Despite significant advancements, there is a limited understanding of how large language models (LLMs) utilize knowledge for reasoning. To address this, we propose a method that deconstructs complex real-world questions into a graph, representing each question as a node with parent nodes of background knowledge needed to solve the question. We develop the DepthQA dataset, deconstructing questions into three depths: (i) recalling conceptual knowledge, (ii) applying procedural knowledge, and (iii) analyzing strategic knowledge. Based on a hierarchical graph, we quantify forward discrepancy, discrepancies in LLMs' performance on simpler sub-problems versus complex questions. We also measure backward discrepancy, where LLMs answer complex questions but struggle with simpler ones. Our analysis shows that smaller models have more discrepancies than larger models. Additionally, guiding models from simpler to complex questions through multi-turn interactions improves performance across model sizes, highlighting the importance of structured intermediate steps in knowledge reasoning. This work enhances our understanding of LLM reasoning and suggests ways to improve their problem-solving abilities.

Artificial intelligence systems often address fairness concerns by evaluating and mitigating measures of group discrimination, for example that indicate biases against certain genders or races. However, what constitutes group fairness depends on who is asked and the social context, whereas definitions are often relaxed to accept small deviations from the statistical constraints they set out to impose. Here we decouple definitions of group fairness both from the context and from relaxation-related uncertainty by expressing them in the axiomatic system of Basic fuzzy Logic (BL) with loosely understood predicates, like encountering group members. We then evaluate the definitions in subclasses of BL, such as Product or Lukasiewicz logics. Evaluation produces continuous instead of binary truth values by choosing the logic subclass and truth values for predicates that reflect uncertain context-specific beliefs, such as stakeholder opinions gathered through questionnaires. Internally, it follows logic-specific rules to compute the truth values of definitions. We show that commonly held propositions standardize the resulting mathematical formulas and we transcribe logic and truth value choices to layperson terms, so that anyone can answer them. We also use our framework to study several literature definitions of algorithmic fairness, for which we rationalize previous expedient practices that are non-probabilistic and show how to re-interpret their formulas and parameters in new contexts.

An AI tool has been developed to provide interpretable support for the diagnosis of BCC via teledermatology, thus speeding up referrals and optimizing resource utilization. The interpretability is provided in two ways: on the one hand, the main BCC dermoscopic patterns are found in the image to justify the BCC/Non BCC classification. Secondly, based on the common visual XAI Grad-CAM, a clinically inspired visual explanation is developed where the relevant features for diagnosis are located. Since there is no established ground truth for BCC dermoscopic features, a standard reference is inferred from the diagnosis of four dermatologists using an Expectation Maximization (EM) based algorithm. The results demonstrate significant improvements in classification accuracy and interpretability, positioning this approach as a valuable tool for early BCC detection and referral to dermatologists. The BCC/non-BCC classification achieved an accuracy rate of 90%. For Clinically-inspired XAI results, the detection of BCC patterns useful to clinicians reaches 99% accuracy. As for the Clinically-inspired Visual XAI results, the mean of the Grad-CAM normalized value within the manually segmented clinical features is 0.57, while outside this region it is 0.16. This indicates that the model struggles to accurately identify the regions of the BCC patterns. These results prove the ability of the AI tool to provide a useful explanation.

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced. This study is focused on recovering from packet loss to improve the word error rate (WER) of ASR models. We propose using a front-end adaptation network connected to a frozen ASR model. The adaptation network is trained to modify the corrupted input spectrum by minimizing the criteria of the ASR model in addition to an enhancement loss function. Our experiments demonstrate that the adaptation network, trained on Whisper's criteria, notably reduces word error rates across domains and languages in packet-loss scenarios. This improvement is achieved with minimal affect to Whisper model's foundational performance, underscoring our method's practicality and potential in enhancing ASR models in challenging acoustic environments.

"Garbage In Garbage Out" is a universally agreed quote by computer scientists from various domains, including Artificial Intelligence (AI). As data is the fuel for AI, models trained on low-quality, biased data are often ineffective. Computer scientists who use AI invest a considerable amount of time and effort in preparing the data for AI. However, there are no standard methods or frameworks for assessing the "readiness" of data for AI. To provide a quantifiable assessment of the readiness of data for AI processes, we define parameters of AI data readiness and introduce AIDRIN (AI Data Readiness Inspector). AIDRIN is a framework covering a broad range of readiness dimensions available in the literature that aid in evaluating the readiness of data quantitatively and qualitatively. AIDRIN uses metrics in traditional data quality assessment such as completeness, outliers, and duplicates for data evaluation. Furthermore, AIDRIN uses metrics specific to assess data for AI, such as feature importance, feature correlations, class imbalance, fairness, privacy, and FAIR (Findability, Accessibility, Interoperability, and Reusability) principle compliance. AIDRIN provides visualizations and reports to assist data scientists in further investigating the readiness of data. The AIDRIN framework enhances the efficiency of the machine learning pipeline to make informed decisions on data readiness for AI applications.

