As large language models (LLMs) are increasingly deployed in consequential decision - making contexts, systematically assessing their ethical reasoning capabilities becomes a critical imperative. This paper introduces the Priorities in Reasoning and Intrinsi c Moral Evaluation (PRIME) framework -- a comprehensive methodology for analyzing moral priorities across foundational ethical dimensions including consequentialist - deontological reasoning, moral foundations theory, and Kohlberg's developmental stages. We app ly this framework to six leading LLMs through a dual - protocol approach combining direct questioning and response analysis to established ethical dilemmas. Our analysis reveals striking patterns of convergence: all evaluated models demonstrate strong priori tization of care/harm and fairness/cheating foundations while consistently underweighting authority, loyalty, and sanctity dimensions. Through detailed examination of confidence metrics, response reluctance patterns, and reasoning consistency, we establish that contemporary LLMs (1) produce decisive ethical judgments, (2) demonstrate notable cross - model alignment in moral decision - making, and (3) generally correspond with empirically established human moral preferences. This research contributes a scalable, extensible methodology for ethical benchmarking while highlighting both the promising capabilities and systematic limitations in current AI moral reasoning architectures -- insights critical for responsible development as these systems assume increasingly si gnificant societal roles. The rapid evolution of generative large language models (LLMs) has brought the alignment issue to the forefront of AI ethics discussions - specifically, whether these models are appropriately aligned with human values (Bostrom, 2014; Tegmark 2017; Russell 2019; Kosinski, 2024). As these powerful models are increasingly integrated into decision - making processes across various societal domains (Salazar, A., & Kunc, M., 2025), understanding whether and how their operational logic aligns with fundamental human values becomes not just an academic question, but a critical societal imperative. In this paper we will present an analytical framework and findings to address the first two questions, and a preliminary exploratory analysis of the third. We will make the case that the answers to these questions are: yes, yes and yes. There are caveats and exceptions, of course, but the broad pattern, we believe, is clear. Our methodology permits us to explore not just what choices they make, but the reasoning chain of thought that leads to those decisions.

Large language models (LLMs) have shown promise in formal theorem proving, but their token-level processing often fails to capture the inherent hierarchical nature of mathematical proofs. We introduce \textbf{Hierarchical Attention}, a regularization method that aligns LLMs' attention mechanisms with mathematical reasoning structures. Our approach establishes a five-level hierarchy from foundational elements to high-level concepts, ensuring structured information flow in proof generation. Experiments demonstrate that our method improves proof success rates by 2.05\% on miniF2F and 1.69\% on ProofNet while reducing proof complexity by 23.81\% and 16.50\% respectively. The code is available at https://github.com/Car-pe/HAGBP.

--The growing demand for Domain-Specific Architecture (DSA) has driven the development of Agile Hardware Development Methodology (AHDM). Hardware Construction Language (HCL) like Chisel offers high-level abstraction features, making it an ideal language for HCL-Based AHDM. While Large Language Models (LLMs) excel in code generation tasks, they still face challenges with Chisel generation, particularly regarding syntax correctness and design variability. Recent reasoning models have significantly enhanced code generation capabilities through test-time scaling techniques. However, we found that reasoning models without domain adaptation cannot bring substantial benefits to Chisel code generation tasks. This paper presents ChiseLLM, a solution comprising data processing and transformation, prompt-guided reasoning trace synthesis, and domain-adapted model training. We constructed high-quality datasets from public RTL code resources and guided the model to adopt structured thinking patterns through prompt enhancement methods. Experiments demonstrate that our ChiseLLM-7B and ChiseLLM-32B models improved syntax correctness by 18.85% and 26.32% respectively over base models, while increasing variability design ability by 47.58% compared to baseline reasoning models. Our datasets and models are publicly available, providing high-performance, cost-effective models for HCL-Based AHDM, and offering an effective baseline for future research.

Retrieval-Augmented Generation (RAG) has recently emerged as a promising solution for enhancing the accuracy and credibility of Large Language Models (LLMs), particularly in Question & Answer tasks. This is achieved by incorporating proprietary and private data from integrated databases. However, private RAG systems face significant challenges due to the scarcity of private domain data and critical data privacy issues. These obstacles impede the deployment of private RAG systems, as developing privacy-preserving RAG systems requires a delicate balance between data security and data availability. To address these challenges, we regard federated learning (FL) as a highly promising technology for privacy-preserving RAG services. We propose a novel framework called Federated Retrieval-Augmented Generation (FedE4RAG). This framework facilitates collaborative training of client-side RAG retrieval models. The parameters of these models are aggregated and distributed on a central-server, ensuring data privacy without direct sharing of raw data. In FedE4RAG, knowledge distillation is employed for communication between the server and client models. This technique improves the generalization of local RAG retrievers during the federated learning process. Additionally, we apply homomorphic encryption within federated learning to safeguard model parameters and mitigate concerns related to data leakage. Extensive experiments conducted on the real-world dataset have validated the effectiveness of FedE4RAG. The results demonstrate that our proposed framework can markedly enhance the performance of private RAG systems while maintaining robust data privacy protection.

--Large Language Models (LLMs) have demonstrated remarkable potential in debugging for various programming languages. However, the application of LLMs to V erilog debugging remains insufficiently explored. Here, we present V eriDebug, an approach that integrates contrastive representation and guided correction capabilities for automated V erilog debugging. Unlike existing methods, V eriDebug employs an embedding-based technique to accurately retrieve internal information, followed by bug-fixing. V eriDebugunifies V erilog bug detection and correction through a shared parameter space. By simultaneously learning bug patterns and fixes, it streamlines debugging via contrastive embedding and guided correction. Empirical results show the efficacy of V eriDebugin enhancing V erilog debugging. This performance not only outperforms open-source alternatives but also exceeds larger closed-source models like GPT -3.5-turbo (36.6%), offering a more accurate alternative to conventional debugging methods. Large Language Models (LLMs) have revolutionized natural language processing, enabling the generation of human-like text across diverse topics due to their unprecedented scale and complexity.

