Automated assessment in natural language generation is a challenging task. Instruction-tuned large language models (LLMs) have shown promise in reference-free evaluation, particularly through comparative assessment. However, the quadratic computational complexity of pairwise comparisons limits its scalability. To address this, efficient comparative assessment has been explored by applying comparative strategies on zero-shot LLM probabilities. We propose a framework for finetuning LLMs for comparative assessment to align the model's output with the target distribution of comparative probabilities. By training on soft probabilities, our approach improves state-of-the-art performance while maintaining high performance with an efficient subset of comparisons.

Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applications, no existing work has analyzed the vulnerability of judge-LLMs to adversarial manipulation. This work presents the first study on the adversarial robustness of assessment LLMs, where we demonstrate that short universal adversarial phrases can be concatenated to deceive judge LLMs to predict inflated scores. Since adversaries may not know or have access to the judge-LLMs, we propose a simple surrogate attack where a surrogate model is first attacked, and the learned attack phrase then transferred to unknown judge-LLMs. We propose a practical algorithm to determine the short universal attack phrases and demonstrate that when transferred to unseen models, scores can be drastically inflated such that irrespective of the assessed text, maximum scores are predicted. It is found that judge-LLMs are significantly more susceptible to these adversarial attacks when used for absolute scoring, as opposed to comparative assessment. Our findings raise concerns on the reliability of LLM-as-a-judge methods, and emphasize the importance of addressing vulnerabilities in LLM assessment methods before deployment in high-stakes real-world scenarios.

LLM-as-a-judge approaches are a practical and effective way of assessing a range of text tasks, aligning with human judgements especially when applied in a comparative assessment fashion. However, when using pairwise comparisons to rank a set of candidates the computational costs scale quadratically with the number of candidates, which can have practical limitations. This paper introduces a Product of Expert (PoE) framework for efficient LLM Comparative Assessment. Here individual comparisons are considered experts that provide information on a pair's score difference. The PoE framework combines the information from these experts to yield an expression that can be maximized with respect to the underlying set of candidates, and is highly flexible where any form of expert can be assumed. When Gaussian experts are used one can derive simple closed-form solutions for the optimal candidate ranking, as well as expressions for selecting which comparisons should be made to maximize the probability of this ranking. Our approach enables efficient comparative assessment, where by using only a small subset of the possible comparisons, one can generate score predictions that correlate as well to human judgements as the predictions when all comparisons are used. We evaluate the approach on multiple NLG tasks and demonstrate that our framework can yield considerable computational savings when performing pairwise comparative assessment. When N is large, with as few as 2% of comparisons the PoE solution can achieve similar performance to when all comparisons are used.

Watermarking generative-AI systems, such as LLMs, has gained considerable interest, driven by their enhanced capabilities across a wide range of tasks. Although current approaches have demonstrated that small, context-dependent shifts in the word distributions can be used to apply and detect watermarks, there has been little work in analyzing the impact that these perturbations have on the quality of generated texts. Balancing high detectability with minimal performance degradation is crucial in terms of selecting the appropriate watermarking setting; therefore this paper proposes a simple analysis framework where comparative assessment, a flexible NLG evaluation framework, is used to assess the quality degradation caused by a particular watermark setting. We demonstrate that our framework provides easy visualization of the quality-detection trade-off of watermark settings, enabling a simple solution to find an LLM watermark operating point that provides a well-balanced performance. This approach is applied to two different summarization systems and a translation system, enabling cross-model analysis for a task, and cross-task analysis.

Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks, however they sometimes fail to maintain crucial invariances for specific tasks. One example is permutation sensitivity, where LLMs' outputs may significantly vary depending on the order of the input options. While debiasing techniques can mitigate these issues, and yield better performance and reliability, they often come with a high computational cost at inference. This paper addresses this inefficiency at inference time. The aim is to distill the capabilities of a computationally intensive, debiased, teacher model into a more compact student model. We explore two variants of student models: one based on pure distillation, and the other on an error-correction approach for more complex tasks, where the student corrects a single biased decision from the teacher to achieve a debiased output. Our approach is general and can be applied to both black-box and white-box LLMs. Furthermore, we demonstrate that our compact, encoder-only student models can outperform their larger, biased teacher counterparts, achieving better results with significantly fewer parameters.

