This study investigates effective strategies for developing a customised GPT agent to code classroom dialogue. While classroom dialogue is widely recognised as a crucial element of education, its analysis remains challenging due to the need for a nuanced understanding of dialogic functions and the labour-intensive nature of manual transcript coding. Recent advancements in large language models offer promising avenues for automating this process. However, existing studies predominantly focus on training large-scale models or evaluating pre-trained models with fixed codebooks, which are often not applicable or replicable for dialogue researchers working with small datasets or customised coding schemes. Using GPT-4's MyGPT agent as a case, this study evaluates its baseline performance in coding classroom dialogue with a human codebook and examines how performance varies with different example inputs through a variable control method. Through a design-based research approach, it identifies a set of practical strategies, based on MyGPT's unique features, for configuring effective agents with limited data. The findings suggest that, despite some limitations, a MyGPT agent developed with these strategies can serve as a useful coding assistant by generating coding suggestions.

While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications. To address this issue, recent research mainly focuses on objective hallucination. However, for sequential images, besides objective hallucination, there is also behavioral hallucination, which is less studied. This work aims to fill in the gap. We first reveal that behavioral hallucinations mainly arise from two key factors: prior-driven bias and the snowball effect. Based on these observations, we introduce SHE (Sequence Hallucination Eradication), a lightweight, two-stage framework that (1) detects hallucinations via visual-textual alignment check using our proposed adaptive temporal window and (2) mitigates them via orthogonal projection onto the joint embedding space. We also propose a new metric (BEACH) to quantify behavioral hallucination severity. Empirical results on standard benchmarks demonstrate that SHE reduces behavioral hallucination by over 10% on BEACH while maintaining descriptive accuracy.

The widespread deployment of Large Language Models (LLMs) trained on massive, uncurated corpora has raised growing concerns about the inclusion of sensitive, copyrighted, or illegal content. This has led to increasing interest in LLM unlearning: the task of selectively removing specific information from a model without retraining from scratch or degrading overall utility. However, existing methods often rely on large-scale forget and retain datasets, and suffer from unnatural responses, poor generalization, or catastrophic utility loss. In this work, we propose Reinforcement UnLearning (RULE), an efficient framework that formulates unlearning as a refusal boundary optimization problem. RULE is trained with a small portion of the forget set and synthesized boundary queries, using a verifiable reward function that encourages safe refusal on forget--related queries while preserving helpful responses on permissible inputs. We provide both theoretical and empirical evidence demonstrating the effectiveness of RULE in achieving targeted unlearning without compromising model utility. Experimental results show that, with only $12%$ forget set and $8%$ synthesized boundary data, RULE outperforms existing baselines by up to $17.5%$ forget quality and $16.3%$ naturalness response while maintaining general utility, achieving forget--retain Pareto optimality. Remarkably, we further observe that RULE improves the naturalness of model outputs, enhances training efficiency, and exhibits strong generalization ability, generalizing refusal behavior to semantically related but unseen queries.

Progress in Natural Language Processing (NLP) has been dictated by the rule of more: more data, more computing power and more complexity, best exemplified by the Large Language Models. However, training (or fine-tuning) large dense models for specific applications usually requires significant amounts of computing resources. This \textbf{Ph.D. dissertation} focuses on an under-investi\-gated NLP data engineering technique, whose potential is enormous in the current scenario known as Instance Selection (IS). The IS goal is to reduce the training set size by removing noisy or redundant instances while maintaining the effectiveness of the trained models and reducing the training process cost. We provide a comprehensive and scientifically sound comparison of IS methods applied to an essential NLP task -- Automatic Text Classification (ATC), considering several classification solutions and many datasets. Our findings reveal a significant untapped potential for IS solutions. We also propose two novel IS solutions that are noise-oriented and redundancy-aware, specifically designed for large datasets and transformer architectures. Our final solution achieved an average reduction of 41\% in training sets, while maintaining the same levels of effectiveness in all datasets. Importantly, our solutions demonstrated speedup improvements of 1.67x (up to 2.46x), making them scalable for datasets with hundreds of thousands of documents.

In the realm of Text-attributed Graphs (TAGs), traditional graph neural networks (GNNs) often fall short due to the complex textual information associated with each node. Recent methods have improved node representations by leveraging large language models (LLMs) to enhance node text features, but these approaches typically require extensive annotations or fine-tuning across all nodes, which is both time-consuming and costly. To overcome these challenges, we introduce GAGA, an efficient framework for TAG representation learning. GAGA reduces annotation time and cost by focusing on annotating only representative nodes and edges. It constructs an annotation graph that captures the topological relationships among these annotations. Furthermore, GAGA employs a two-level alignment module to effectively integrate the annotation graph with the TAG, aligning their underlying structures. Experiments show that GAGA achieves classification accuracies on par with or surpassing state-of-the-art methods while requiring only 1% of the data to be annotated, demonstrating its high efficiency.

