Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition. However, limited study has been done on large language models' capability to perform conceptual reasoning. In this work, we bridge this gap and propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions and generate solutions in a verifiable symbolic space. Using this framework as an analytical tool, we show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks compared to direct inference methods. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making. We propose two techniques to add trustworthy induction signals by generating familiar questions with similar underlying reasoning paths and asking models to perform self-refinement. Experiments show that our proposed techniques improve models' conceptual reasoning performance by 8% to 11%, achieving a more robust reasoning system that relies less on inductive biases.

Counter narratives - informed responses to hate speech contexts designed to refute hateful claims and de-escalate encounters - have emerged as an effective hate speech intervention strategy. While previous work has proposed automatic counter narrative generation methods to aid manual interventions, the evaluation of these approaches remains underdeveloped. Previous automatic metrics for counter narrative evaluation lack alignment with human judgment as they rely on superficial reference comparisons instead of incorporating key aspects of counter narrative quality as evaluation criteria. To address prior evaluation limitations, we propose a novel evaluation framework prompting LLMs to provide scores and feedback for generated counter narrative candidates using 5 defined aspects derived from guidelines from counter narrative specialized NGOs. We found that LLM evaluators achieve strong alignment to human-annotated scores and feedback and outperform alternative metrics, indicating their potential as multi-aspect, reference-free and interpretable evaluators for counter narrative evaluation.

Conventional processes for analyzing datasets and extracting meaningful information are often time-consuming and laborious. Previous work has identified manual, repetitive coding and data collection as major obstacles that hinder data scientists from undertaking more nuanced labor and high-level projects. To combat this, we evaluated OpenAI's GPT-3.5 as a "Language Data Scientist" (LDS) that can extrapolate key findings, including correlations and basic information, from a given dataset. The model was tested on a diverse set of benchmark datasets to evaluate its performance across multiple standards, including data science code-generation based tasks involving libraries such as NumPy, Pandas, Scikit-Learn, and TensorFlow, and was broadly successful in correctly answering a given data science query related to the benchmark dataset. The LDS used various novel prompt engineering techniques to effectively answer a given question, including Chain-of-Thought reinforcement and SayCan prompt engineering. Our findings demonstrate great potential for leveraging Large Language Models for low-level, zero-shot data analysis.

Monocular 3D detectors achieve remarkable performance on cars and smaller objects. However, their performance drops on larger objects, leading to fatal accidents. Some attribute the failures to training data scarcity or their receptive field requirements of large objects. In this paper, we highlight this understudied problem of generalization to large objects. We find that modern frontal detectors struggle to generalize to large objects even on nearly balanced datasets. We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects. To bridge this gap, we comprehensively investigate regression and dice losses, examining their robustness under varying error levels and object sizes. We mathematically prove that the dice loss leads to superior noise-robustness and model convergence for large objects compared to regression losses for a simplified case. Leveraging our theoretical insights, we propose SeaBird (Segmentation in Bird's View) as the first step towards generalizing to large objects. SeaBird effectively integrates BEV segmentation on foreground objects for 3D detection, with the segmentation head trained with the dice loss. SeaBird achieves SoTA results on the KITTI-360 leaderboard and improves existing detectors on the nuScenes leaderboard, particularly for large objects. Code and models at https://github.com/abhi1kumar/SeaBird

Scientific articles are long text documents organized into sections, each describing aspects of the research. Analyzing scientific production has become progressively challenging due to the increase in the number of available articles. Within this scenario, our approach consisted of fine-tuning transformer language models to generate sentence-level embeddings from scientific articles, considering the following labels: background, objective, methods, results, and conclusion. We trained our models on three datasets with contrastive learning. Two datasets are from the article's abstracts in the computer science and medical domains. Also, we introduce PMC-Sents-FULL, a novel dataset of sentences extracted from the full texts of medical articles. We compare the fine-tuned and baseline models in clustering and classification tasks to evaluate our approach. On average, clustering agreement measures values were five times higher. For the classification measures, in the best-case scenario, we had an average improvement in F1-micro of 30.73\%. Results show that fine-tuning sentence transformers with contrastive learning and using the generated embeddings in downstream tasks is a feasible approach to sentence classification in scientific articles. Our experiment codes are available on GitHub.

