In recent years, the application of behavioral testing in Natural Language Processing (NLP) model evaluation has experienced a remarkable and substantial growth. However, the existing methods continue to be restricted by the requirements for manual labor and the limited scope of capability assessment. To address these limitations, we introduce AutoTestForge, an automated and multidimensional testing framework for NLP models in this paper. Within AutoTestForge, through the utilization of Large Language Models (LLMs) to automatically generate test templates and instantiate them, manual involvement is significantly reduced. Additionally, a mechanism for the validation of test case labels based on differential testing is implemented which makes use of a multi-model voting system to guarantee the quality of test cases. The framework also extends the test suite across three dimensions, taxonomy, fairness, and robustness, offering a comprehensive evaluation of the capabilities of NLP models. This expansion enables a more in-depth and thorough assessment of the models, providing valuable insights into their strengths and weaknesses. A comprehensive evaluation across sentiment analysis (SA) and semantic textual similarity (STS) tasks demonstrates that AutoTestForge consistently outperforms existing datasets and testing tools, achieving higher error detection rates (an average of $30.89\%$ for SA and $34.58\%$ for STS). Moreover, different generation strategies exhibit stable effectiveness, with error detection rates ranging from $29.03\% - 36.82\%$.

Statistical topic modeling is widely used in political science to study text. Researchers examine documents of varying lengths, from tweets to speeches. There is ongoing debate on how document length affects the interpretability of topic models. We investigate the effects of aggregating short documents into larger ones based on natural units that partition the corpus. In our study, we analyze one million tweets by U.S. state legislators from April 2016 to September 2020. We find that for documents aggregated at the account level, topics are more associated with individual states than when using individual tweets. This finding is replicated with Wikipedia pages aggregated by birth cities, showing how document definitions can impact topic modeling results.

The mathematical complexity and high dimensionality of neural networks hinder the training and deployment of machine learning (ML) systems while also requiring substantial computational resources. This fundamental limitation drives ML research, particularly in the exploration of alternative neural network architectures that integrate novel building blocks, such as advanced activation functions. Tunnel diodes are well-known electronic components that utilise the physical effect of quantum tunnelling (QT). Here, we propose using the current voltage characteristic of a tunnel diode as a novel, physics-based activation function for neural networks. We demonstrate that the tunnel-diode activation function (TDAF) outperforms traditional activation functions in terms of accuracy and loss during both training and evaluation. We also highlight its potential for implementation in electronic circuits suited to developing neuromorphic, quantum-inspired AI systems capable of operating in environments not suitable for qubit-based quantum computing hardware.

In recent years, there has been a growing concern and emphasis on conducting research beyond academic or scientific research communities, benefiting society at large. A well-known approach to measuring the impact of research on society is enumerating its policy citation(s). Despite the importance of research in informing policy, there is no concrete evidence to suggest the research's relevance in cited policy documents. This is concerning because it may increase the possibility of evidence used in policy being manipulated by individual, social, or political biases that may lead to inappropriate, fragmented, or archaic research evidence in policy. Therefore, it is crucial to identify the degree of relevance between research articles and citing policy documents. In this paper, we examined the scale of contextual relevance of youth-focused research in the referenced US policy documents using natural language processing techniques, state-of-the-art pre-trained Large Language Models (LLMs), and statistical analysis. Our experiments and analysis concluded that youth-related research articles that get US policy citations are mostly relevant to the citing policy documents.

The growing computational demand for deep neural networks ( DNNs) has raised concerns about their energy consumption and carbon footprint, particularly as the size and complexity of the models continue to increase. To address these challenges, energy-efficient hardware and custom accelerators have become essential. Additionally, adaptable DNN s are being developed to dynamically balance performance and efficiency. The use of these strategies became more common to enable sustainable AI deployment. However, these efficiency-focused designs may also introduce vulnerabilities, as attackers can potentially exploit them to increase latency and energy usage by triggering their worst-case-performance scenarios. This new type of attack, called energy-latency attacks, has recently gained significant research attention, focusing on the vulnerability of DNN s to this emerging attack paradigm, which can trigger denial-of-service ( DoS) attacks. This paper provides a comprehensive overview of current research on energy-latency attacks, categorizing them using the established taxonomy for traditional adversarial attacks. We explore different metrics used to measure the success of these attacks and provide an analysis and comparison of existing attack strategies. We also analyze existing defense mechanisms and highlight current challenges and potential areas for future research in this developing field. The GitHub page for this work can be accessed at https://github.com/hbrachemi/Survey_energy_attacks/

The emergence of powerful LLMs has led to a paradigm shift in Natural Language Understanding and Natural Language Generation. The properties that make LLMs so valuable for these tasks -- creativity, ability to produce fluent speech, and ability to quickly and effectively abstract information from large corpora -- also present new challenges to evaluating their outputs. The rush to market has led teams to fall back on quick, cost-effective automatic evaluations which offer value, but do not obviate the need for human judgments in model training and evaluation. This paper argues that in cases in which end users need to agree with the decisions made by ML models -- e.g. in toxicity detection or extraction of main points for summarization -- models should be trained and evaluated on data that represent the preferences of those users. We support this argument by explicating the role of human feedback in labeling and judgment tasks for model training and evaluation. First, we propose methods for disentangling noise from signal in labeling tasks. Then we show that noise in labeling disagreement can be minimized by adhering to proven methodological best practices, while signal can be maximized to play an integral role in model training and evaluation tasks. Finally, we illustrate best practices by providing a case study in which two guardrails classifiers are evaluated using human judgments to align final model behavior to user preferences. We aim for this paper to provide researchers and professionals with guidelines to integrating human judgments into their ML and generative AI evaluation toolkit, particularly when working toward achieving accurate and unbiased features that align with users' needs and expectations.

