This paper systematically investigates the generation of code explanations by Large Language Models (LLMs) for code examples commonly encountered in introductory programming courses. Our findings reveal significant variations in the nature of code explanations produced by LLMs, influenced by factors such as the wording of the prompt, the specific code examples under consideration, the programming language involved, the temperature parameter, and the version of the LLM. However, a consistent pattern emerges for Java and Python, where explanations exhibit a Flesch-Kincaid readability level of approximately 7-8 grade and a consistent lexical density, indicating the proportion of meaningful words relative to the total explanation size. Additionally, the generated explanations consistently achieve high scores for correctness, but lower scores on three other metrics: completeness, conciseness, and specificity.
相關內容
This paper introduces a novel operator, termed the Y operator, to elevate control performance in Actor-Critic(AC) based reinforcement learning for systems governed by stochastic differential equations(SDEs). The Y operator ingeniously integrates the stochasticity of a class of child-mother system into the Critic network's loss function, yielding substantial advancements in the control performance of RL algorithms.Additionally, the Y operator elegantly reformulates the challenge of solving partial differential equations for the state-value function into a parallel problem for the drift and diffusion functions within the system's SDEs.A rigorous mathematical proof confirms the operator's validity.This transformation enables the Y Operator-based Reinforcement Learning(YORL) framework to efficiently tackle optimal control problems in both model-based and data-driven systems.The superiority of YORL is demonstrated through linear and nonlinear numerical examples showing its enhanced performance over existing methods post convergence.
Printed Electronics (PE) feature distinct and remarkable characteristics that make them a prominent technology for achieving true ubiquitous computing. This is particularly relevant in application domains that require conformal and ultra-low cost solutions, which have experienced limited penetration of computing until now. Unlike silicon-based technologies, PE offer unparalleled features such as non-recurring engineering costs, ultra-low manufacturing cost, and on-demand fabrication of conformal, flexible, non-toxic, and stretchable hardware. However, PE face certain limitations due to their large feature sizes, that impede the realization of complex circuits, such as machine learning classifiers. In this work, we address these limitations by leveraging the principles of Approximate Computing and Bespoke (fully-customized) design. We propose an automated framework for designing ultra-low power Multilayer Perceptron (MLP) classifiers which employs, for the first time, a holistic approach to approximate all functions of the MLP's neurons: multiplication, accumulation, and activation. Through comprehensive evaluation across various MLPs of varying size, our framework demonstrates the ability to enable battery-powered operation of even the most intricate MLP architecture examined, significantly surpassing the current state of the art.
In this paper we present an efficient approach to implementing model checking in the Higher Order Logic (HOL) of Isabelle. This is a non-trivial task since model checking is restricted to finite state sets. By restricting our scope to considering security attacks, we achieve an efficient executable specification of a model checking algorithm for attack trees. We provide the existing background, the necessary theory and illustrate its application. Theory and application are fully formalized in Isabelle thus providing an executable model checking algorithm.
This paper presents the adaptive software security model, an innovative approach integrating the MAPE-K loop and the Software Development Life Cycle (SDLC). It proactively embeds security policies throughout development, reducing vulnerabilities from different levels of software engineering. Three primary contributions-MAPE-K integration, SDLC embedding, and analytical insights-converge to create a comprehensive approach for strengthening software systems against security threats. This research represents a paradigm shift, adapting security measures with agile software development and ensuring continuous improvement in the face of evolving threats. The model emerges as a robust solution, addressing the crucial need for adaptive software security strategies in modern software development. We analytically discuss the advantages of the proposed model.
Vector Error Correction Model (VECM) is a classic method to analyse cointegration relationships amongst multivariate non-stationary time series. In this paper, we focus on high dimensional setting and seek for sample-size-efficient methodology to determine the level of cointegration. Our investigation centres at a Bayesian approach to analyse the cointegration matrix, henceforth determining the cointegration rank. We design two algorithms and implement them on simulated examples, yielding promising results particularly when dealing with high number of variables and relatively low number of observations. Furthermore, we extend this methodology to empirically investigate the constituents of the S&P 500 index, where low-volatility portfolios can be found during both in-sample training and out-of-sample testing periods.
