research of wireless communication, improve the elliptic curve cryptographic algorithm to build a system encryption model, obtain legal and valid node private keys, evaluate and analyze the relevant security attributes of the system, verify the security of the keys, and realize the encryption optimization of wireless network communication. Experimental results show that: Using the improved elliptic curve to simulate the system data chain encryption under the certificateless public key cryptosystem in network communication, the time is only 2.31 milliseconds, which is lower than other algorithms. Conclusion: It is proved that the technology research based on wireless communication can effectively improve the encryption simulation effect of electronic communication data link.
Experimentation is crucial for managers to rigorously quantify the value of a change and determine if it leads to a statistically significant improvement over the status quo. As companies increasingly mandate that all changes undergo experimentation before widespread release, two challenges arise: (1) minimizing the proportion of customers assigned to the inferior treatment and (2) increasing experimentation velocity by enabling data-dependent stopping. This paper addresses both challenges by introducing the Mixture Adaptive Design (MAD), a new experimental design for multi-armed bandit (MAB) algorithms that enables anytime-valid inference on the Average Treatment Effect (ATE) for \emph{any} MAB algorithm. Intuitively, MAD "mixes" any bandit algorithm with a Bernoulli design, where at each time step, the probability of assigning a unit via the Bernoulli design is determined by a user-specified deterministic sequence that can converge to zero. This sequence lets managers directly control the trade-off between regret minimization and inferential precision. Under mild conditions on the rate the sequence converges to zero, we provide a confidence sequence that is asymptotically anytime-valid and guaranteed to shrink around the true ATE. Hence, when the true ATE converges to a non-zero value, the MAD confidence sequence is guaranteed to exclude zero in finite time. Therefore, the MAD enables managers to stop experiments early while ensuring valid inference, enhancing both the efficiency and reliability of adaptive experiments. Empirically, we demonstrate that the MAD achieves finite-sample anytime-validity while accurately and precisely estimating the ATE, all without incurring significant losses in reward compared to standard bandit designs.
With the advances in computationally efficient artificial Intelligence (AI) techniques and their numerous applications in our everyday life, there is a pressing need to understand the computational details hidden in black box AI techniques such as most popular machine learning and deep learning techniques; through more detailed explanations. The origin of explainable AI (xAI) is coined from these challenges and recently gained more attention by the researchers by adding explainability comprehensively in traditional AI systems. This leads to develop an appropriate framework for successful applications of xAI in real life scenarios with respect to innovations, risk mitigation, ethical issues and logical values to the users. In this book chapter, an in-depth analysis of several xAI frameworks and methods including LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations) are provided. Random Forest Classifier as black box AI is used on a publicly available Diabetes symptoms dataset with LIME and SHAP for better interpretations. The results obtained are interesting in terms of transparency, valid and trustworthiness in diabetes disease prediction.
Early-exit neural networks (EENNs) enable adaptive and efficient inference by providing predictions at multiple stages during the forward pass. In safety-critical applications, these predictions are meaningful only when accompanied by reliable uncertainty estimates. A popular method for quantifying the uncertainty of predictive models is the use of prediction sets. However, we demonstrate that standard techniques such as conformal prediction and Bayesian credible sets are not suitable for EENNs. They tend to generate non-nested sets across exits, meaning that labels deemed improbable at one exit may reappear in the prediction set of a subsequent exit. To address this issue, we investigate anytime-valid confidence sequences (AVCSs), an extension of traditional confidence intervals tailored for data-streaming scenarios. These sequences are inherently nested and thus well-suited for an EENN's sequential predictions. We explore the theoretical and practical challenges of using AVCSs in EENNs and show that they indeed yield nested sets across exits. Thus our work presents a promising approach towards fast, yet still safe, predictive modeling
The monograph discusses certain aspects of modern real-world problems facing humanity, which are much more challenging than scientific ones. Modern science is unable to solve them in a fundamental way. Vernadsky's noosphere thesis, in fact, appeals to the scientific worldview that needs to be built in a way that overcomes the interdisciplinary barriers and increases the effectiveness of interdisciplinary interaction and modern science overall. We are talking about the general transdisciplinary knowledge. In world practice, there is still no systematic methodology and a specific form of generally accepted valid scientific theory that would provide transdisciplinary knowledge. Non-linear interdisciplinary interaction is the standard of evolution of modern science. At the same time, a new transdisciplinary theory (domain of scientific research) is being de facto created and the process is repeated many times: from an individual or group of disciplines, through interdisciplinary interaction, in a direction that brings us closer to creating a holistic general scientific worldview.
