The development of explanations for scientific phenomena is essential in science assessment, but scoring student-written explanations remains challenging and resource-intensive. Large language models (LLMs) have shown promise in addressing this issue, particularly in alphabetic languages like English. However, their applicability to logographic languages is less explored. This study investigates the potential of fine-tuning ChatGPT, a leading LLM, to automatically score scientific explanations written in Chinese. Student responses to seven scientific explanation tasks were collected and automatically scored, with scoring accuracy examined in relation to reasoning complexity using the Kendall correlation. A qualitative analysis explored how linguistic features influenced scoring accuracy. The results show that domain-specific adaptation enables ChatGPT to score Chinese scientific explanations with accuracy. However, scoring accuracy correlates with reasoning complexity: a negative correlation for lower-level responses and a positive one for higher-level responses. The model overrates complex reasoning in low-level responses with intricate sentence structures and underrates high-level responses using concise causal reasoning. These correlations stem from linguistic features--simplicity and clarity enhance accuracy for lower-level responses, while comprehensiveness improves accuracy for higher-level ones. Simpler, shorter responses tend to score more accurately at lower levels, whereas longer, information-rich responses yield better accuracy at higher levels. These findings demonstrate the effectiveness of LLMs in automatic scoring within a Chinese context and emphasize the importance of linguistic features and reasoning complexity in fine-tuning scoring models for educational assessments.

Much has been discussed about how Large Language Models, Knowledge Graphs and Search Engines can be combined in a synergistic manner. A dimension largely absent from current academic discourse is the user perspective. In particular, there remain many open questions regarding how best to address the diverse information needs of users, incorporating varying facets and levels of difficulty. This paper introduces a taxonomy of user information needs, which guides us to study the pros, cons and possible synergies of Large Language Models, Knowledge Graphs and Search Engines. From this study, we derive a roadmap for future research.

Large Language Models (LLMs) have advanced the capability of game agents in social deduction games (SDGs). These games rely heavily on conversation-driven interactions and require agents to infer, make decisions, and express based on such information. While this progress leads to more sophisticated and strategic non-player characters (NPCs) in SDGs, there exists a need to control the proficiency of these agents. This control not only ensures that NPCs can adapt to varying difficulty levels during gameplay, but also provides insights into the safety and fairness of LLM agents. In this paper, we present DVM, a novel framework for developing controllable LLM agents for SDGs, and demonstrate its implementation on one of the most popular SDGs, Werewolf. DVM comprises three main components: Predictor, Decider, and Discussor. By integrating reinforcement learning with a win rate-constrained decision chain reward mechanism, we enable agents to dynamically adjust their gameplay proficiency to achieve specified win rates. Experiments show that DVM not only outperforms existing methods in the Werewolf game, but also successfully modulates its performance levels to meet predefined win rate targets. These results pave the way for LLM agents' adaptive and balanced gameplay in SDGs, opening new avenues for research in controllable game agents.

Prompt engineering can significantly improve the performance of large language models (LLMs), with automated prompt optimization (APO) gaining significant attention due to the time-consuming and laborious nature of manual prompt design. However, much of the existing work in APO overlooks task-specific characteristics, resulting in prompts that lack domain specificity and are not well-suited for task-specific optimization. In this paper, we introduce TAPO, a multitask-aware prompt optimization framework composed of three key modules. First, a task-aware metric selection module is proposed to enhance task-specific prompt generation capabilities. Second, we present a multi-metrics evaluation module to jointly evaluate prompts from multiple perspectives. Third, an evolution-based optimization framework is introduced for automatic prompt refinement, which improves adaptability across various tasks. Extensive experiments on six datasets demonstrate the effectiveness of our approach, and our code is publicly available.

This paper explores the synergy between human cognition and Large Language Models (LLMs), highlighting how generative AI can drive personalized learning at scale. We discuss parallels between LLMs and human cognition, emphasizing both the promise and new perspectives on integrating AI systems into education. After examining challenges in aligning technology with pedagogy, we review AutoTutor-one of the earliest Intelligent Tutoring Systems (ITS)-and detail its successes, limitations, and unfulfilled aspirations. We then introduce the Socratic Playground, a next-generation ITS that uses advanced transformer-based models to overcome AutoTutor's constraints and provide personalized, adaptive tutoring. To illustrate its evolving capabilities, we present a JSON-based tutoring prompt that systematically guides learner reflection while tracking misconceptions. Throughout, we underscore the importance of placing pedagogy at the forefront, ensuring that technology's power is harnessed to enhance teaching and learning rather than overshadow it.

