This work reframes the Text-to-SQL task as a pathway for teaching large language models (LLMs) to reason over and manipulate tabular data--moving beyond the traditional focus on query generation. We propose a two-stage framework that leverages SQL supervision to develop transferable table reasoning capabilities. First, we synthesize detailed chain-of-thought (CoT) traces from real-world SQL queries, providing step-by-step, clause-level supervision that teaches the model how to traverse, filter, and aggregate table fields. Second, we introduce a Group Relative Policy Optimization (GRPO) reinforcement learning objective that connects SQL execution accuracy to generalizable reasoning by encouraging steps that extend beyond task-specific syntax and transfer across datasets. Empirically, our approach improves performance on standard Text-to-SQL benchmarks and achieves substantial gains on reasoning-intensive datasets such as BIRD and CRT-QA, demonstrating enhanced generalization and interpretability. Specifically, the distilled-quantized LLaMA model achieved a relative 33.9\% increase in accuracy when trained on Text-to-SQL tasks, while Qwen achieved a relative 14.5\% increase. These results suggest that SQL can serve not only as a target formalism but also as an effective scaffold for learning robust, transferable reasoning over structured data.

Sanitizing sensitive text data typically involves removing personally identifiable information (PII) or generating synthetic data under the assumption that these methods adequately protect privacy; however, their effectiveness is often only assessed by measuring the leakage of explicit identifiers but ignoring nuanced textual markers that can lead to re-identification. We challenge the above illusion of privacy by proposing a new framework that evaluates re-identification attacks to quantify individual privacy risks upon data release. Our approach shows that seemingly innocuous auxiliary information -- such as routine social activities -- can be used to infer sensitive attributes like age or substance use history from sanitized data. For instance, we demonstrate that Azure's commercial PII removal tool fails to protect 74\% of information in the MedQA dataset. Although differential privacy mitigates these risks to some extent, it significantly reduces the utility of the sanitized text for downstream tasks. Our findings indicate that current sanitization techniques offer a \textit{false sense of privacy}, highlighting the need for more robust methods that protect against semantic-level information leakage.

Moral stories are a time-tested vehicle for transmitting values, yet modern NLP lacks a large, structured corpus that couples coherent narratives with explicit ethical lessons. We close this gap with TF1-EN-3M, the first open dataset of three million English-language fables generated exclusively by instruction-tuned models no larger than 8B parameters. Each story follows a six-slot scaffold (character -> trait -> setting -> conflict -> resolution -> moral), produced through a combinatorial prompt engine that guarantees genre fidelity while covering a broad thematic space. A hybrid evaluation pipeline blends (i) a GPT-based critic that scores grammar, creativity, moral clarity, and template adherence with (ii) reference-free diversity and readability metrics. Among ten open-weight candidates, an 8B-parameter Llama-3 variant delivers the best quality-speed trade-off, producing high-scoring fables on a single consumer GPU (<24 GB VRAM) at approximately 13.5 cents per 1,000 fables. We release the dataset, generation code, evaluation scripts, and full metadata under a permissive license, enabling exact reproducibility and cost benchmarking. TF1-EN-3M opens avenues for research in instruction following, narrative intelligence, value alignment, and child-friendly educational AI, demonstrating that large-scale moral storytelling no longer requires proprietary giant models.

Accurately modeling user preferences is vital not only for improving recommendation performance but also for enhancing transparency in recommender systems. Conventional user profiling methods, such as averaging item embeddings, often overlook the evolving, nuanced nature of user interests, particularly the interplay between short-term and long-term preferences. In this work, we leverage large language models (LLMs) to generate natural language summaries of users' interaction histories, distinguishing recent behaviors from more persistent tendencies. Our framework not only models temporal user preferences but also produces natural language profiles that can be used to explain recommendations in an interpretable manner. These textual profiles are encoded via a pre-trained model, and an attention mechanism dynamically fuses the short-term and long-term embeddings into a comprehensive user representation. Beyond boosting recommendation accuracy over multiple baselines, our approach naturally supports explainability: the interpretable text summaries and attention weights can be exposed to end users, offering insights into why specific items are suggested. Experiments on real-world datasets underscore both the performance gains and the promise of generating clearer, more transparent justifications for content-based recommendations.

Agentic pipelines present novel challenges and opportunities for human-centered explainability. The HCXAI community is still grappling with how best to make the inner workings of LLMs transparent in actionable ways. Agentic pipelines consist of multiple LLMs working in cooperation with minimal human control. In this research paper, we present early findings from an agentic pipeline implementation of a perceptive task guidance system. Through quantitative and qualitative analysis, we analyze how Chain-of-Thought (CoT) reasoning, a common vehicle for explainability in LLMs, operates within agentic pipelines. We demonstrate that CoT reasoning alone does not lead to better outputs, nor does it offer explainability, as it tends to produce explanations without explainability, in that they do not improve the ability of end users to better understand systems or achieve their goals.

