Understanding the conversation abilities of Large Language Models (LLMs) can help lead to its more cautious and appropriate deployment. This is especially important for safety-critical domains like mental health, where someone's life may depend on the exact wording of a response to an urgent question. In this paper, we propose a novel framework for evaluating the nuanced conversation abilities of LLMs. Within it, we develop a series of quantitative metrics developed from literature on using psychotherapy conversation analysis literature. While we ensure that our framework and metrics are transferable by researchers to relevant adjacent domains, we apply them to the mental health field. We use our framework to evaluate several popular frontier LLMs, including some GPT and Llama models, through a verified mental health dataset. Our results show that GPT4 Turbo can perform significantly more similarly to verified therapists than other selected LLMs. We conduct additional analysis to examine how LLM conversation performance varies across specific mental health topics. Our results indicate that GPT4 Turbo performs well in achieving high correlation with verified therapists in particular topics such as Parenting and Relationships. We believe our contributions will help researchers develop better LLMs that, in turn, will more positively support people's lives.

Multi-contrast (MC) Magnetic Resonance Imaging (MRI) reconstruction aims to incorporate a reference image of auxiliary modality to guide the reconstruction process of the target modality. Known MC reconstruction methods perform well with a fully sampled reference image, but usually exhibit inferior performance, compared to single-contrast (SC) methods, when the reference image is missing or of low quality. To address this issue, we propose DuDoUniNeXt, a unified dual-domain MRI reconstruction network that can accommodate to scenarios involving absent, low-quality, and high-quality reference images. DuDoUniNeXt adopts a hybrid backbone that combines CNN and ViT, enabling specific adjustment of image domain and k-space reconstruction. Specifically, an adaptive coarse-to-fine feature fusion module (AdaC2F) is devised to dynamically process the information from reference images of varying qualities. Besides, a partially shared shallow feature extractor (PaSS) is proposed, which uses shared and distinct parameters to handle consistent and discrepancy information among contrasts. Experimental results demonstrate that the proposed model surpasses state-of-the-art SC and MC models significantly. Ablation studies show the effectiveness of the proposed hybrid backbone, AdaC2F, PaSS, and the dual-domain unified learning scheme.

Acquiring factual knowledge for language models (LMs) in low-resource languages poses a serious challenge, thus resorting to cross-lingual transfer in multilingual LMs (ML-LMs). In this study, we ask how ML-LMs acquire and represent factual knowledge. Using the multilingual factual knowledge probing dataset, mLAMA, we first conducted a neuron investigation of ML-LMs (specifically, multilingual BERT). We then traced the roots of facts back to the knowledge source (Wikipedia) to identify the ways in which ML-LMs acquire specific facts. We finally identified three patterns of acquiring and representing facts in ML-LMs: language-independent, cross-lingual shared and transferred, and devised methods for differentiating them. Our findings highlight the challenge of maintaining consistent factual knowledge across languages, underscoring the need for better fact representation learning in ML-LMs.

A major factor in the recent success of large language models is the use of enormous and ever-growing text datasets for unsupervised pre-training. However, naively training a model on all available data may not be optimal (or feasible), as the quality of available text data can vary. Filtering out data can also decrease the carbon footprint and financial costs of training models by reducing the amount of training required. Data selection methods aim to determine which candidate data points to include in the training dataset and how to appropriately sample from the selected data points. The promise of improved data selection methods has caused the volume of research in the area to rapidly expand. However, because deep learning is mostly driven by empirical evidence and experimentation on large-scale data is expensive, few organizations have the resources for extensive data selection research. Consequently, knowledge of effective data selection practices has become concentrated within a few organizations, many of which do not openly share their findings and methodologies. To narrow this gap in knowledge, we present a comprehensive review of existing literature on data selection methods and related research areas, providing a taxonomy of existing approaches. By describing the current landscape of research, this work aims to accelerate progress in data selection by establishing an entry point for new and established researchers. Additionally, throughout this review we draw attention to noticeable holes in the literature and conclude the paper by proposing promising avenues for future research.

The need for high-quality automated seizure detection algorithms based on electroencephalography (EEG) becomes ever more pressing with the increasing use of ambulatory and long-term EEG monitoring. Heterogeneity in validation methods of these algorithms influences the reported results and makes comprehensive evaluation and comparison challenging. This heterogeneity concerns in particular the choice of datasets, evaluation methodologies, and performance metrics. In this paper, we propose a unified framework designed to establish standardization in the validation of EEG-based seizure detection algorithms. Based on existing guidelines and recommendations, the framework introduces a set of recommendations and standards related to datasets, file formats, EEG data input content, seizure annotation input and output, cross-validation strategies, and performance metrics. We also propose the 10-20 seizure detection benchmark, a machine-learning benchmark based on public datasets converted to a standardized format. This benchmark defines the machine-learning task as well as reporting metrics. We illustrate the use of the benchmark by evaluating a set of existing seizure detection algorithms. The SzCORE (Seizure Community Open-source Research Evaluation) framework and benchmark are made publicly available along with an open-source software library to facilitate research use, while enabling rigorous evaluation of the clinical significance of the algorithms, fostering a collective effort to more optimally detect seizures to improve the lives of people with epilepsy.

