Interesting to see how well the proposed model would do under such zero-shot setup (i.e. GPT -2 accuracy is taken from their paper. The BERT paper reports that BooksCorpus and Wikipedia contain 0.8B and 2.5B words, respectively. For our processed data, BooksCorpus and Wikipedia contain 0.75B and 2B words, respectively. The implementation is the same as word embedding, i.e., a lookup "Segment 1", and "Segment 2") and feed it to model input, which indicates the segment of input tokens.

Large Language Models (LLMs) have recently demonstrated strong emergent abilities in complex reasoning and zero-shot generalization, showing unprecedented potential for LLM-as-a-judge applications in education, peer review, and data quality evaluation. However, their robustness under prompt injection attacks, where malicious instructions are embedded into the content to manipulate outputs, remains a significant concern. In this work, we explore a frustratingly simple yet effective attack setting to test whether LLMs can be easily misled. Specifically, we evaluate LLMs on basic arithmetic questions (e.g., "What is 3 + 2?") presented as either multiple-choice or true-false judgment problems within PDF files, where hidden prompts are injected into the file. Our results reveal that LLMs are indeed vulnerable to such hidden prompt injection attacks, even in these trivial scenarios, highlighting serious robustness risks for LLM-as-a-judge applications.

Formula alpha mining, which generates predictive signals from financial data, is critical for quantitative investment. Although various algorithmic approaches-such as genetic programming, reinforcement learning, and large language models-have significantly expanded the capacity for alpha discovery, systematic evaluation remains a key challenge. Existing evaluation metrics predominantly include backtesting and correlation-based measures. Backtesting is computationally intensive, inherently sequential, and sensitive to specific strategy parameters. Correlation-based metrics, though efficient, assess only predictive ability and overlook other crucial properties such as temporal stability, robustness, diversity, and interpretability. Additionally, the closed-source nature of most existing alpha mining models hinders reproducibility and slows progress in this field. To address these issues, we propose AlphaEval, a unified, parallelizable, and backtest-free evaluation framework for automated alpha mining models. AlphaEval assesses the overall quality of generated alphas along five complementary dimensions: predictive power, stability, robustness to market perturbations, financial logic, and diversity. Extensive experiments across representative alpha mining algorithms demonstrate that AlphaEval achieves evaluation consistency comparable to comprehensive backtesting, while providing more comprehensive insights and higher efficiency. Furthermore, AlphaEval effectively identifies superior alphas compared to traditional single-metric screening approaches. All implementations and evaluation tools are open-sourced to promote reproducibility and community engagement.

Understanding and quantifying human cognitive biases from empirical data has long posed a formidable challenge, particularly in cybersecurity, where defending against unknown adversaries is paramount. Traditional cyber defense strategies have largely focused on fortification, while some approaches attempt to anticipate attacker strategies by mapping them to cognitive vulnerabilities, yet they fall short in dynamically interpreting attacks in progress. In recognition of this gap, IARPA's ReSCIND program seeks to infer, defend against, and even exploit attacker cognitive traits. In this paper, we present a novel methodology that leverages large language models (LLMs) to extract quantifiable insights into the cognitive bias of loss aversion from hacker behavior. Our data are collected from an experiment in which hackers were recruited to attack a controlled demonstration network. We process the hacker generated notes using LLMs using it to segment the various actions and correlate the actions to predefined persistence mechanisms used by hackers. By correlating the implementation of these mechanisms with various operational triggers, our analysis provides new insights into how loss aversion manifests in hacker decision-making. The results demonstrate that LLMs can effectively dissect and interpret nuanced behavioral patterns, thereby offering a transformative approach to enhancing cyber defense strategies through real-time, behavior-based analysis.

In this paper, we introduce MATA, a novel evaluation dataset to assess the ability of Large Language Models (LLMs) in Telugu language, comprising 729 carefully curated multiple-choice and open-ended questions that span diverse linguistic dimensions. We evaluate 11 open-weight and closed-source LLMs on our dataset and present a fine-grained analysis of their performance. Further, we empirically show how LLMs rely on superficial heuristics such as answer position and distractor patterns for multiple-choice questions. Finally, we also compare LLM-as-a-judge evaluation with human evaluation for open-ended questions and draw some conclusions on its reliability in a low-resource language. We argue that such fine-grained evaluation is essential for understanding model limitations and can inform the development of more linguistically capable LLMs, while also serving as a foundation for future research in Telugu NLP.

