Liqun He

Haoran Que, Feiyu Duan, Liqun He et al.

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks (e.g., long-context understanding), and many benchmarks have been proposed. However, we observe that long text generation capabilities are not well investigated. Therefore, we introduce the Hierarchical Long Text Generation Benchmark (HelloBench), a comprehensive, in-the-wild, and open-ended benchmark to evaluate LLMs' performance in generating long text. Based on Bloom's Taxonomy, HelloBench categorizes long text generation tasks into five subtasks: open-ended QA, summarization, chat, text completion, and heuristic text generation. Besides, we propose Hierarchical Long Text Evaluation (HelloEval), a human-aligned evaluation method that significantly reduces the time and effort required for human evaluation while maintaining a high correlation with human evaluation. We have conducted extensive experiments across around 30 mainstream LLMs and observed that the current LLMs lack long text generation capabilities. Specifically, first, regardless of whether the instructions include explicit or implicit length constraints, we observe that most LLMs cannot generate text that is longer than 4000 words. Second, we observe that while some LLMs can generate longer text, many issues exist (e.g., severe repetition and quality degradation). Third, to demonstrate the effectiveness of HelloEval, we compare HelloEval with traditional metrics (e.g., ROUGE, BLEU, etc.) and LLM-as-a-Judge methods, which show that HelloEval has the highest correlation with human evaluation. We release our code in https://github.com/Quehry/HelloBench.

Songlin Xu, Guanjie Wang, Ziyuan Fang et al.

We present HeadText, a hands-free technique on a smart earpiece for text entry by motion sensing. Users input text utilizing only 7 head gestures for key selection, word selection, word commitment and word cancelling tasks. Head gesture recognition is supported by motion sensing on a smart earpiece to capture head moving signals and machine learning algorithms (K-Nearest-Neighbor (KNN) with a Dynamic Time Warping (DTW) distance measurement). A 10-participant user study proved that HeadText could recognize 7 head gestures at an accuracy of 94.29%. After that, the second user study presented that HeadText could achieve a maximum accuracy of 10.65 WPM and an average accuracy of 9.84 WPM for text entry. Finally, we demonstrate potential applications of HeadText in hands-free scenarios for (a). text entry of people with motor impairments, (b). private text entry, and (c). socially acceptable text entry.

Liqun He, Jiaqi Xu

This study explores the use of generative AI for automating the classification of tutors' Dialogue Acts (DAs), aiming to reduce the time and effort required by traditional manual coding. This case study uses the open-source CIMA corpus, in which tutors' responses are pre-annotated into four DA categories. Both GPT-3.5-turbo and GPT-4 models were tested using tailored prompts. Results show that GPT-4 achieved 80% accuracy, a weighted F1-score of 0.81, and a Cohen's Kappa of 0.74, surpassing baseline performance and indicating substantial agreement with human annotations. These findings suggest that generative AI has strong potential to provide an efficient and accessible approach to DA classification, with meaningful implications for educational dialogue analysis. The study also highlights the importance of task-specific label definitions and contextual information in enhancing the quality of automated annotation. Finally, it underscores the ethical considerations associated with the use of generative AI and the need for responsible and transparent research practices. The script of this research is publicly available at https://github.com/liqunhe27/Generative-AI-for-educational-dialogue-act-tagging.

Liqun He, Shijun, Chen et al.

While generative AI (GenAI) voice chatbots offer scalable opportunities for second language (L2) oral practice, the interactional processes related to learners' gains remain underexplored. This study investigates dialogue act (DA) patterns in interactions between Grade 9 Chinese English as a foreign language (EFL) learners and a GenAI voice chatbot over a 10-week intervention. Seventy sessions from 12 students were annotated by human coders using a pedagogy-informed coding scheme, yielding 6,957 coded DAs. DA distributions and sequential patterns were compared between high- and low-progress sessions. At the DA level, high-progress sessions showed more learner-initiated questions, whereas low-progress sessions exhibited higher rates of clarification-seeking, indicating greater comprehension difficulty. At the sequential level, high-progress sessions were characterised by more frequent prompting-based corrective feedback sequences, consistently positioned after learner responses, highlighting the role of feedback type and timing in effective interaction. Overall, these findings underscore the value of a dialogic lens in GenAI chatbot design, contribute a pedagogy-informed DA coding framework, and inform the design of adaptive GenAI chatbots for L2 education.

Liqun He, Manolis Mavrikis, Mutlu Cukurova

Dialogue plays a crucial role in educational settings, yet existing evaluation methods for educational applications of large language models (LLMs) primarily focus on technical performance or learning outcomes, often neglecting attention to learner-LLM interactions. To narrow this gap, this AIED Doctoral Consortium paper presents an ongoing study employing a dialogue analysis approach to identify effective pedagogical strategies from learner-LLM dialogues. The proposed approach involves dialogue data collection, dialogue act (DA) annotation, DA pattern mining, and predictive model building. Early insights are outlined as an initial step toward future research. The work underscores the need to evaluate LLM-based educational applications by focusing on dialogue dynamics and pedagogical strategies.