Despite the recent advances in model compression techniques for Model compression techniques such as quantization have been deep neural networks, deploying such models on ultra-low-power successfully applied to Convolutional Neural Networks (CNNs), embedded devices still proves challenging. In particular, quantization allowing them to be deployed on embedded devices with limited schemes for Gated Recurrent Units (GRU) are difficult to computational resources. Remarkably, the quantization of RNNs tune due to their dependence on an internal state, preventing them has not been explored as extensively, potentially due to the additional from fully benefiting from sub-8bit quantization. In this work, we complexity introduced by their recurrent nature. Among the propose a modular integer quantization scheme for GRUs where the most notable works, [1] propose binary, ternary, and quaternary bit width of each operator can be selected independently. We then quantization schemes for RNNs and evaluate it on sentiment analysis, employ Genetic Algorithms (GA) to explore the vast search space [11] combines structural pruning and 8-bit quantization to of possible bit widths, simultaneously optimizing for model size optimize LSTMs for speech enhancement on a Cortex-M7 embedded and accuracy. We evaluate our methods on four different sequential platform, [20] presents quantization schemes for the standard tasks and demonstrate that mixed-precision solutions exceed LSTM and its variants, based on fixed-point arithmetic, evaluating homogeneous-precision ones in terms of Pareto efficiency. Our them on speech recognition; finally [26] employs mixed-precision results show a model size reduction between 25% and 55% while FP16 and 8-bit integer quantization to deploy speech enhancement maintaining an accuracy comparable with the 8-bit homogeneous models based on LSTMs or GRUs on a RISC-V embedded target.

Contextualized embeddings are the preferred tool for modeling Lexical Semantic Change (LSC). Current evaluations typically focus on a specific task known as Graded Change Detection (GCD). However, performance comparison across work are often misleading due to their reliance on diverse settings. In this paper, we evaluate state-of-the-art models and approaches for GCD under equal conditions. We further break the LSC problem into Word-in-Context (WiC) and Word Sense Induction (WSI) tasks, and compare models across these different levels. Our evaluation is performed across different languages on eight available benchmarks for LSC, and shows that (i) APD outperforms other approaches for GCD; (ii) XL-LEXEME outperforms other contextualized models for WiC, WSI, and GCD, while being comparable to GPT-4; (iii) there is a clear need for improving the modeling of word meanings, as well as focus on how, when, and why these meanings change, rather than solely focusing on the extent of semantic change.

Sentence simplification, which rewrites a sentence to be easier to read and understand, is a promising technique to help people with various reading difficulties. With the rise of advanced large language models (LLMs), evaluating their performance in sentence simplification has become imperative. Recent studies have used both automatic metrics and human evaluations to assess the simplification abilities of LLMs. However, the suitability of existing evaluation methodologies for LLMs remains in question. First, the suitability of current automatic metrics on LLMs' simplification evaluation is still uncertain. Second, current human evaluation approaches in sentence simplification often fall into two extremes: they are either too superficial, failing to offer a clear understanding of the models' performance, or overly detailed, making the annotation process complex and prone to inconsistency, which in turn affects the evaluation's reliability. To address these problems, this study provides in-depth insights into LLMs' performance while ensuring the reliability of the evaluation. We design an error-based human annotation framework to assess the GPT-4's simplification capabilities. Results show that GPT-4 generally generates fewer erroneous simplification outputs compared to the current state-of-the-art. However, LLMs have their limitations, as seen in GPT-4's struggles with lexical paraphrasing. Furthermore, we conduct meta-evaluations on widely used automatic metrics using our human annotations. We find that while these metrics are effective for significant quality differences, they lack sufficient sensitivity to assess the overall high-quality simplification by GPT-4.

Explainability models are now prevalent within machine learning to address the black-box nature of neural networks. The question now is which explainability model is most effective. Probabilistic Lipschitzness has demonstrated that the smoothness of a neural network is fundamentally linked to the quality of post hoc explanations. In this work, we prove theoretical lower bounds on the probabilistic Lipschitzness of Integrated Gradients, LIME and SmoothGrad. We propose a novel metric using probabilistic Lipschitzness, normalised astuteness, to compare the robustness of explainability models. Further, we prove a link between the local Lipschitz constant of a neural network and its stable rank. We then demonstrate that the stable rank of a neural network provides a heuristic for the robustness of explainability models.

Long-context large language models (LLMs) hold promise for tasks such as question-answering (QA) over long documents, but they tend to miss important information in the middle of context documents (arXiv:2307.03172v3). Here, we introduce $\textit{R&R}$ -- a combination of two novel prompt-based methods called $\textit{reprompting}$ and $\textit{in-context retrieval}$ (ICR) -- to alleviate this effect in document-based QA. In reprompting, we repeat the prompt instructions periodically throughout the context document to remind the LLM of its original task. In ICR, rather than instructing the LLM to answer the question directly, we instruct it to retrieve the top $k$ passage numbers most relevant to the given question, which are then used as an abbreviated context in a second QA prompt. We test R&R with GPT-4 Turbo and Claude-2.1 on documents up to 80k tokens in length and observe a 16-point boost in QA accuracy on average. Our further analysis suggests that R&R improves performance on long document-based QA because it reduces the distance between relevant context and the instructions. Finally, we show that compared to short-context chunkwise methods, R&R enables the use of larger chunks that cost fewer LLM calls and output tokens, while minimizing the drop in accuracy.