The widespread application of machine learning algorithms is a matter of increasing concern for the data privacy research community, and many have sought to develop privacy-preserving techniques for it. Among existing approaches, the homomorphic evaluation of ML algorithms stands out by performing operations directly over encrypted data, enabling strong guarantees of confidentiality. The homomorphic evaluation of inference algorithms is practical even for relatively deep Convolution Neural Networks (CNNs). However, training is still a major challenge, with current solutions often resorting to lightweight algorithms that can be unfit for solving more complex problems, such as image recognition. This work introduces the homomorphic evaluation of Wilkie, Stonham, and Aleksander's Recognition Device (WiSARD) and subsequent Weightless Neural Networks (WNNs) for training and inference on encrypted data. Compared to CNNs, WNNs offer better performance with a relatively small accuracy drop. We develop a complete framework for it, including several building blocks that can be of independent interest. Our framework achieves 91.7% accuracy on the MNIST dataset after only 3.5 minutes of encrypted training (multi-threaded), going up to 93.8% in 3.5 hours. For the HAM10000 dataset, we achieve 67.9% accuracy in just 1.5 minutes, going up to 69.9% after 1 hour. Compared to the state of the art on the HE evaluation of CNN training, Glyph (Lou et al., NeurIPS 2020), these results represent a speedup of up to 1200 times with an accuracy loss of at most 5.4%. For HAM10000, we even achieved a 0.65% accuracy improvement while being 60 times faster than Glyph. We also provide solutions for small-scale encrypted training. In a single thread on a desktop machine using less than 200MB of memory, we train over 1000 MNIST images in 12 minutes or over the entire Wisconsin Breast Cancer dataset in just 11 seconds.

Definition modelling (DM) is the task of automatically generating a dictionary definition for a specific word. Computational systems that are capable of DM can have numerous applications benefiting a wide range of audiences. As DM is considered a supervised natural language generation problem, these systems require large annotated datasets to train the machine learning (ML) models. Several DM datasets have been released for English and other high-resource languages. While Portuguese is considered a mid/high-resource language in most natural language processing tasks and is spoken by more than 200 million native speakers, there is no DM dataset available for Portuguese. In this research, we fill this gap by introducing DORE; the first dataset for Definition MOdelling for PoRtuguEse containing more than 100,000 definitions. We also evaluate several deep learning based DM models on DORE and report the results. The dataset and the findings of this paper will facilitate research and study of Portuguese in wider contexts. Keywords: Portuguese dataset, automatic generation of definitions, definition modelling, transfer learning, pretrained models.

Understanding data visualizations like charts and plots requires reasoning about both visual elements and numerics. Although strong in extractive questions, current chart visual question answering (chart VQA) models suffer on complex reasoning questions. In this work, we address the lack of reasoning ability by data augmentation. We leverage Large Language Models (LLMs), which have shown to have strong reasoning ability, as an automatic data annotator that generates question-answer annotations for chart images. The key innovation in our method lies in the Synthesize Step-by-Step strategy: our LLM-based data generator learns to decompose the complex question into step-by-step sub-questions (rationales), which are then used to derive the final answer using external tools, i.e. Python. This step-wise generation procedure is trained on synthetic data generated using a template-based QA generation pipeline. Experimental results highlight the significance of the proposed step-by-step generation. By training with the LLM-augmented data (LAMENDA), we significantly enhance the chart VQA models, achieving the state-of-the-art accuracy on the ChartQA and PlotQA datasets. In particular, our approach improves the accuracy of the previous state-of-the-art approach from 38% to 54% on the human-written questions in the ChartQA dataset, which needs strong reasoning. We hope our work underscores the potential of synthetic data and encourages further exploration of data augmentation using LLMs for reasoning-heavy tasks.

Foundational models benefit from pre-training on large amounts of unlabeled data and enable strong performance in a wide variety of applications with a small amount of labeled data. Such models can be particularly effective in analyzing brain signals, as this field encompasses numerous application scenarios, and it is costly to perform large-scale annotation. In this work, we present the largest foundation model in brain signals, Brant-2. Compared to Brant, a foundation model designed for intracranial neural signals, Brant-2 not only exhibits robustness towards data variations and modeling scales but also can be applied to a broader range of brain neural data. By experimenting on an extensive range of tasks, we demonstrate that Brant-2 is adaptive to various application scenarios in brain signals. Further analyses reveal the scalability of the Brant-2, validate each component's effectiveness, and showcase our model's ability to maintain performance in scenarios with scarce labels.

As mobile networks embrace the 5G era, the interest in adopting Reinforcement Learning (RL) algorithms to handle challenges in ultra-low-latency and high throughput scenarios increases. Simultaneously, the advent of packetized fronthaul networks imposes demanding requirements that traditional congestion control mechanisms cannot accomplish, highlighting the potential of RL-based congestion control algorithms. Although learning RL policies optimized for satisfying the stringent fronthaul requirements is feasible, the adoption of neural network models in real deployments still poses some challenges regarding real-time inference and interpretability. This paper proposes a methodology to deal with such challenges while maintaining the performance and generalization capabilities provided by a baseline RL policy. The method consists of (1) training a congestion control policy specialized in fronthaul-like networks via reinforcement learning, (2) collecting state-action experiences from the baseline, and (3) performing deep symbolic regression on the collected dataset. The proposed process overcomes the challenges related to inference-time limitations through closed-form expressions that approximate the baseline performance (link utilization, delay, and fairness) and which can be directly implemented in any programming language. Finally, we analyze the inner workings of the closed-form expressions.