Providing effective feedback is important for student learning in programming problem-solving. In this sense, Large Language Models (LLMs) have emerged as potential tools to automate feedback generation. However, their reliability and ability to identify reasoning errors in student code remain not well understood. This study evaluates the performance of four LLMs (GPT-4o, GPT-4o mini, GPT-4-Turbo, and Gemini-1.5-pro) on a benchmark dataset of 45 student solutions. We assessed the models' capacity to provide accurate and insightful feedback, particularly in identifying reasoning mistakes. Our analysis reveals that 63\% of feedback hints were accurate and complete, while 37\% contained mistakes, including incorrect line identification, flawed explanations, or hallucinated issues. These findings highlight the potential and limitations of LLMs in programming education and underscore the need for improvements to enhance reliability and minimize risks in educational applications.

Translating software written in legacy languages to modern languages, such as C to Rust, has significant benefits in improving memory safety while maintaining high performance. However, manual translation is cumbersome, error-prone, and produces unidiomatic code. Large language models (LLMs) have demonstrated promise in producing idiomatic translations, but offer no correctness guarantees as they lack the ability to capture all the semantics differences between the source and target languages. To resolve this issue, we propose SACTOR, an LLM-driven C-to-Rust zero-shot translation tool using a two-step translation methodology: an "unidiomatic" step to translate C into Rust while preserving semantics, and an "idiomatic" step to refine the code to follow Rust's semantic standards. SACTOR utilizes information provided by static analysis of the source C program to address challenges such as pointer semantics and dependency resolution. To validate the correctness of the translated result from each step, we use end-to-end testing via the foreign function interface to embed our translated code segment into the original code. We evaluate the translation of 200 programs from two datasets and two case studies, comparing the performance of GPT-4o, Claude 3.5 Sonnet, Gemini 2.0 Flash, Llama 3.3 70B and DeepSeek-R1 in SACTOR. Our results demonstrate that SACTOR achieves high correctness and improved idiomaticity, with the best-performing model (DeepSeek-R1) reaching 93% and (GPT-4o, Claude 3.5, DeepSeek-R1) reaching 84% correctness (on each dataset, respectively), while producing more natural and Rust-compliant translations compared to existing methods.

Large Language Models (LLMs) have achieved widespread adoption, yet our understanding of their behavior remains limited, particularly in detecting data contamination and hallucinations. While recently proposed probing techniques provide insights through activation analysis, they require "white-box" access to model internals, often unavailable. Current "gray-box" approaches typically analyze only the probability of the actual tokens in the sequence with simple task-specific heuristics. Importantly, these methods overlook the rich information contained in the full token distribution at each processing step. To address these limitations, we propose that gray-box analysis should leverage the complete observable output of LLMs, consisting of both the previously used token probabilities as well as the complete token distribution sequences - a unified data type we term LOS (LLM Output Signature). To this end, we develop a transformer-based approach to process LOS that theoretically guarantees approximation of existing techniques while enabling more nuanced analysis. Our approach achieves superior performance on hallucination and data contamination detection in gray-box settings, significantly outperforming existing baselines. Furthermore, it demonstrates strong transfer capabilities across datasets and LLMs, suggesting that LOS captures fundamental patterns in LLM behavior.

Batch prompting, which combines a batch of multiple queries sharing the same context in one inference, has emerged as a promising solution to reduce inference costs. However, our study reveals a significant security vulnerability in batch prompting: malicious users can inject attack instructions into a batch, leading to unwanted interference across all queries, which can result in the inclusion of harmful content, such as phishing links, or the disruption of logical reasoning. In this paper, we construct BATCHSAFEBENCH, a comprehensive benchmark comprising 150 attack instructions of two types and 8k batch instances, to study the batch prompting vulnerability systematically. Our evaluation of both closed-source and open-weight LLMs demonstrates that all LLMs are susceptible to batch-prompting attacks. We then explore multiple defending approaches. While the prompting-based defense shows limited effectiveness for smaller LLMs, the probing-based approach achieves about 95% accuracy in detecting attacks. Additionally, we perform a mechanistic analysis to understand the attack and identify attention heads that are responsible for it.

Real dialogues with AI assistants for solving data-centric tasks often follow dynamic, unpredictable paths due to imperfect information provided by the user or in the data, which must be caught and handled. Developing datasets which capture such user-AI interactions is difficult and time-consuming. In this work, we develop a novel framework for synthetically generating controlled, multi-turn conversations between a user and AI assistant for the task of table-based question answering, which can be generated from an existing dataset with fully specified table QA examples for any target domain. Each conversation aims to solve a tablebased reasoning question through collaborative effort, modeling one of two real-world scenarios: (1) an AI-initiated clarification, or (2) a user-initiated correction. Critically, we employ a strong teacher LLM to verify the correctness of our synthetic conversations, ensuring high quality. We demonstrate synthetic datasets generated from TAT-QA and WikiTableQuestions as benchmarks of frontier LLMs. We find that even larger models struggle to effectively issuing clarification questions and accurately integrate Figure 1: Illustration of synthetic corrections and clarifications user feedback for corrections.