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains. However, their susceptibility to prompt injection attacks poses significant security risks, as adversarial inputs can manipulate model behavior and override intended instructions. Despite numerous defense strategies, a standardized framework to rigorously evaluate their effectiveness, especially under adaptive adversarial scenarios, is lacking. To address this gap, we introduce OET, an optimization-based evaluation toolkit that systematically benchmarks prompt injection attacks and defenses across diverse datasets using an adaptive testing framework. Our toolkit features a modular workflow that facilitates adversarial string generation, dynamic attack execution, and comprehensive result analysis, offering a unified platform for assessing adversarial robustness. Crucially, the adaptive testing framework leverages optimization methods with both white-box and black-box access to generate worst-case adversarial examples, thereby enabling strict red-teaming evaluations. Extensive experiments underscore the limitations of current defense mechanisms, with some models remaining susceptible even after implementing security enhancements.

This report explores the convergence of large language models (LLMs) and cybersecurity, synthesizing interdisciplinary insights from network security, artificial intelligence, formal methods, and human-centered design. It examines emerging applications of LLMs in software and network security, 5G vulnerability analysis, and generative security engineering. The report highlights the role of agentic LLMs in automating complex tasks, improving operational efficiency, and enabling reasoning-driven security analytics. Socio-technical challenges associated with the deployment of LLMs -- including trust, transparency, and ethical considerations -- can be addressed through strategies such as human-in-the-loop systems, role-specific training, and proactive robustness testing. The report further outlines critical research challenges in ensuring interpretability, safety, and fairness in LLM-based systems, particularly in high-stakes domains. By integrating technical advances with organizational and societal considerations, this report presents a forward-looking research agenda for the secure and effective adoption of LLMs in cybersecurity.

HMCF: A Human-in-the-loop Multi-Robot Collaboration Framework Based on Large Language Models Zhaoxing Li, Wenbo Wu, Y ue Wang, Y anran Xu, William Hunt, and Sebastian Stein Abstract -- Rapid advancements in artificial intelligence (AI) have enabled robots to perform complex tasks autonomously with increasing precision. Traditional approaches often lack generalization, requiring extensive engineering for new tasks and scenarios, and struggle with managing diverse robots. T o overcome these limitations, we propose a Human-in-the-loop Multi-Robot Collaboration Framework (HMCF) powered by large language models (LLMs). LLMs enhance adaptability by reasoning over diverse tasks and robot capabilities, while human oversight ensures safety and reliability, intervening only when necessary. Each robot is equipped with an LLM agent capable of understanding its capabilities, converting tasks into executable instructions, and reducing hallucinations through task verification and human supervision. Simulation results show that our framework outperforms state-of-the-art task planning methods, achieving higher task success rates with an improvement of 4.76%. Real-world tests demonstrate its robust zero-shot generalization feature and ability to handle diverse tasks and environments with minimal human intervention. I NTRODUCTION The rapid progress of artificial intelligence (AI) and robotics has significantly advanced multi-robot systems (MRSs), enabling them to perform increasingly complex tasks with high autonomy and precision [1]. These systems are deployed in various real-world applications, including disaster response, industrial automation, logistics, and healthcare [2], [3]. By coordinating multiple robots, MRSs can efficiently handle large-scale tasks that exceed the capabilities of individual robots.

Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models (LLMs). In this work, we introduce Spill The Beans, a novel application of cache side-channels to leak tokens generated by an LLM. By co-locating an attack process on the same hardware as the victim model, we flush and reload embedding vectors from the embedding layer, where each token corresponds to a unique embedding vector. When accessed during token generation, it results in a cache hit detectable by our attack on shared lower-level caches. A significant challenge is the massive size of LLMs, which, by nature of their compute intensive operation, quickly evicts embedding vectors from the cache. We address this by balancing the number of tokens monitored against the amount of information leaked. Monitoring more tokens increases potential vocabulary leakage but raises the chance of missing cache hits due to eviction; monitoring fewer tokens improves detection reliability but limits vocabulary coverage. Through extensive experimentation, we demonstrate the feasibility of leaking tokens from LLMs via cache side-channels. Our findings reveal a new vulnerability in LLM deployments, highlighting that even sophisticated models are susceptible to traditional side-channel attacks. We discuss the implications for privacy and security in LLM-serving infrastructures and suggest considerations for mitigating such threats. For proof of concept we consider two concrete attack scenarios: Our experiments show that an attacker can recover as much as 80%-90% of a high entropy API key with single shot monitoring. As for English text we can reach a 40% recovery rate with a single shot. We should note that the rate highly depends on the monitored token set and these rates can be improved by targeting more specialized output domains.

Large Language Models (LLMs) have shown remarkable capabilities in manipulating natural language across multiple applications, but their ability to handle simple reasoning tasks is often questioned. In this work, we aim to provide a comprehensive analysis of LLMs' reasoning competence, specifically focusing on their prompt dependency. In particular, we introduce a new benchmark dataset with a series of simple reasoning questions demanding shallow logical reasoning. Aligned with cognitive psychology standards, the questions are confined to a basic domain revolving around geometric figures, ensuring that responses are independent of any pre-existing intuition about the world and rely solely on deduction. An empirical analysis involving zero-shot and few-shot prompting across 24 LLMs of different sizes reveals that, while LLMs with over 70 billion parameters perform better in the zero-shot setting, there is still a large room for improvement. An additional test with chain-of-thought prompting over 22 LLMs shows that this additional prompt can aid or damage the performance of models, depending on whether the rationale is required before or after the answer.