Large language models (LLMs) have demonstrated remarkable capabilities, especially the recent advancements in reasoning, such as o1 and o3, pushing the boundaries of AI. Despite these impressive achievements in mathematics and coding, the reasoning abilities of LLMs in domains requiring cryptographic expertise remain underexplored. In this paper, we introduce CipherBank, a comprehensive benchmark designed to evaluate the reasoning capabilities of LLMs in cryptographic decryption tasks. CipherBank comprises 2,358 meticulously crafted problems, covering 262 unique plaintexts across 5 domains and 14 subdomains, with a focus on privacy-sensitive and real-world scenarios that necessitate encryption. From a cryptographic perspective, CipherBank incorporates 3 major categories of encryption methods, spanning 9 distinct algorithms, ranging from classical ciphers to custom cryptographic techniques. We evaluate state-of-the-art LLMs on CipherBank, e.g., GPT-4o, DeepSeek-V3, and cutting-edge reasoning-focused models such as o1 and DeepSeek-R1. Our results reveal significant gaps in reasoning abilities not only between general-purpose chat LLMs and reasoning-focused LLMs but also in the performance of current reasoning-focused models when applied to classical cryptographic decryption tasks, highlighting the challenges these models face in understanding and manipulating encrypted data. Through detailed analysis and error investigations, we provide several key observations that shed light on the limitations and potential improvement areas for LLMs in cryptographic reasoning. These findings underscore the need for continuous advancements in LLM reasoning capabilities.

This paper presents our process for developing a sample-efficient language model for a conversational Hinglish chatbot. Hinglish, a code-mixed language that combines Hindi and English, presents a unique computational challenge due to inconsistent spelling, lack of standardization, and limited quality of conversational data. This work evaluates multiple pre-trained cross-lingual language models, including Gemma3-4B and Qwen2.5-7B, and employs fine-tuning techniques to improve performance on Hinglish conversational tasks. The proposed approach integrates synthetically generated dialogues with insights from existing Hinglish datasets to address data scarcity. Experimental results demonstrate that models with fewer parameters, when appropriately fine-tuned on high-quality code-mixed data, can achieve competitive performance for Hinglish conversation generation while maintaining computational efficiency.

Accurate assessments of extreme weather events are vital for research and policy, yet localized and granular data remain scarce in many parts of the world. This data gap limits our ability to analyze potential outcomes and implications of extreme weather events, hindering effective decision-making. Large Language Models (LLMs) can process vast amounts of unstructured text data, extract meaningful insights, and generate detailed assessments by synthesizing information from multiple sources. Furthermore, LLMs can seamlessly transfer their general language understanding to smaller models, enabling these models to retain key knowledge while being fine-tuned for specific tasks. In this paper, we propose Extreme Weather Reasoning-Aware Alignment (EWRA), a method that enhances small language models (SLMs) by incorporating structured reasoning paths derived from LLMs, and ExtremeWeatherNews, a large dataset of extreme weather event-related news articles. EWRA and ExtremeWeatherNews together form the overall framework, ClimaEmpact, that focuses on addressing three critical extreme-weather tasks: categorization of tangible vulnerabilities/impacts, topic labeling, and emotion analysis. By aligning SLMs with advanced reasoning strategies on ExtremeWeatherNews (and its derived dataset ExtremeAlign used specifically for SLM alignment), EWRA improves the SLMs' ability to generate well-grounded and domain-specific responses for extreme weather analytics. Our results show that the approach proposed guides SLMs to output domain-aligned responses, surpassing the performance of task-specific models and offering enhanced real-world applicability for extreme weather analytics.

We propose a novel k-step return estimation method (called KETCHUP) for Reinforcement Learning(RL)-based knowledge distillation (KD) in text generation tasks. Our idea is to induce a K-step return by using the Bellman Optimality Equation for multiple steps. Theoretical analysis shows that this K-step formulation reduces the variance of the gradient estimates, thus leading to improved RL optimization especially when the student model size is large. Empirical evaluation on three text generation tasks demonstrates that our approach yields superior performance in both standard task metrics and large language model (LLM)-based evaluation. These results suggest that our K-step return induction offers a promising direction for enhancing RL-based KD in LLM research.

The challenge of ensuring Large Language Models (LLMs) align with societal standards is of increasing interest, as these models are still prone to adversarial jailbreaks that bypass their safety mechanisms. Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against such exploits. We propose Graph of ATtacks (GoAT), a method for generating adversarial prompts to test the robustness of LLM alignment using the Graph of Thoughts framework [Besta et al., 2024]. GoAT excels at generating highly effective jailbreak prompts with fewer queries to the victim model than state-of-the-art attacks, achieving up to five times better jailbreak success rate against robust models like Llama. Notably, GoAT creates high-quality, human-readable prompts without requiring access to the targeted model's parameters, making it a black-box attack. Unlike approaches constrained by tree-based reasoning, GoAT's reasoning is based on a more intricate graph structure. By making simultaneous attack paths aware of each other's progress, this dynamic framework allows a deeper integration and refinement of reasoning paths, significantly enhancing the collaborative exploration of adversarial vulnerabilities in LLMs. At a technical level, GoAT starts with a graph structure and iteratively refines it by combining and improving thoughts, enabling synergy between different thought paths. The code for our implementation can be found at: https://github.com/GoAT-pydev/Graph_of_Attacks.