The main advantages of deep neural networks (DNNs) are their architectural simplicity and automatic feature learning. The latter is crucial for working with unstructured data as developers don't need to design features by hand. However, giving away the control over features leads to black box models - DNNs tend to learn hardly interpretable "shortcut" correlations [17] that leak from train to test [20], hampering alignment and out-of-distribution performance. In particular, this gives rise to adversarial attacks [35] - semantically negligible perturbations of data that arbitrarily change model's predictions. Adversarial vulnerability is a widespread phenomenon (vision [35], segmentation/detection [39], speech recognition [9], tabular data [10], RL [19], NLP [41]) and largely contributes to the general lack of trust in DNNs, substantially limiting their adoption in high-stakes applications such as healthcare, military, autonomous vehicles or cybersecurity. Conversely, the main advantage of hand-designed features is the fine-grained control over model's performance; however, such systems quickly become infeasibly complex. This paper aims to address those issues by reconciling Deep Learning with feature engineering - with the help of locality engineering. Specifically, semantic features are introduced as a general conceptual machinery for controlled dimensionality reduction inside a neural network layer. Figure 1 presents the core idea behind the notion and the rigorous definition is given in Section 4. Implementing a semantic feature predominantly involves encoding appropriate invariants (i.e.

Measuring the quality of contributions in political online discussions is crucial in deliberation research and computer science. Research has identified various indicators to assess online discussion quality, and with deep learning advancements, automating these measures has become feasible. While some studies focus on analyzing specific quality indicators, a comprehensive quality score incorporating various deliberative aspects is often preferred. In this work, we introduce AQuA, an additive score that calculates a unified deliberative quality score from multiple indices for each discussion post. Unlike other singular scores, AQuA preserves information on the deliberative aspects present in comments, enhancing model transparency. We develop adapter models for 20 deliberative indices, and calculate correlation coefficients between experts' annotations and the perceived deliberativeness by non-experts to weigh the individual indices into a single deliberative score. We demonstrate that the AQuA score can be computed easily from pre-trained adapters and aligns well with annotations on other datasets that have not be seen during training. The analysis of experts' vs. non-experts' annotations confirms theoretical findings in the social science literature.

Deep Neural Networks (DNNs) have advanced in many real-world applications, such as healthcare and autonomous driving. However, their high computational complexity and vulnerability to adversarial attacks are ongoing challenges. In this letter, approximate multipliers are used to explore DNN robustness improvement against adversarial attacks. By uniformly replacing accurate multipliers for state-of-the-art approximate ones in DNN layer models, we explore the DNNs robustness against various adversarial attacks in a feasible time. Results show up to 7% accuracy drop due to approximations when no attack is present while improving robust accuracy up to 10% when attacks applied.

Numerical lattice quantum chromodynamics (QCD) is an integral part of the modern particle and nuclear theory toolkit [1-9]. In this framework, the discretized path integral is computed using Monte Carlo methods. Computationally, this is very expensive, and grows more so as physical limits of interest are approached [10-12]. Consequently, algorithmic developments are an important driver of progress. For example, resolving topological freezing [12-14]--an issue that arises in sampling gauge field configurations with state-of-the-art Markov chain Monte Carlo (MCMC) algorithms like heatbath [15-19] or Hybrid/Hamiltonian Monte Carlo (HMC) [20-22]--would provide access to finer lattice spacings than presently affordable. To such ends, recent work has explored how emerging machine learning (ML) techniques may be applied to lattice QCD [23, 24]. Of particular interest has been the possibility of accelerating gauge-field sampling [25-34] using normalizing flows [35-37], a class of generative statistical models with tractable density functions. In this framework, a flow is a learned, invertible (diffeomorphic) map between gauge fields. Abstractly, flows may be thought of as bridges between different distributions over gauge fields (or, equivalently, different theories or choices of action parameters).

Through the advent of pre-trained language models, there have been notable advancements in abstractive summarization systems. Simultaneously, a considerable number of novel methods for evaluating factual consistency in abstractive summarization systems has been developed. But these evaluation approaches incorporate substantial limitations, especially on refinement and interpretability. In this work, we propose highly effective and interpretable factual inconsistency detection method metric Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document for abstractive summarization systems that is based on fine-grained atomic facts decomposition. Moreover, we align atomic facts decomposed from the summary with the source document through adaptive granularity expansion. These atomic facts represent a more fine-grained unit of information, facilitating detailed understanding and interpretability of the summary's factual inconsistency. Experimental results demonstrate that our proposed factual consistency checking system significantly outperforms existing systems.