Large language models (LLMs) for Arabic are still dominated by Modern Standard Arabic (MSA), with limited support for Saudi dialects such as Najdi and Hijazi. This underrepresentation hinders their ability to capture authentic dialectal variation. Using a privately curated Saudi Dialect Instruction dataset (Hijazi and Najdi; 5,466 synthetic instruction-response pairs; 50/50 split), we LoRA-tune ALLaM-7B-Instruct-preview, the first foundation model developed in Saudi Arabia, for Saudi dialect generation. We investigate two variants: (i) Dialect-Token training, which prepends an explicit dialect tag to the instruction, and (ii) No-Token training, which omits the tag at formatting time. Evaluation on a held-out test set combines an external dialect classifier with text fidelity metrics (chrF++ and BERTScore) and diversity measures. The Dialect-Token model achieves the best control, raising the Saudi rate from 47.97% to 84.21% and reducing MSA leakage from 32.63% to 6.21%; fidelity also improves (chrF++ +3.53, BERTScore +0.059). Both LoRA variants outperform strong generic instruction models (Falcon-7B-Instruct, Llama-3.1-8B-Instruct, Qwen-2.5-7B-Instruct, AceGPT-v2-8B-Chat, JAIS-13B-Chat) in dialect control and fidelity, while avoiding metadata-tag echoing that these baselines frequently exhibit. We do not release the dataset or any model weights/adapters; instead, we release training/evaluation/inference code and a detailed datasheet (schema and aggregate statistics) to support independent verification.

Digital health analytics face critical challenges nowadays. The sophisticated analysis of patient-generated health content, which contains complex emotional and medical contexts, requires scarce domain expertise, while traditional ML approaches are constrained by data shortage and privacy limitations in healthcare settings. Online Health Communities (OHCs) exemplify these challenges with mixed-sentiment posts, clinical terminology, and implicit emotional expressions that demand specialised knowledge for accurate Sentiment Analysis (SA). To address these challenges, this study explores how Large Language Models (LLMs) can integrate expert knowledge through in-context learning for SA, providing a scalable solution for sophisticated health data analysis. Specifically, we develop a structured codebook that systematically encodes expert interpretation guidelines, enabling LLMs to apply domain-specific knowledge through targeted prompting rather than extensive training. Six GPT models validated alongside DeepSeek and LLaMA 3.1 are compared with pre-trained language models (BioBERT variants) and lexicon-based methods, using 400 expert-annotated posts from two OHCs. LLMs achieve superior performance while demonstrating expert-level agreement. This high agreement, with no statistically significant difference from inter-expert agreement levels, suggests knowledge integration beyond surface-level pattern recognition. The consistent performance across diverse LLM models, supported by in-context learning, offers a promising solution for digital health analytics. This approach addresses the critical challenge of expert knowledge shortage in digital health research, enabling real-time, expert-quality analysis for patient monitoring, intervention assessment, and evidence-based health strategies.

Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reasoning tasks. Recent studies have explored fine-tuning Large Language Models (LLMs) with synthetic data to enhance their long-context capabilities. However, the effectiveness of such approaches is often limited by the low diversity and factual inconsistencies in the generated data. To address these challenges, we propose LongMab-PO, a novel framework that leverages a Multi-Armed Bandit (MAB) rollout strategy to identify the most informative chunks from the given long context for sampling high-quality and diverse responses and constructing preference data pairs for Direct Preference Optimization (DPO) training. Specifically, we treat context chunks as arms of MAB, select chunks based on their expected reward scores to input into LLMs to generate responses, and iteratively update these scores based on reward feedback. This exploration and exploitation process enables the model to focus on the most relevant context segments, thereby generating and collecting high-quality and diverse responses. Finally, we collect these generated responses from the rollout process and apply the DPO method to further optimize the LLM. Experimental results show that LongMab-PO significantly improves the diversity and quality of preference data pairs, achieving state-of-the-art performance on long-context reasoning benchmarks.