Continued pretraining (CPT) is a popular approach to adapt existing large language models (LLMs) to new languages. When doing so, it is common practice to include a portion of English data in the mixture, but its role has not been carefully studied to date. In this work, we show that including English does not impact validation perplexity, yet it is critical for the emergence of downstream capabilities in the target language. We introduce a language-agnostic benchmark for in-context learning (ICL), which reveals catastrophic forgetting early on CPT when English is not included. This in turn damages the ability of the model to generalize to downstream prompts in the target language as measured by perplexity, even if it does not manifest in terms of accuracy until later in training, and can be tied to a big shift in the model parameters. Based on these insights, we introduce curriculum learning and exponential moving average (EMA) of weights as effective alternatives to mitigate the need for English. All in all, our work sheds light into the dynamics by which emergent abilities arise when doing CPT for language adaptation, and can serve as a foundation to design more effective methods in the future.

Miscalibration in Large Language Models (LLMs) undermines their reliability, highlighting the need for accurate confidence estimation. We introduce CCPS (Calibrating LLM Confidence by Probing Perturbed Representation Stability), a novel method analyzing internal representational stability in LLMs. CCPS applies targeted adversarial perturbations to final hidden states, extracts features reflecting the model's response to these perturbations, and uses a lightweight classifier to predict answer correctness. CCPS was evaluated on LLMs from 8B to 32B parameters (covering Llama, Qwen, and Mistral architectures) using MMLU and MMLU-Pro benchmarks in both multiple-choice and open-ended formats. Our results show that CCPS significantly outperforms current approaches. Across four LLMs and three MMLU variants, CCPS reduces Expected Calibration Error by approximately 55% and Brier score by 21%, while increasing accuracy by 5 percentage points, Area Under the Precision-Recall Curve by 4 percentage points, and Area Under the Receiver Operating Characteristic Curve by 6 percentage points, all relative to the strongest prior method. CCPS delivers an efficient, broadly applicable, and more accurate solution for estimating LLM confidence, thereby improving their trustworthiness.

Large language models (LLMs) exhibit remarkable multilingual capabilities despite English-dominated pre-training, attributed to cross-lingual mechanisms during pre-training. Existing methods for enhancing cross-lingual transfer remain constrained by parallel resources, suffering from limited linguistic and domain coverage. We propose Cross-lingual In-context Pre-training (CrossIC-PT), a simple and scalable approach that enhances cross-lingual transfer by leveraging semantically related bilingual texts via simple next-word prediction. We construct CrossIC-PT samples by interleaving semantic-related bilingual Wikipedia documents into a single context window. To access window size constraints, we implement a systematic segmentation policy to split long bilingual document pairs into chunks while adjusting the sliding window mechanism to preserve contextual coherence. We further extend data availability through a semantic retrieval framework to construct CrossIC-PT samples from web-crawled corpus. Experimental results demonstrate that CrossIC-PT improves multilingual performance on three models (Llama-3.1-8B, Qwen2.5-7B, and Qwen2.5-1.5B) across six target languages, yielding performance gains of 3.79%, 3.99%, and 1.95%, respectively, with additional improvements after data augmentation.

--The flipped classroom is a new pedagogical strategy that has been gaining increasing importance recently. Spoken discussion dialog commonly occurs in flipped classroom, which embeds rich information indicating processes and progression of students' learning. This study focuses on learning analytics from spoken discussion dialog in the flipped classroom, which aims to collect and analyze the discussion dialogs in flipped classroom in order to get to know group learning processes and outcomes. We have recently transformed a course using the flipped classroom strategy, where students watched video-recorded lectures at home prior to group-based problem-solving discussions in class. The in-class group discussions were recorded throughout the semester and then transcribed manually. After features are extracted from the dialogs by multiple tools and customized processing techniques, we performed statistical analyses to explore the indicators that are related to the group learning outcomes from face-to-face discussion dialogs in the flipped classroom. Then, machine learning algorithms are applied to the indicators in order to predict the group learning outcome as High, Mid or Low. The best prediction accuracy reaches 78.9%, which demonstrates the feasibility of achieving automatic learning outcome prediction from group discussion dialog in flipped classroom. EARNING analytics is concerned with collection and analyses of data related to learning in order to inform and improve the learning process or their outcomes [1]. Applying properly learning analytics can not only track student progress but also improve student performance [2]. Recent advancements in the development of data science and machine learning techniques has led to a rise in popularity of learning analytics within the educational research field. The flipped classroom is a new pedagogical method, which utilizes asynchronous video lectures and basic practice as homework, and conducts group-based problem solving discussions or activities in the classroom [3]. Since flipped classroom promotes cooperative learning [4, 5] and increases student engagement and motivation [6, 7], it is gaining increasing importance for teaching and learning in recent years. A common in-class activity for the flipped classroom is student group discussions, where participants are involved in solving problems together. Such discussion dialogs embed rich information that cannot be captured objectively by conventional data, such as students' in-class sentiments, degree of concentration, amount of information exchange... etc. Authors are with The Chinese University of Hong Kong, Shatin, N.T., Hong Kong Therefore, spoken discussion dialogs in flipped classroom deserve greater attention for learning analytics, which aims to collect and analyze the discussion dialogs in flipped classroom in order to explore indicators that reflect group learning outcomes.