Large language model (LLM)-based tools such as ChatGPT seem useful for classical programming assignments. The more specialized the field, the more likely they lack reliability because of the lack of data to train them. In the case of quantum computing, the quality of answers of generic chatbots is low. C4Q is a chatbot focused on quantum programs that addresses this challenge through a software architecture that integrates specialized LLMs to classify requests and specialized question answering modules with a deterministic logical engine to provide trustworthy quantum computing support. This article describes the latest version (2.0) of C4Q, which delivers several enhancements: ready-to-run Qiskit code for gate definitions and circuit operations, expanded features to solve software engineering tasks such as the travelling salesperson problem and the knapsack problem, and a feedback mechanism for iterative improvement. Extensive testing of the backend confirms the system's reliability, while empirical evaluations show that C4Q 2.0's classification LLM reaches near-perfect accuracy. The evaluation of the result consists in a comparative study with three existing chatbots highlighting C4Q 2.0's maintainability and correctness, reflecting on how software architecture decisions, such as separating deterministic logic from probabilistic text generation impact the quality of the results.

For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all focusing on spatial (or static) imprints within the targeted underlying victim models, we present a fresh temporal paradigm for understanding these attacks. Of paramount discovery is that these imprints are encapsulated within a single loss metric, spanning universally across diverse tasks such as classification and regression, and modalities including image, text, and audio. Recognizing the distinct nature of loss between adversarial and clean examples, we exploit this temporal imprint for AE detection by proposing TRAIT (TRaceable Adversarial temporal trajectory ImprinTs). TRAIT operates under minimal assumptions without prior knowledge of attacks, thereby framing the detection challenge as a one-class classification problem. However, detecting AEs is still challenged by significant overlaps between the constructed synthetic losses of adversarial and clean examples due to the absence of ground truth for incoming inputs. TRAIT addresses this challenge by converting the synthetic loss into a spectrum signature, using the technique of Fast Fourier Transform to highlight the discrepancies, drawing inspiration from the temporal nature of the imprints, analogous to time-series signals. Across 12 AE attacks including SMACK (USENIX Sec'2023), TRAIT demonstrates consistent outstanding performance across comprehensively evaluated modalities, tasks, datasets, and model architectures. In all scenarios, TRAIT achieves an AE detection accuracy exceeding 97%, often around 99%, while maintaining a false rejection rate of 1%. TRAIT remains effective under the formulated strong adaptive attacks.

Missing link prediction is a method for network analysis, with applications in recommender systems, biology, social sciences, cybersecurity, information retrieval, and Artificial Intelligence (AI) reasoning in Knowledge Graphs. Missing link prediction identifies unseen but potentially existing connections in a network by analyzing the observed patterns and relationships. In proliferation detection, this supports efforts to identify and characterize attempts by state and non-state actors to acquire nuclear weapons or associated technology - a notoriously challenging but vital mission for global security. Dimensionality reduction techniques like Non-Negative Matrix Factorization (NMF) and Logistic Matrix Factorization (LMF) are effective but require selection of the matrix rank parameter, that is, of the number of hidden features, k, to avoid over/under-fitting. We introduce novel Weighted (WNMFk), Boolean (BNMFk), and Recommender (RNMFk) matrix factorization methods, along with ensemble variants incorporating logistic factorization, for link prediction. Our methods integrate automatic model determination for rank estimation by evaluating stability and accuracy using a modified bootstrap methodology and uncertainty quantification (UQ), assessing prediction reliability under random perturbations. We incorporate Otsu threshold selection and k-means clustering for Boolean matrix factorization, comparing them to coordinate descent-based Boolean thresholding. Our experiments highlight the impact of rank k selection, evaluate model performance under varying test-set sizes, and demonstrate the benefits of UQ for reliable predictions using abstention. We validate our methods on three synthetic datasets (Boolean and uniformly distributed) and benchmark them against LMF and symmetric LMF (symLMF) on five real-world protein-protein interaction networks, showcasing an improved prediction performance.

Inference-Time Scaling has been critical to the success of recent models such as OpenAI o1 and DeepSeek R1. However, many techniques used to train models for inference-time scaling require tasks to have answers that can be verified, limiting their application to domains such as math, coding and logical reasoning. We take inspiration from how humans make first attempts, ask for detailed feedback from others and make improvements based on such feedback across a wide spectrum of open-ended endeavors. To this end, we collect data for and train dedicated Feedback and Edit Models that are capable of performing inference-time scaling for open-ended general-domain tasks. In our setup, one model generates an initial response, which are given feedback by a second model, that are then used by a third model to edit the response. We show that performance on Arena Hard, a benchmark strongly predictive of Chatbot Arena Elo can be boosted by scaling the number of initial response drafts, effective feedback and edited responses. When scaled optimally, our setup based on 70B models from the Llama 3 family can reach SoTA performance on Arena Hard at 92.7 as of 5 Mar 2025, surpassing OpenAI o1-preview-2024-09-12 with 90.4 and DeepSeek R1 with 92.3.