Predicting human decision-making under risk and uncertainty is a long-standing challenge in cognitive science, economics, and AI. While prior research has focused on numerically described lotteries, real-world decisions often rely on textual descriptions. This study conducts the first large-scale exploration of human decision-making in such tasks using a large dataset of one-shot binary choices between textually described lotteries. We evaluate multiple computational approaches, including fine-tuning Large Language Models (LLMs), leveraging embeddings, and integrating behavioral theories of choice under risk. Our results show that fine-tuned LLMs, specifically RoBERTa and GPT-4o outperform hybrid models that incorporate behavioral theory, challenging established methods in numerical settings. These findings highlight fundamental differences in how textual and numerical information influence decision-making and underscore the need for new modeling strategies to bridge this gap.

Leading large language models have demonstrated impressive capabilities in reasoning-intensive tasks, such as standardized educational testing. However, they often require extensive training in low-resource settings with inaccessible infrastructure. Small or compact models, though more efficient, frequently lack sufficient support for underrepresented languages, leaving a performance gap in critical domains. This work explores the potential of parameter-efficient fine-tuning of compact open-weight language models to handle reasoning-intensive tasks in the underrepresented Ukrainian language, building on the findings of the ZNO-Eval benchmark. Parameter-efficient fine-tuning of LLaMA 3.1 (8 billion parameters), LLaMA 3.2 (3 billion parameters), and Gemma 2 (9 billion parameters) models on chain-of-thought solutions resulted in a modest test score improvement of up to 17.4% on complex matching tasks and 1.6% overall compared to tuning on answer letters alone, offering enhanced interpretability and robustness. In addition, the proposed tuning method with joint task topic and step-by-step solution generation outperforms standard chain-of-thought tuning in matching tasks and provides a 5.4% gain over the best LLaMA 3.2 model due to guiding the model to recall and apply domain-relevant information. Contrasting obtained results with zero-shot evaluations of leading open-weight and proprietary models such as Qwen, DeepSeek R1, OpenAI o1 and o3, Gemini, and Claude, highlight that fine-tuning LLaMA and Gemma models with 2,032 step-by-step solutions and 20 to 50 million trainable parameters on a single A100 GPU lets them outperform GPT-4o mini, Mistral Large, and larger open-weight models. This research also evaluates how merging the quantized adapter with the base model influences the generation quality. Source code and tuned models are available at https://github.com/NLPForUA/ZNO.

Building high-quality large language models (LLMs) for enterprise Arabic applications remains challenging due to the limited availability of digitized Arabic data. In this work, we present a data synthesis and refinement strategy to help address this problem, namely, by leveraging synthetic data generation and human-in-the-loop annotation to expand our Arabic training corpus. We further present our iterative post training recipe that is essential to achieving state-of-the-art performance in aligning the model with human preferences, a critical aspect to enterprise use cases. The culmination of this effort is the release of a small, 7B, open-weight model that outperforms similarly sized peers in head-to-head comparisons and on Arabic-focused benchmarks covering cultural knowledge, instruction following, RAG, and contextual faithfulness.

The purpose of this paper is to examine whether large language models (LLMs) can understand what is good and evil with respect to judging good/evil reputation of celebrities. Specifically, we first apply a large language model (namely, ChatGPT) to the task of collecting sentences that mention the target celebrity from articles about celebrities on Web pages. Next, the collected sentences are categorized based on their contents by ChatGPT, where ChatGPT assigns a category name to each of those categories. Those assigned category names are referred to as "aspects" of each celebrity. Then, by applying the framework of retrieval augmented generation (RAG), we show that the large language model is quite effective in the task of judging good/evil reputation of aspects and descriptions of each celebrity. Finally, also in terms of proving the advantages of the proposed method over existing services incorporating RAG functions, we show that the proposed method of judging good/evil of aspects/descriptions of each celebrity significantly outperform an existing service incorporating RAG functions.

Temporal graph neural networks (TGNNs) have shown remarkable performance in temporal graph modeling. However, real-world temporal graphs often possess rich textual information, giving rise to temporal text-attributed graphs (TTAGs). Such combination of dynamic text semantics and evolving graph structures introduces heightened complexity. Existing TGNNs embed texts statically and rely heavily on encoding mechanisms that biasedly prioritize structural information, overlooking the temporal evolution of text semantics and the essential interplay between semantics and structures for synergistic reinforcement. To tackle these issues, we present \textbf{{Cross}}, a novel framework that seamlessly extends existing TGNNs for TTAG modeling. The key idea is to employ the advanced large language models (LLMs) to extract the dynamic semantics in text space and then generate expressive representations unifying both semantics and structures. Specifically, we propose a Temporal Semantics Extractor in the {Cross} framework, which empowers the LLM to offer the temporal semantic understanding of node's evolving contexts of textual neighborhoods, facilitating semantic dynamics. Subsequently, we introduce the Semantic-structural Co-encoder, which collaborates with the above Extractor for synthesizing illuminating representations by jointly considering both semantic and structural information while encouraging their mutual reinforcement. Extensive experimental results on four public datasets and one practical industrial dataset demonstrate {Cross}'s significant effectiveness and robustness.