As large language models (LLMs) are increasingly deployed in diverse cultural environments, evaluating their cultural understanding capability has become essential for ensuring trustworthy and culturally aligned applications. However, most existing benchmarks lack comprehensiveness and are challenging to scale and adapt across different cultural contexts, because their frameworks often lack guidance from well-established cultural theories and tend to rely on expert-driven manual annotations. To address these issues, we propose CultureScope, the most comprehensive evaluation framework to date for assessing cultural understanding in LLMs. Inspired by the cultural iceberg theory, we design a novel dimensional schema for cultural knowledge classification, comprising 3 layers and 140 dimensions, which guides the automated construction of culture-specific knowledge bases and corresponding evaluation datasets for any given languages and cultures. Experimental results demonstrate that our method can effectively evaluate cultural understanding. They also reveal that existing large language models lack comprehensive cultural competence, and merely incorporating multilingual data does not necessarily enhance cultural understanding.

A key requirement for generalist robots is compositional generalization - the ability to combine atomic skills to solve complex, long-horizon tasks. While prior work has primarily focused on synthesizing a planner that sequences pre-learned skills, robust execution of the individual skills themselves remains challenging, as visuomotor policies often fail under distribution shifts induced by scene composition. To address this, we introduce a scene graph-based representation that focuses on task-relevant objects and relations, thereby mitigating sensitivity to irrelevant variation. Building on this idea, we develop a scene-graph skill learning framework that integrates graph neural networks with diffusion-based imitation learning, and further combine "focused" scene-graph skills with a vision-language model (VLM) based task planner. Experiments in both simulation and real-world manipulation tasks demonstrate substantially higher success rates than state-of-the-art baselines, highlighting improved robustness and compositional generalization in long-horizon tasks.

Recently, data-driven trajectory prediction methods have achieved remarkable results, significantly advancing the development of autonomous driving. However, the instability of single-vehicle perception introduces certain limitations to trajectory prediction. In this paper, a novel lightweight framework for cooperative trajectory prediction, CoPAD, is proposed. This framework incorporates a fusion module based on the Hungarian algorithm and Kalman filtering, along with the Past Time Attention (PTA) module, mode attention module and anchor-oriented decoder (AoD). It effectively performs early fusion on multi-source trajectory data from vehicles and road infrastructure, enabling the trajectories with high completeness and accuracy. The PTA module can efficiently capture potential interaction information among historical trajectories, and the mode attention module is proposed to enrich the diversity of predictions. Additionally, the decoder based on sparse anchors is designed to generate the final complete trajectories. Extensive experiments show that CoPAD achieves the state-of-the-art performance on the DAIR-V2X-Seq dataset, validating the effectiveness of the model in cooperative trajectory prediction in V2X scenarios.

Bias-only fine-tuning has the potential for unprecedented parameter efficiency. However, the link between fine-tuning different bias terms (i.e., bias terms in the query, key, or value projections) and downstream performance remains unclear. The existing approaches, e.g., based on the magnitude of bias change or empirical Fisher information, provide limited guidance for selecting the particular bias term for effective fine-tuning. In this paper, we propose an approach for selecting the bias term to be fine-tuned, forming the foundation of our bias-efficient fine-tuning (BEFT). We extensively evaluate our bias-efficient approach against other bias-selection approaches, across a wide range of large language models (LLMs) spanning encoder-only and decoder-only architectures from 110M to 6.7B parameters. Our results demonstrate the effectiveness and superiority of our bias-efficient approach on diverse downstream tasks, including classification, multiple-choice, and generation tasks.

Automated Essay Scoring (AES) systems now reach near human agreement on some public benchmarks, yet real-world adoption, especially in high-stakes examinations, remains limited. A principal obstacle is that most models output a single score without any accompanying measure of confidence or explanation. We address this gap with conformal prediction, a distribution-free wrapper that equips any classifier with set-valued outputs and formal coverage guarantees. Two open-source large language models (Llama-3 8B and Qwen-2.5 3B) are fine-tuned on three diverse corpora (ASAP, TOEFL11, Cambridge-FCE) and calibrated at a 90 percent risk level. Reliability is assessed with UAcc, an uncertainty-aware accuracy that rewards models for being both correct and concise. To our knowledge, this is the first work to combine conformal prediction and UAcc for essay scoring. The calibrated models consistently meet the coverage target while keeping prediction sets compact, indicating that open-source, mid-sized LLMs can already support teacher-in-the-loop AES; we discuss scaling and broader user studies as future work.

While multimodal LLMs (MLLMs) demonstrate remarkable reasoning progress, their application in specialized scientific domains like physics reveals significant gaps in current evaluation benchmarks. Specifically, existing benchmarks often lack fine-grained subject coverage, neglect the step-by-step reasoning process, and are predominantly English-centric, failing to systematically evaluate the role of visual information. Therefore, we introduce \textbf {Multi-Physics} for Chinese physics reasoning, a comprehensive benchmark that includes 5 difficulty levels, featuring 1,412 image-associated, multiple-choice questions spanning 11 high-school physics subjects. We employ a dual evaluation framework to evaluate 20 different MLLMs, analyzing both final answer accuracy and the step-by-step integrity of their chain-of-thought. Furthermore, we systematically study the impact of difficulty level and visual information by comparing the model performance before and after changing the input mode. Our work provides not only a fine-grained resource for the community but also offers a robust methodology for dissecting the multimodal reasoning process of state-of-the-art MLLMs, and our dataset and code have been open-sourced: https://github.com/luozhongze/Multi-Physics.