Autonomous driving (AD) has experienced significant improvements in recent years and achieved promising 3D detection, classification, and localization results. However, many challenges remain, e.g. semantic understanding of pedestrians' behaviors, and downstream handling for pedestrian interactions. Recent studies in applications of Large Language Models (LLM) and Vision-Language Models (VLM) have achieved promising results in scene understanding and high-level maneuver planning in diverse traffic scenarios. However, deploying the billion-parameter LLMs to vehicles requires significant computation and memory resources. In this paper, we analyzed effective knowledge distillation of semantic labels to smaller Vision networks, which can be used for the semantic representation of complex scenes for downstream decision-making for planning and control.

Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models (LLMs) with human preferences. These algorithms implicitly treat the LLM as a reward model, and focus on training it to correct misranked preference pairs. However, recent work~\citep{chen2024preference} empirically finds that DPO training \textit{rarely improves these misranked preference pairs}, despite its gradient emphasizing on these cases. We introduce FocalPO, a DPO variant that instead \textit{down-weighs} misranked preference pairs and prioritizes enhancing the model's understanding of pairs that it can already rank correctly. Inspired by Focal Loss used in vision tasks, FocalPO achieves this by adding a modulating factor to dynamically scale DPO loss. Our experiment demonstrates that FocalPO surpasses DPO and its variants on popular benchmarks like Alpaca Eval 2.0 using Mistral-Base-7B and Llama-3-Instruct-8B. Additionally, we empirically reveals how FocalPO affects training on correct and incorrect sample groups, further underscoring its effectiveness.

Semantic leakage is a phenomenon recently introduced by Gonen et al. (2024). It refers to a situation in which associations learnt from the training data emerge in language model generations in an unexpected and sometimes undesired way. Prior work has focused on leakage in large language models (7B+ parameters). In this study, I use Qwen2.5 model family to explore whether smaller models, ranging from 500M to 7B parameters, demonstrate less semantic leakage due to their limited capacity for capturing complex associations. Building on the previous dataset from Gonen et al. (2024), I introduce a new dataset of color-focused prompts, categorized into specific types of semantic associations, to systematically evaluate the models' performance. Results indicate that smaller models exhibit less semantic leakage overall, although this trend is not strictly linear, with medium-sized models sometimes surpassing larger ones in leaking behavior. The dataset, the model generations, and the evaluation code are publicly available at https://github.com/smilni/semantic_leakage_project.

This paper introduces a neuro-symbolic approach for relational exploration in cultural heritage knowledge graphs, leveraging Large Language Models (LLMs) for explanation generation and a novel mathematical framework to quantify the interestingness of relationships. We demonstrate the importance of interestingness measure using a quantitative analysis, by highlighting its impact on the overall performance of our proposed system, particularly in terms of precision, recall, and F1-score. Using the Wikidata Cultural Heritage Linked Open Data (WCH-LOD) dataset, our approach yields a precision of 0.70, recall of 0.68, and an F1-score of 0.69, representing an improvement compared to graph-based (precision: 0.28, recall: 0.25, F1-score: 0.26) and knowledge-based baselines (precision: 0.45, recall: 0.42, F1-score: 0.43). Furthermore, our LLM-powered explanations exhibit better quality, reflected in BLEU (0.52), ROUGE-L (0.58), and METEOR (0.63) scores, all higher than the baseline approaches. We show a strong correlation (0.65) between interestingness measure and the quality of generated explanations, validating its effectiveness. The findings highlight the importance of LLMs and a mathematical formalization for interestingness in enhancing the effectiveness of relational exploration in cultural heritage knowledge graphs, with results that are measurable and testable. We further show that the system enables more effective exploration compared to purely knowledge-based and graph-based methods. Keywords Knowledge Graphs, Large Language Models (LLMs), Explainable AI (XAI), Cultural Heritage, Neuro-Symbolic AI, Interestingness Score, Contextual Relevance, Relational Search 1. Introduction The digitization of cultural heritage artifacts and historical records has generated a vast amount of knowledge encoded in the form of interconnected knowledge graphs (KGs) [1, 2]. Unlocking meaningful insights from these KGs requires more than simple keyword searches [3].

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning abilities. This paper introduces a novel agentic framework for ``guided code generation'' that tries to address these limitations through a deliberately structured, fine-grained approach to code generation tasks. Our framework leverages LLMs' strengths as fuzzy searchers and approximate information retrievers while mitigating their weaknesses in long sequential reasoning and long-context understanding. Empirical evaluation using OpenAI's HumanEval benchmark with Meta's Llama 3.1 8B model (int4 precision) demonstrates a 23.79\% improvement in solution accuracy compared to direct one-shot generation. Our results indicate that structured, guided approaches to code generation can significantly enhance the practical utility of LLMs in software development while overcoming their inherent limitations in compositional reasoning and context handling.