Multiscale phenomena manifest across various scientific domains, presenting a ubiquitous challenge in accurately and effectively predicting multiscale dynamics in complex systems. In this paper, a novel decoupling solving mode is proposed through modelling large-scale dynamics independently and treating small-scale dynamics as a slaved system. A Spectral Physics-informed Neural Network (PINN) is developed to characterize the small-scale system in an efficient and accurate way. The effectiveness of the method is demonstrated through extensive numerical experiments, including one-dimensional Kuramot-Sivashinsky equation, two- and three-dimensional Navier-Stokes equations, showcasing its versatility in addressing problems of fluid dynamics. Furthermore, we also delve into the application of the proposed approach to more complex problems, including non-uniform meshes, complex geometries, large-scale data with noise, and high-dimensional small-scale dynamics. The discussions about these scenarios contribute to a comprehensive understanding of the method's capabilities and limitations. This paper presents a valuable and promising approach to enhance the computational simulations of multiscale spatiotemporal systems, which enables the acquisition of large-scale data with minimal computational demands, followed by Spectral PINN to capture small-scale dynamics with improved efficiency and accuracy.

Current developments in large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. An interesting application of these systems is in the automated assessment of natural language generation (NLG), a highly challenging area with great practical benefit. In this paper, we explore two options for exploiting the emergent abilities of LLMs for zero-shot NLG assessment: absolute score prediction, and comparative assessment which uses relative comparisons between pairs of candidates. Though comparative assessment has not been extensively studied in NLG assessment, we note that humans often find it more intuitive to compare two options rather than scoring each one independently. This work examines comparative assessment from multiple perspectives: performance compared to absolute grading; positional biases in the prompt; and efficient ranking in terms of the number of comparisons. We illustrate that LLM comparative assessment is a simple, general and effective approach for NLG assessment. For moderate-sized open-source LLMs, such as FlanT5 and Llama2-chat, comparative assessment is superior to prompt scoring, and in many cases can achieve performance competitive with state-of-the-art methods. Additionally, we demonstrate that LLMs often exhibit strong positional biases when making pairwise comparisons, and we propose debiasing methods that can further improve performance.

With a rapidly increasing amount and diversity of remote sensing (RS) data sources, there is a strong need for multi-view learning modeling. This is a complex task when considering the differences in resolution, magnitude, and noise of RS data. The typical approach for merging multiple RS sources has been input-level fusion, but other - more advanced - fusion strategies may outperform this traditional approach. This work assesses different fusion strategies for crop classification in the CropHarvest dataset. The fusion methods proposed in this work outperform models based on individual views and previous fusion methods. We do not find one single fusion method that consistently outperforms all other approaches. Instead, we present a comparison of multi-view fusion methods for three different datasets and show that, depending on the test region, different methods obtain the best performance. Despite this, we suggest a preliminary criterion for the selection of fusion methods.

In this case study we trained and published a state-of-the-art open-source model for Automatic Speech Recognition (ASR) for German to evaluate the current potential of this technology for the use in the larger context of Digital Humanities and cultural heritage indexation. Along with this paper we publish our wav2vec2 based speech to text model while we evaluate its performance on a corpus of historical recordings we assembled compared against commercial cloud-based and proprietary services. While our model achieves moderate results, we see that proprietary cloud services fare significantly better. As our results show, recognition rates over 90 percent can currently be achieved, however, these numbers drop quickly once the recordings feature limited audio quality or use of non-every day or outworn language. A big issue is the high variety of different dialects and accents in the German language. Nevertheless, this paper highlights that the currently available quality of recognition is high enough to address various use cases in the Digital Humanities. We argue that ASR will become a key technology for the documentation and analysis of audio-visual sources and identify an array of important questions that the DH community and cultural heritage stakeholders will have to address in the near future.

Accurate quantification of snowfall rate from space is important, but has remained difficult. Four years (2007‐2010) of NOAA‐18 Microwave Humidity Sounder (MHS) data are trained and tested with snowfall estimates from coincident CloudSat Cloud Profiling Radar (CPR) observations using several machine learning methods. Among the studied methods, random forest using MHS (RF‐MHS) is found the best for both detection and estimation of global snowfall. The RF‐MHS estimates are tested using independent years of coincident CPR snowfall estimates and compared with snowfall rates from Modern‐Era Retrospective analysis for Research and Applications Version 2 (MERRA‐2), Atmospheric Infrared Sounder (AIRS), and MHS Goddard Profiling Algorithm (GPROF). It was found that RF‐MHS algorithm can detect global snowfall with approximately 90% accuracy and a Heidke skill score of 0.48 compared to independent CloudSat samples. The surface wet bulb temperatures, brightness temperatures at 190 GHz, and 157 GHz channels are found to be the most important features to delineate snowfall areas.