As large language models continue to advance, their application in educational contexts remains underexplored and under-optimized. In this paper, we address this gap by introducing the first diverse benchmark tailored for educational scenarios, incorporating synthetic data containing 9 major scenarios and over 4,000 distinct educational contexts. To enable comprehensive assessment, we propose a set of multi-dimensional evaluation metrics that cover 12 critical aspects relevant to both teachers and students. We further apply human annotation to ensure the effectiveness of the model-generated evaluation responses. Additionally, we succeed to train a relatively small-scale model on our constructed dataset and demonstrate that it can achieve performance comparable to state-of-the-art large models (e.g., Deepseek V3, Qwen Max) on the test set. Overall, this work provides a practical foundation for the development and evaluation of education-oriented language models.

While Large Reasoning Models (LRMs) have demonstrated remarkable capabilities through explicit Chain-of-Thought (CoT) generation, they frequently suffer from “overthinking”. In this work, we bridge this gap by introducing Token-level Marginal Utility, which quantifies the per-token log-probability gain of the ground-truth answer. Leveraging this dense supervision signal, we propose MUTO (Marginal Utility Guided Thinking Optimization), a unified training framework designed to synthesize concise reasoning chains. Rather than relying only on coarse trajectory-level length control, MUTO identifies tokens that reduce the model’s likelihood of the correct answer and penalizes such negative-utility reasoning, yielding concise yet effective CoT trajectories. Experiments on DeepSeek-R1-Distill-Qwen backbones (1.5B and 7B) across six math reasoning benchmarks show that MUTO yields a markedly better efficiency-accuracy Pareto frontier. It reduces average token usage by 87.1% at 1.5B while improving accuracy by 2.3%, and cuts tokens by 80.2% at 7B with only -0.1% accuracy change, achieving the best length-normalized accuracy among baselines.

Although substantial efforts have been made to mitigate catastrophic forgetting in continual learning, the intrinsic mechanisms are not well understood. In this work, we demonstrate the existence of “pseudo forgetting”: the performance degradation in previous tasks is not attributed to a loss of capabilities, but rather to the failure of the instructions to activate the appropriate model capabilities. We show that the model’s performance on previous tasks can be restored through two simple interventions: (1) providing partial external correct rationale, and (2) appending semantically meaningless suffixes to the original instructions, to guide the generation of correct rationales. Through empirical analysis of the internal mechanisms governing rationale generation, we reveal that models exhibiting pseudo forgetting show reduced instruction dependence during rationale generation, leading to suboptimal activation of their inherent capabilities. Based on this insight, we propose Rationale-Guidance Difficulty based Replay (RGD-R) framework that dynamically allocates replay data based on the model’s ability to correctly leverage the intrinsic capabilities. Experimental results demonstrate that RGD-R effectively mitigates pseudo forgetting while maintaining model plasticity.

Recent studies have demonstrated that In-Context Learning (ICL), through the use of specific demonstrations, can align Large Language Models (LLMs) with human preferences known as In-Context Alignment (ICA), indicating that models can comprehend human instructions without requiring parameter adjustments. However, the exploration of the mechanism and applicability of ICA remains limited. In this paper, we begin by dividing the context text used in ICA into three categories: format, system prompt, and example. Through ablation experiments, we investigate the effectiveness of each part in enabling ICA to function effectively. We then examine how variants in these parts impact the model’s alignment performance. Our findings indicate that the example part is crucial for enhancing the model’s alignment capabilities, with changes in examples significantly affecting alignment performance. We also conduct a comprehensive evaluation of ICA’s zero-shot capabilities in various alignment tasks. The results indicate that compared to parameter fine-tuning methods, ICA demonstrates superior performance in knowledge-based tasks and tool-use tasks. However, it still exhibits certain limitations in areas such as multi-turn dialogues and instruction following. Source codes and scripts are available at https://github.com/li-aolong/how-far-can-ica-go.

Language style is necessary for AI systems to accurately understand and generate diverse human language. However, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application needs. To overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking style. Grounded in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of LLMs. For such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized texts. Comprehensive experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information. We will release our data, code, and model upon acceptance.

Large Language Models (LLMs) demonstrate significant value in domain-specific applications, benefiting from their fundamental capabilities. Nevertheless, it is still unclear which fundamental capabilities contribute to success in specific domains. Moreover, the existing benchmark-based evaluation cannot effectively reflect the performance of real-world applications. In this survey, we review recent advances of LLMs in domain applications, aiming to summarize the fundamental capabilities and their collaboration. Furthermore, we establish connections between fundamental capabilities and specific domains, evaluating the varying importance of different capabilities. Based on our findings, we propose a reliable strategy for domains to choose more robust backbone LLMs for real-world applications.