Imagine training a machine learning model with Differentially Private Stochastic Gradient Descent (DP-SGD), only to discover post-training that the noise level was either too high, crippling your model's utility, or too low, compromising privacy. The dreaded realization hits: you must start the lengthy training process from scratch. But what if you could avoid this retraining nightmare? In this study, we introduce a groundbreaking approach (to our knowledge) that applies differential privacy noise to the model's weights after training. We offer a comprehensive mathematical proof for this novel approach's privacy bounds, use formal methods to validate its privacy guarantees, and empirically evaluate its effectiveness using membership inference attacks and performance evaluations. This method allows for a single training run, followed by post-hoc noise adjustments to achieve optimal privacy-utility trade-offs. We compare this novel fine-tuned model (DP-Weights model) to a traditional DP-SGD model, demonstrating that our approach yields statistically similar performance and privacy guarantees. Our results validate the efficacy of post-training noise application, promising significant time savings and flexibility in fine-tuning differential privacy parameters, making it a practical alternative for deploying differentially private models in real-world scenarios.

We use transductive regression techniques to learn mappings between source and target features of given parallel corpora and use these mappings to generate machine translation outputs. We show the effectiveness of $L_1$ regularized regression (\textit{lasso}) to learn the mappings between sparsely observed feature sets versus $L_2$ regularized regression. Proper selection of training instances plays an important role to learn correct feature mappings within limited computational resources and at expected accuracy levels. We introduce \textit{dice} instance selection method for proper selection of training instances, which plays an important role to learn correct feature mappings for improving the source and target coverage of the training set. We show that $L_1$ regularized regression performs better than $L_2$ regularized regression both in regression measurements and in the translation experiments using graph decoding. We present encouraging results when translating from German to English and Spanish to English. We also demonstrate results when the phrase table of a phrase-based decoder is replaced with the mappings we find with the regression model.

Multimodal intent recognition poses significant challenges, requiring the incorporation of non-verbal modalities from real-world contexts to enhance the comprehension of human intentions. Existing benchmark datasets are limited in scale and suffer from difficulties in handling out-of-scope samples that arise in multi-turn conversational interactions. We introduce MIntRec2.0, a large-scale benchmark dataset for multimodal intent recognition in multi-party conversations. It contains 1,245 dialogues with 15,040 samples, each annotated within a new intent taxonomy of 30 fine-grained classes. Besides 9,304 in-scope samples, it also includes 5,736 out-of-scope samples appearing in multi-turn contexts, which naturally occur in real-world scenarios. Furthermore, we provide comprehensive information on the speakers in each utterance, enriching its utility for multi-party conversational research. We establish a general framework supporting the organization of single-turn and multi-turn dialogue data, modality feature extraction, multimodal fusion, as well as in-scope classification and out-of-scope detection. Evaluation benchmarks are built using classic multimodal fusion methods, ChatGPT, and human evaluators. While existing methods incorporating nonverbal information yield improvements, effectively leveraging context information and detecting out-of-scope samples remains a substantial challenge. Notably, large language models exhibit a significant performance gap compared to humans, highlighting the limitations of machine learning methods in the cognitive intent understanding task. We believe that MIntRec2.0 will serve as a valuable resource, providing a pioneering foundation for research in human-machine conversational interactions, and significantly facilitating related applications. The full dataset and codes are available at https://github.com/thuiar/MIntRec2.0.

In this paper, we fine-tuned three pre-trained BERT models on the task of "definition extraction" from mathematical English written in LaTeX. This is presented as a binary classification problem, where either a sentence contains a definition of a mathematical term or it does not. We used two original data sets, "Chicago" and "TAC," to fine-tune and test these models. We also tested on WFMALL, a dataset presented by Vanetik and Litvak in 2021 and compared the performance of our models to theirs. We found that a high-performance Sentence-BERT transformer model performed best based on overall accuracy, recall, and precision metrics, achieving comparable results to the earlier models with less computational effort.

Recent research efforts on adversarial machine learning (ML) have investigated problem-space attacks, focusing on the generation of real evasive objects in domains where, unlike images, there is no clear inverse mapping to the feature space (e.g., software). However, the design, comparison, and real-world implications of problem-space attacks remain underexplored. This article makes three major contributions. Firstly, we propose a general formalization for adversarial ML evasion attacks in the problem-space, which includes the definition of a comprehensive set of constraints on available transformations, preserved semantics, absent artifacts, and plausibility. We shed light on the relationship between feature space and problem space, and we introduce the concept of side-effect features as the by-product of the inverse feature-mapping problem. This enables us to define and prove necessary and sufficient conditions for the existence of problem-space attacks. Secondly, building on our general formalization, we propose a novel problem-space attack on Android malware that overcomes past limitations in terms of semantics and artifacts. We have tested our approach on a dataset with 150K Android apps from 2016 and 2018 which show the practical feasibility of evading a state-of-the-art malware classifier along with its hardened version. Thirdly, we explore the effectiveness of adversarial training as a possible approach to enforce robustness against adversarial samples, evaluating its effectiveness on the considered machine learning models under different scenarios. Our results demonstrate that "adversarial-malware as a service" is a realistic threat, as we automatically generate thousands of realistic and inconspicuous adversarial applications at scale, where on average it takes only a few minutes to generate an adversarial instance.