Recently, Large Language Models (LLMs) have shown impressive abilities in code generation. However, existing LLMs' decoding strategies are designed for Natural Language (NL) generation, overlooking the differences between NL and programming languages (PL). Due to this oversight, a better decoding strategy for code generation remains an open question. In this paper, we conduct the first systematic study to explore a decoding strategy specialized in code generation. With an analysis of loss distributions of code tokens, we find that code tokens can be divided into two categories: challenging tokens that are difficult to predict and confident tokens that can be easily inferred. Among them, the challenging tokens mainly appear at the beginning of a code block. Inspired by the above findings, we propose a simple yet effective method: Adaptive Temperature (AdapT) sampling, which dynamically adjusts the temperature coefficient when decoding different tokens. We apply a larger temperature when sampling for challenging tokens, allowing LLMs to explore diverse choices. We employ a smaller temperature for confident tokens avoiding the influence of tail randomness noises. We apply AdapT sampling to LLMs with different sizes and conduct evaluations on two popular datasets. Results show that AdapT sampling significantly outperforms state-of-the-art decoding strategy.
Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks and beyond. This success of LLMs has led to a large influx of research contributions in this direction. These works encompass diverse topics such as architectural innovations, better training strategies, context length improvements, fine-tuning, multi-modal LLMs, robotics, datasets, benchmarking, efficiency, and more. With the rapid development of techniques and regular breakthroughs in LLM research, it has become considerably challenging to perceive the bigger picture of the advances in this direction. Considering the rapidly emerging plethora of literature on LLMs, it is imperative that the research community is able to benefit from a concise yet comprehensive overview of the recent developments in this field. This article provides an overview of the existing literature on a broad range of LLM-related concepts. Our self-contained comprehensive overview of LLMs discusses relevant background concepts along with covering the advanced topics at the frontier of research in LLMs. This review article is intended to not only provide a systematic survey but also a quick comprehensive reference for the researchers and practitioners to draw insights from extensive informative summaries of the existing works to advance the LLM research.
The paper describes a system that uses large language model (LLM) technology to support the automatic learning of new entries in an intelligent agent's semantic lexicon. The process is bootstrapped by an existing non-toy lexicon and a natural language generator that converts formal, ontologically-grounded representations of meaning into natural language sentences. The learning method involves a sequence of LLM requests and includes an automatic quality control step. To date, this learning method has been applied to learning multiword expressions whose meanings are equivalent to those of transitive verbs in the agent's lexicon. The experiment demonstrates the benefits of a hybrid learning architecture that integrates knowledge-based methods and resources with both traditional data analytics and LLMs.
This paper builds and extends on the authors previous work related to the algorithmic tool, Cylindrical Algebraic Decomposition (CAD), and one of its core applications, Real Quantifier Elimination (QE). These topics are at the heart of symbolic computation and were first implemented in computer algebra systems decades ago, but have recently received renewed interest as part of the ongoing development of SMT solvers for non-linear real arithmetic. First, we consider the use of iterated univariate resultants in traditional CAD, and how this leads to inefficiencies, especially in the case of an input with multiple equational constraints. We reproduce the workshop paper [Davenport \& England, 2023], adding important clarifications to our suggestions first made there to make use of multivariate resultants in the projection phase of CAD. We then consider an alternative approach to this problem first documented in [McCallum \& Brown, 2009] which redefines the actual object under construction, albeit only in the case of two equational constraints. We correct an important typo and provide a missing proof in that paper. We finish by revising the topic of how to deal with SMT or Real QE problems expressed using rational functions (as opposed to the usual polynomial ones) noting that these are often found in industrial applications. We revisit a proposal made in [Uncu, Davenport and England, 2023] for doing this in the case of satisfiability, explaining why such an approach does not trivially extend to more complicated quantification structure and giving a suitable alternative.
We study the problem of incorporating prior knowledge into a deep Transformer-based model,i.e.,Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks. By probing and analyzing what BERT has already known when solving this task, we obtain better understanding of what task-specific knowledge BERT needs the most and where it is most needed. The analysis further motivates us to take a different approach than most existing works. Instead of using prior knowledge to create a new training task for fine-tuning BERT, we directly inject knowledge into BERT's multi-head attention mechanism. This leads us to a simple yet effective approach that enjoys fast training stage as it saves the model from training on additional data or tasks other than the main task. Extensive experiments demonstrate that the proposed knowledge-enhanced BERT is able to consistently improve semantic textual matching performance over the original BERT model, and the performance benefit is most salient when training data is scarce.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191