While current large language models (LLMs) demonstrate some capabilities in knowledge-intensive tasks, they are limited by relying on their parameters as an implicit storage mechanism. As a result, they struggle with infrequent knowledge and temporal degradation. In addition, the uninterpretable nature of parametric memorization makes it challenging to understand and prevent hallucination. Parametric memory pools and model editing are only partial solutions. Retrieval Augmented Generation (RAG) $\unicode{x2013}$ though non-parametric $\unicode{x2013}$ has its own limitations: it lacks structure, complicates interpretability and makes it hard to effectively manage stored knowledge. In this paper, we introduce MemLLM, a novel method of enhancing LLMs by integrating a structured and explicit read-and-write memory module. MemLLM tackles the aforementioned challenges by enabling dynamic interaction with the memory and improving the LLM's capabilities in using stored knowledge. Our experiments indicate that MemLLM enhances the LLM's performance and interpretability, in language modeling in general and knowledge-intensive tasks in particular. We see MemLLM as an important step towards making LLMs more grounded and factual through memory augmentation.

Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial robustness by learning and reasoning on the training classification distribution. GenFighter identifies potentially malicious instances deviating from the distribution, transforms them into semantically equivalent instances aligned with the training data, and employs ensemble techniques for a unified and robust response. By conducting extensive experiments, we show that GenFighter outperforms state-of-the-art defenses in accuracy under attack and attack success rate metrics. Additionally, it requires a high number of queries per attack, making the attack more challenging in real scenarios. The ablation study shows that our approach integrates transfer learning, a generative/evolutive procedure, and an ensemble method, providing an effective defense against NLP adversarial attacks.

Communal violence in online forums has become extremely prevalent in South Asia, where many communities of different cultures coexist and share resources. These societies exhibit a phenomenon characterized by strong bonds within their own groups and animosity towards others, leading to conflicts that frequently escalate into violent confrontations. To address this issue, we have developed the first comprehensive framework for the automatic detection of communal violence markers in online Bangla content accompanying the largest collection (13K raw sentences) of social media interactions that fall under the definition of four major violence class and their 16 coarse expressions. Our workflow introduces a 7-step expert annotation process incorporating insights from social scientists, linguists, and psychologists. By presenting data statistics and benchmarking performance using this dataset, we have determined that, aside from the category of Non-communal violence, Religio-communal violence is particularly pervasive in Bangla text. Moreover, we have substantiated the effectiveness of fine-tuning language models in identifying violent comments by conducting preliminary benchmarking on the state-of-the-art Bangla deep learning model.

Bin packing is a classic optimization problem with a wide range of applications, from load balancing to supply chain management. In this work, we study the online variant of the problem, in which a sequence of items of various sizes must be placed into a minimum number of bins of uniform capacity. The online algorithm is enhanced with a (potentially erroneous) prediction concerning the frequency of item sizes in the sequence. We design and analyze online algorithms with efficient tradeoffs between the consistency (i.e., the competitive ratio assuming no prediction error) and the robustness (i.e., the competitive ratio under adversarial error), and whose performance degrades near-optimally as a function of the prediction error. This is the first theoretical and experimental study of online bin packing under competitive analysis, in the realistic setting of learnable predictions. Previous work addressed only extreme cases with respect to the prediction error, and relied on overly powerful and error-free oracles.

Unanswered questions about how human-AV interaction designers can support rider's informational needs hinders Autonomous Vehicles (AV) adoption. To achieve joint human-AV action goals - such as safe transportation, trust, or learning from an AV - sufficient situational awareness must be held by the human, AV, and human-AV system collectively. We present a systems-level framework that integrates cognitive theories of joint action and situational awareness as a means to tailor communications that meet the criteria necessary for goal success. This framework is based on four components of the shared situation: AV traits, action goals, subject-specific traits and states, and the situated driving context. AV communications should be tailored to these factors and be sensitive when they change. This framework can be useful for understanding individual, shared, and distributed human-AV situational awareness and designing for future AV communications that meet the informational needs and goals of diverse groups and in diverse driving contexts.