Understanding event descriptions is a central aspect of language processing, but current approaches focus overwhelmingly on single sentences or documents. Aggregating information about an event \emph{across documents} can offer a much richer understanding. To this end, we present FAMuS, a new corpus of Wikipedia passages that \emph{report} on some event, paired with underlying, genre-diverse (non-Wikipedia) \emph{source} articles for the same event. Events and (cross-sentence) arguments in both report and source are annotated against FrameNet, providing broad coverage of different event types. We present results on two key event understanding tasks enabled by FAMuS: \emph{source validation} -- determining whether a document is a valid source for a target report event -- and \emph{cross-document argument extraction} -- full-document argument extraction for a target event from both its report and the correct source article. We release both FAMuS and our models to support further research.
Molecular modeling at the quantum level requires choosing a parameterization of the wavefunction that both respects the required particle symmetries, and is scalable to systems of many particles. For the simulation of fermions, valid parameterizations must be antisymmetric with respect to the exchange of particles. Typically, antisymmetry is enforced by leveraging the anti-symmetry of determinants with respect to the exchange of matrix rows, but this involves computing a full determinant each time the wavefunction is evaluated. Instead, we introduce a new antisymmetrization layer derived from sorting, the $\textit{sortlet}$, which scales as $O(N \log N)$ with regards to the number of particles -- in contrast to $O(N^3)$ for the determinant. We show numerically that applying this anti-symmeterization layer on top of an attention based neural-network backbone yields a flexible wavefunction parameterization capable of reaching chemical accuracy when approximating the ground state of first-row atoms and small molecules.
This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition attracted a total of 8 participating teams with valid submissions from academia and industry. The competition aimed to motivate and attract solutions that target detecting face presentation attacks while considering synthetic-based training data motivated by privacy, legal and ethical concerns associated with personal data. To achieve that, the training data used by the participants was limited to synthetic data provided by the organizers. The submitted solutions presented innovations and novel approaches that led to outperforming the considered baseline in the investigated benchmarks.
With large language models (LLMs) like GPT-4 appearing to behave increasingly human-like in text-based interactions, it has become popular to attempt to evaluate personality traits of LLMs using questionnaires originally developed for humans. While reusing measures is a resource-efficient way to evaluate LLMs, careful adaptations are usually required to ensure that assessment results are valid even across human subpopulations. In this work, we provide evidence that LLMs' responses to personality tests systematically deviate from human responses, implying that the results of these tests cannot be interpreted in the same way. Concretely, reverse-coded items ("I am introverted" vs. "I am extraverted") are often both answered affirmatively. Furthermore, variation across prompts designed to "steer" LLMs to simulate particular personality types does not follow the clear separation into five independent personality factors from human samples. In light of these results, we believe that it is important to investigate tests' validity for LLMs before drawing strong conclusions about potentially ill-defined concepts like LLMs' "personality".
Certifiable, adaptive uncertainty estimates for unknown quantities are an essential ingredient of sequential decision-making algorithms. Standard approaches rely on problem-dependent concentration results and are limited to a specific combination of parameterization, noise family, and estimator. In this paper, we revisit the likelihood-based inference principle and propose to use likelihood ratios to construct any-time valid confidence sequences without requiring specialized treatment in each application scenario. Our method is especially suitable for problems with well-specified likelihoods, and the resulting sets always maintain the prescribed coverage in a model-agnostic manner. The size of the sets depends on a choice of estimator sequence in the likelihood ratio. We discuss how to provably choose the best sequence of estimators and shed light on connections to online convex optimization with algorithms such as Follow-the-Regularized-Leader. To counteract the initially large bias of the estimators, we propose a reweighting scheme that also opens up deployment in non-parametric settings such as RKHS function classes. We provide a non-asymptotic analysis of the likelihood ratio confidence sets size for generalized linear models, using insights from convex duality and online learning. We showcase the practical strength of our method on generalized linear bandit problems, survival analysis, and bandits with various additive noise distributions.