Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language

We are exposed to much information trying to influence us, such as teaser messages, debates, politically framed news, and propaganda - all of which use persuasive language. With the recent interest in Large Language Models (LLMs), we study the ability of LLMs to produce persuasive text. As opposed to prior work which focuses on particular domains or types of persuasion, we conduct a general study across various domains to measure and benchmark to what degree LLMs produce persuasive text - both when explicitly instructed to rewrite text to be more or less persuasive and when only instructed to paraphrase. To this end, we construct a new dataset, Persuasive-Pairs, of pairs each consisting of a short text and of a text rewritten by an LLM to amplify or diminish persuasive language. We multi-annotate the pairs on a relative scale for persuasive language. This data is not only a valuable resource in itself, but we also show that it can be used to train a regression model to predict a score of persuasive language between text pairs. This model can score and benchmark new LLMs across domains, thereby facilitating the comparison of different LLMs. Finally, we discuss effects observed for different system prompts. Notably, we find that different 'personas' in the system prompt of LLaMA3 change the persuasive language in the text substantially, even when only instructed to paraphrase. These findings underscore the importance of investigating persuasive language in LLM generated text.

Wiki Entity Summarization Benchmark

Entity summarization aims to compute concise summaries for entities in knowledge graphs. Existing datasets and benchmarks are often limited to a few hundred entities and discard graph structure in source knowledge graphs. This limitation is particularly pronounced when it comes to ground-truth summaries, where there exist only a few labeled summaries for evaluation and training. We propose WikES, a comprehensive benchmark comprising of entities, their summaries, and their connections. Additionally, WikES features a dataset generator to test entity summarization algorithms in different areas of the knowledge graph. Importantly, our approach combines graph algorithms and NLP models as well as different data sources such that WikES does not require human annotation, rendering the approach cost-effective and generalizable to multiple domains. Finally, WikES is scalable and capable of capturing the complexities of knowledge graphs in terms of topology and semantics. WikES features existing datasets for comparison. Empirical studies of entity summarization methods confirm the usefulness of our benchmark. Data, code, and models are available at: https://github.com/msorkhpar/wiki-entity-summarization.

RainAI -- Precipitation Nowcasting from Satellite Data

This paper presents a solution to the Weather4Cast 2023 competition, where the goal is to forecast high-resolution precipitation with an 8-hour lead time using lower-resolution satellite radiance images. We propose a simple, yet effective method for spatiotemporal feature learning using a 2D U-Net model, that outperforms the official 3D U-Net baseline in both performance and efficiency. We place emphasis on refining the dataset, through importance sampling and dataset preparation, and show that such techniques have a significant impact on performance. We further study an alternative cross-entropy loss function that improves performance over the standard mean squared error loss, while also enabling models to produce probabilistic outputs. Additional techniques are explored regarding the generation of predictions at different lead times, specifically through Conditioning Lead Time. Lastly, to generate high-resolution forecasts, we evaluate standard and learned upsampling methods. The code and trained parameters are available at https://github.com/rafapablos/w4c23-rainai.

ActUp: Analyzing and Consolidating tSNE and UMAP

tSNE and UMAP are popular dimensionality reduction algorithms due to their speed and interpretable low-dimensional embeddings. Despite their popularity, however, little work has been done to study their full span of differences. We theoretically and experimentally evaluate the space of parameters in both tSNE and UMAP and observe that a single one -- the normalization -- is responsible for switching between them. This, in turn, implies that a majority of the algorithmic differences can be toggled without affecting the embeddings. We discuss the implications this has on several theoretic claims behind UMAP, as well as how to reconcile them with existing tSNE interpretations. Based on our analysis, we provide a method (\ourmethod) that combines previously incompatible techniques from tSNE and UMAP and can replicate the results of either algorithm. This allows our method to incorporate further improvements, such as an acceleration that obtains either method's outputs faster than UMAP. We release improved versions of tSNE, UMAP, and \ourmethod that are fully plug-and-play with the traditional libraries at https://github.com/Andrew-Draganov/GiDR-DUN

GiDR-DUN; Gradient Dimensionality Reduction -- Differences and Unification

TSNE and UMAP are two of the most popular dimensionality reduction algorithms due to their speed and interpretable low-dimensional embeddings. However, while attempts have been made to improve on TSNE's computational complexity, no existing method can obtain TSNE embeddings at the speed of UMAP. In this work, we show that this is indeed possible by combining the two approaches into a single method. We theoretically and experimentally evaluate the full space of parameters in the TSNE and UMAP algorithms and observe that a single parameter, the normalization, is responsible for switching between them. This, in turn, implies that a majority of the algorithmic differences can be toggled without affecting the embeddings. We discuss the implications this has on several theoretic claims underpinning the UMAP framework, as well as how to reconcile them with existing TSNE interpretations. Based on our analysis, we propose a new dimensionality reduction algorithm, GDR, that combines previously incompatible techniques from TSNE and UMAP and can replicate the results of either algorithm by changing the normalization. As a further advantage, GDR performs the optimization faster than available UMAP methods and thus an order of magnitude faster than available TSNE methods. Our implementation is plug-and-play with the traditional UMAP and TSNE libraries and can be found at github.com/Andrew-Draganov/GiDR-DUN.

Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding

Large-scale crop type classification is a task at the core of remote sensing efforts with applications of both economic and ecological importance. Current state-of-the-art deep learning methods are based on self-attention and use satellite image time series (SITS) to discriminate crop types based on their unique growth patterns. However, existing methods generalize poorly to regions not seen during training mainly due to not being robust to temporal shifts of the growing season caused by variations in climate. To this end, we propose Thermal Positional Encoding (TPE) for attention-based crop classifiers. Unlike previous positional encoding based on calendar time (e.g. day-of-year), TPE is based on thermal time, which is obtained by accumulating daily average temperatures over the growing season. Since crop growth is directly related to thermal time, but not calendar time, TPE addresses the temporal shifts between different regions to improve generalization. We propose multiple TPE strategies, including learnable methods, to further improve results compared to the common fixed positional encodings. We demonstrate our approach on a crop classification task across four different European regions, where we obtain state-of-the-art generalization results.

Weakly-Supervised Cloud Detection with Fixed-Point GANs

The detection of clouds in satellite images is an essential preprocessing task for big data in remote sensing. Convolutional neural networks (CNNs) have greatly advanced the state-of-the-art in the detection of clouds in satellite images, but existing CNN-based methods are costly as they require large amounts of training images with expensive pixel-level cloud labels. To alleviate this cost, we propose Fixed-Point GAN for Cloud Detection (FCD), a weakly-supervised approach. Training with only image-level labels, we learn fixed-point translation between clear and cloudy images, so only clouds are affected during translation. Doing so enables our approach to predict pixel-level cloud labels by translating satellite images to clear ones and setting a threshold to the difference between the two images. Moreover, we propose FCD+, where we exploit the label-noise robustness of CNNs to refine the prediction of FCD, leading to further improvements. We demonstrate the effectiveness of our approach on the Landsat-8 Biome cloud detection dataset, where we obtain performance close to existing fully-supervised methods that train with expensive pixel-level labels. By fine-tuning our FCD+ with just 1% of the available pixel-level labels, we match the performance of fully-supervised methods.

TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation

The recent developments of deep learning models that capture the complex temporal patterns of crop phenology have greatly advanced crop classification of Satellite Image Time Series (SITS). However, when applied to target regions spatially different from the training region, these models perform poorly without any target labels due to the temporal shift of crop phenology between regions. To address this unsupervised cross-region adaptation setting, existing methods learn domain-invariant features without any target supervision, but not the temporal shift itself. As a consequence, these techniques provide only limited benefits for SITS. In this paper, we propose TimeMatch, a new unsupervised domain adaptation method for SITS that directly accounts for the temporal shift. TimeMatch consists of two components: 1) temporal shift estimation, which estimates the temporal shift of the unlabeled target region with a source-trained model, and 2) TimeMatch learning, which combines temporal shift estimation with semi-supervised learning to adapt a classifier to an unlabeled target region. We also introduce an open-access dataset for cross-region adaptation with SITS from four different regions in Europe. On this dataset, we demonstrate that TimeMatch outperforms all competing methods by 11% in F1-score across five different adaptation scenarios, setting a new state-of-the-art for cross-region adaptation.

On Quantitative Evaluations of Counterfactuals

As counterfactual examples become increasingly popular for explaining decisions of deep learning models, it is essential to understand what properties quantitative evaluation metrics do capture and equally important what they do not capture. Currently, such understanding is lacking, potentially slowing down scientific progress. In this paper, we consolidate the work on evaluating visual counterfactual examples through an analysis and experiments. We find that while most metrics behave as intended for sufficiently simple datasets, some fail to tell the difference between good and bad counterfactuals when the complexity increases. We observe experimentally that metrics give good scores to tiny adversarial-like changes, wrongly identifying such changes as superior counterfactual examples. To mitigate this issue, we propose two new metrics, the Label Variation Score and the Oracle score, which are both less vulnerable to such tiny changes. We conclude that a proper quantitative evaluation of visual counterfactual examples should combine metrics to ensure that all aspects of good counterfactuals are quantified.

Learning by Design: Structuring and Documenting the Human Choices in Machine Learning Development

The influence of machine learning (ML) is quickly spreading, and a number of recent technological innovations have applied ML as a central technology. However, ML development still requires a substantial amount of human expertise to be successful. The deliberation and expert judgment applied during ML development cannot be revisited or scrutinized if not properly documented, and this hinders the further adoption of ML technologies--especially in safety critical situations. In this paper, we present a method consisting of eight design questions, that outline the deliberation and normative choices going into creating a ML model. Our method affords several benefits, such as supporting critical assessment through methodological transparency, aiding in model debugging, and anchoring model explanations by committing to a pre hoc expectation of the model's behavior. We believe that our method can help ML practitioners structure and justify their choices and assumptions when developing ML models, and that it can help bridge a gap between those inside and outside the ML field in understanding how and why ML models are designed and developed the way they are.