Kun Sun

Kun Sun, Rong Wang, Anders Søgaard

Amidst the rapid evolution of LLMs, the significance of evaluation in comprehending and propelling these models forward is increasingly paramount. Evaluations have revealed that factors such as scaling, training types, architectures and other factors profoundly impact the performance of LLMs. However, the extent and nature of these impacts continue to be subjects of debate because most assessments have been restricted to a limited number of models and data points. Clarifying the effects of these factors on performance scores can be more effectively achieved through a statistical lens. Our study embarks on a thorough re-examination of these LLMs, targeting the inadequacies in current evaluation methods. With the advent of a uniform evaluation framework, our research leverages an expansive dataset of evaluation results, introducing a comprehensive statistical methodology. This includes the application of ANOVA, Tukey HSD tests, GAMM, and clustering technique, offering a robust and transparent approach to deciphering LLM performance data. Contrary to prevailing findings, our results challenge assumptions about emergent abilities and the influence of given training types and architectures in LLMs. These findings furnish new perspectives on the characteristics, intrinsic nature, and developmental trajectories of LLMs. By providing straightforward and reliable methods to scrutinize and reassess LLM performance data, this study contributes a nuanced perspective on LLM efficiency and potentials.

Kun Sun, Rong Wang

The majority of research in computational psycholinguistics has concentrated on the processing of words. This study introduces innovative methods for computing sentence-level metrics using multilingual large language models. The metrics developed sentence surprisal and sentence relevance and then are tested and compared to validate whether they can predict how humans comprehend sentences as a whole across languages. These metrics offer significant interpretability and achieve high accuracy in predicting human sentence reading speeds. Our results indicate that these computational sentence-level metrics are exceptionally effective at predicting and elucidating the processing difficulties encountered by readers in comprehending sentences as a whole across a variety of languages. Their impressive performance and generalization capabilities provide a promising avenue for future research in integrating LLMs and cognitive science.

Kun Sun

In recent years, several influential computational models and metrics have been proposed to predict how humans comprehend and process sentence. One particularly promising approach is contextual semantic similarity. Inspired by the attention algorithm in Transformer and human memory mechanisms, this study proposes an ``attention-aware'' approach for computing contextual semantic relevance. This new approach takes into account the different contributions of contextual parts and the expectation effect, allowing it to incorporate contextual information fully. The attention-aware approach also facilitates the simulation of existing reading models and evaluate them. The resulting ``attention-aware'' metrics of semantic relevance can more accurately predict fixation durations in Chinese reading tasks recorded in an eye-tracking corpus than those calculated by existing approaches. The study's findings further provide strong support for the presence of semantic preview benefits in Chinese naturalistic reading. Furthermore, the attention-aware metrics of semantic relevance, being memory-based, possess high interpretability from both linguistic and cognitive standpoints, making them a valuable computational tool for modeling eye-movements in reading and further gaining insight into the process of language comprehension. Our approach underscores the potential of these metrics to advance our comprehension of how humans understand and process language, ultimately leading to a better understanding of language comprehension and processing.

Rong Wang, Kun Sun

This study employs deep learning techniques to explore four speaker profiling tasks on the TIMIT dataset, namely gender classification, accent classification, age estimation, and speaker identification, highlighting the potential and challenges of multi-task learning versus single-task models. The motivation for this research is twofold: firstly, to empirically assess the advantages and drawbacks of multi-task learning over single-task models in the context of speaker profiling; secondly, to emphasize the undiminished significance of skillful feature engineering for speaker recognition tasks. The findings reveal challenges in accent classification, and multi-task learning is found advantageous for tasks of similar complexity. Non-sequential features are favored for speaker recognition, but sequential ones can serve as starting points for complex models. The study underscores the necessity of meticulous experimentation and parameter tuning for deep learning models.

Kun Sun, Rong Wang

Data-driven approaches have revolutionized scientific research, with machine learning and statistical analysis being commonly used methodologies. Despite their widespread use, these approaches differ significantly in their techniques, objectives and implementations. Few studies have systematically applied both methods to identical datasets to highlight potential differences, particularly in language and cognitive sciences. This study employs the Buckeye Speech Corpus to illustrate how machine learning and statistical analysis are applied in data-driven research to obtain distinct insights on language production. We demonstrate the theoretical differences, implementation steps, and unique objectives of each approach through a comprehensive, tutorial-like comparison. Our analysis reveals that while machine learning excels at pattern recognition and prediction, statistical methods provide deeper insights into relationships between variables. The study highlights how semantic relevance, a novel metric measuring contextual influence on target words, contributes to understanding word duration in speech. We also systematically compare the differences between regression models used in machine learning and statistical analysis, particularly focusing on the training and fitting processes. Additionally, we clarify several common misconceptions that contribute to the confusion between these two approaches. Overall, by elucidating the complementary strengths of machine learning and statistics, this research enhances our understanding of diverse data-driven strategies in language and cognitive sciences, offering researchers valuable guidance on when and how to effectively apply these approaches in different research contexts.

Kun Sun, Rong Wang

Machine Translation (MT) Quality Estimation (QE) assesses translation reliability without reference texts. This study introduces "textual similarity" as a new metric for QE, using sentence transformers and cosine similarity to measure semantic closeness. Analyzing data from the MLQE-PE dataset, we found that textual similarity exhibits stronger correlations with human scores than traditional metrics (hter, model evaluation, sentence probability etc.). Employing GAMMs as a statistical tool, we demonstrated that textual similarity consistently outperforms other metrics across multiple language pairs in predicting human scores. We also found that "hter" actually failed to predict human scores in QE. Our findings highlight the effectiveness of textual similarity as a robust QE metric, recommending its integration with other metrics into QE frameworks and MT system training for improved accuracy and usability.