Controlling the syntactic structure of text generated by language models is valuable for applications requiring clarity, stylistic consistency, or interpretability, yet it remains a challenging task. In this paper, we argue that sampling algorithms based on the posterior inference can effectively enforce a target constituency structure during generation. Our approach combines sequential Monte Carlo, which estimates the posterior distribution by sampling from a proposal distribution, with a syntactic tagger that ensures that each generated token aligns with the desired syntactic structure. Our experiments with GPT2 and Llama3-8B models show that with an appropriate proposal distribution, we can improve syntactic accuracy, increasing the F1 score from $12.31$ (GPT2-large) and $35.33$ (Llama3-8B) to about $93$ in both cases without compromising the language model's fluency. These results underscore both the complexity of syntactic control and the effectiveness of sampling algorithms, offering a promising approach for applications where precise control over syntax is essential.

Large language model (LLM) is an effective approach to addressing data scarcity in low-resource scenarios. Recent existing research designs hand-crafted prompts to guide LLM for data augmentation. We introduce a data augmentation strategy for the aspect category sentiment analysis (ACSA) task that preserves the original sentence semantics and has linguistic diversity, specifically by providing a structured prompt template for an LLM to generate predefined content. In addition, we employ a post-processing technique to further ensure semantic consistency between the generated sentence and the original sentence. The augmented data increases the semantic coverage of the training distribution, enabling the model better to understand the relationship between aspect categories and sentiment polarities, enhancing its inference capabilities. Furthermore, we propose a confidence-weighted fine-tuning strategy to encourage the model to generate more confident and accurate sentiment polarity predictions. Compared with powerful and recent works, our method consistently achieves the best performance on four benchmark datasets over all baselines.

This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT) prompting, a technique that encourages a large language model (LLM) to "think step by step" (Wei et al., 2022). CoT is a widely adopted method for improving reasoning tasks, however, our findings reveal a more nuanced picture of its effectiveness. We demonstrate two things: - The effectiveness of Chain-of-Thought prompting can vary greatly depending on the type of task and model. For non-reasoning models, CoT generally improves average performance by a small amount, particularly if the model does not inherently engage in step-by-step processing by default. However, CoT can introduce more variability in answers, sometimes triggering occasional errors in questions the model would otherwise get right. We also found that many recent models perform some form of CoT reasoning even if not asked; for these models, a request to perform CoT had little impact. Performing CoT generally requires far more tokens (increasing cost and time) than direct answers. - For models designed with explicit reasoning capabilities, CoT prompting often results in only marginal, if any, gains in answer accuracy. However, it significantly increases the time and tokens needed to generate a response.

Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long vision token sequences. In this paper, we explore the spatial redundancy among vision tokens and shorten the length of vision token sequences for inference acceleration. Specifically, we propose a Spatial Token Fusion (STF) method to learn compact vision tokens for short vision token sequence, where spatial-adjacent tokens are fused into one. Meanwhile, weight-frozen vision encoder can not well adapt to the demand of extensive downstream vision-language tasks. To this end, we further introduce a Multi-Block Token Fusion (MBTF) module to supplement multi-granularity features for the reduced token sequence. Overall, we combine STF and MBTF module to balance token reduction and information preservation, thereby improving inference efficiency without sacrificing multimodal reasoning capabilities. Experimental results demonstrate that our method based on LLaVA-1.5 achieves comparable or even superior performance to the baseline on 8 popular vision-language benchmarks with only $25\%$ vision tokens of baseline. The source code and trained weights are available at https://github.com/visresearch/LLaVA-STF.

As quantum computing advances, quantum programming libraries' heterogeneity and steady evolution create new challenges for software developers. Frequent updates in software libraries break working code that needs to be refactored, thus adding complexity to an already complex landscape. These refactoring challenges are, in many cases, fundamentally different from those known in classical software engineering due to the nature of quantum computing software. This study addresses these challenges by developing a taxonomy of quantum circuit's refactoring problems, providing a structured framework to analyze and compare different refactoring approaches. Large Language Models (LLMs) have proven valuable tools for classic software development, yet their value in quantum software engineering remains unexplored. This study uses LLMs to categorize refactoring needs in migration scenarios between different Qiskit versions. Qiskit documentation and release notes were scrutinized to create an initial taxonomy of refactoring required for migrating between Qiskit releases. Two taxonomies were produced: one by expert developers and one by an LLM. These taxonomies were compared, analyzing differences and similarities, and were integrated into a unified taxonomy that reflects the findings of both methods. By systematically categorizing refactoring challenges in Qiskit, the unified taxonomy is a foundation for future research on AI-assisted migration while enabling a more rigorous evaluation of automated refactoring techniques. Additionally, this work contributes to quantum software engineering (QSE) by enhancing software development workflows, improving language compatibility, and promoting best practices in quantum programming.