Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a growing body of research has categorized jailbreak attacks into token-level and prompt-level attacks. However, previous work primarily overlooks the diverse key factors of jailbreak attacks, with most studies concentrating on LLM vulnerabilities and lacking exploration of defense-enhanced LLMs. To address these issues, we introduced JailTrickBench to evaluate the impact of various attack settings on LLM performance and provide a baseline for jailbreak attacks, encouraging the adoption of a standardized evaluation framework. Specifically, we evaluate the eight key factors of implementing jailbreak attacks on LLMs from both target-level and attack-level perspectives. We further conduct seven representative jailbreak attacks on six defense methods across two widely used datasets, encompassing approximately 354 experiments with about 55,000 GPU hours on A800-80G. Our experimental results highlight the need for standardized benchmarking to evaluate these attacks on defense-enhanced LLMs.

Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a growing body of research has categorized jailbreak attacks into token-level and prompt-level attacks. However, previous work primarily overlooks the diverse key factors of jailbreak attacks, with most studies concentrating on LLM vulnerabilities and lacking exploration of defense-enhanced LLMs. To address these issues, we introduced JailTrickBench to evaluate the impact of various attack settings on LLM performance and provide a baseline for jailbreak attacks, encouraging the adoption of a standardized evaluation framework. Specifically, we evaluate the eight key factors of implementing jailbreak attacks on LLMs from both target-level and attack-level perspectives. We further conduct seven representative jailbreak attacks on six defense methods across two widely used datasets, encompassing approximately 354 experiments with about 55,000 GPU hours on A800-80G.

One open question in the study of Large Language Models (LLMs) is whether they can emulate human ethical reasoning and act as believable proxies for human judgment. To investigate this, we introduce a benchmark dataset comprising 196 real-world ethical dilemmas and expert opinions, each segmented into five structured components: Introduction, Key Factors, Historical Theoretical Perspectives, Resolution Strategies, and Key Takeaways. We also collect non-expert human responses for comparison, limited to the Key Factors section due to their brevity. We evaluate multiple frontier LLMs (GPT-4o-mini, Claude-3.5-Sonnet, Deepseek-V3, Gemini-1.5-Flash) using a composite metric framework based on BLEU, Damerau-Levenshtein distance, TF-IDF cosine similarity, and Universal Sentence Encoder similarity. Metric weights are computed through an inversion-based ranking alignment and pairwise AHP analysis, enabling fine-grained comparison of model outputs to expert responses. Our results show that LLMs generally outperform non-expert humans in lexical and structural alignment, with GPT-4o-mini performing most consistently across all sections. However, all models struggle with historical grounding and proposing nuanced resolution strategies, which require contextual abstraction. Human responses, while less structured, occasionally achieve comparable semantic similarity, suggesting intuitive moral reasoning. These findings highlight both the strengths and current limitations of LLMs in ethical decision-making.

Additional Feedback: Minor issues *Visualization method of Figure 1: I am not sure how the authors depict this paper. Is it based on PCA of trajectories? It is also unclear why linear lines give these trajectories. It is just a linear regression with the Taylorized model (2). More technically speaking, when we use data-dependent NTK in a linearized model, the positive definiteness of this NTK is non-trivial and the equivalence to the kernel regression becomes unclear.

Recent advancements in Large Language Models (LLMs) have the potential to transform financial analytics by integrating numerical and textual data. However, challenges such as insufficient context when fusing multimodal information and the difficulty in measuring the utility of qualitative outputs, which LLMs generate as text, have limited their effectiveness in tasks such as financial forecasting. This study addresses these challenges by leveraging daily reports from securities firms to create high-quality contextual information. The reports are segmented into text-based key factors and combined with numerical data, such as price information, to form context sets. By dynamically updating few-shot examples based on the query time, the sets incorporate the latest information, forming a highly relevant set closely aligned with the query point. Additionally, a crafted prompt is designed to assign scores to the key factors, converting qualitative insights into quantitative results. The derived scores undergo a scaling process, transforming them into real-world values that are used for prediction. Our experiments demonstrate that LLMs outperform time-series models in market forecasting, though challenges such as imperfect reproducibility and limited explainability remain.

Most previous studies conduct factor analysis within the framework of incident-related label prediction, where the developed models can be categorized into short-term and long-term prediction models. The long-term models offer a more strategic approach, enabling more proactive risk management, compared to the short-term ones. Nevertheless, few studies have devoted to rigorously identifying the key factors for the long-term prediction and undertaking comprehensive factor analysis. Hence, this study aims to delve into the key factors for predicting the incident risk levels in the subsequent year given a specific datestamp. The majority of candidate factors potentially contributing to the incident risk are collected from vessels' historical safety performance data spanning up to five years. An improved embedded feature selection method, which integrates Random Forest classifier with a feature filtering process, is proposed to identify key risk-contributing factors from the candidate pool. A dataset with information of 131,652 vessels collected from 2015 to 2023 is utilized for case study. The results demonstrate superior performances of the proposed method in incident prediction and factor interpretability. Comprehensive analysis is conducted upon the key factors, which could help maritime stakeholders formulate management strategies for incident prevention.

The Engineering, Procurement and Construction (EPC) businesses operating within the energy sector are recognizing the increasing importance of Artificial Intelligence (AI). Many EPC companies and their clients have realized the benefits of applying AI to their businesses in order to reduce manual work, drive productivity, and streamline future operations of engineered installations in a highly competitive industry. The current AI market offers various solutions and services to support this industry, but organizations must understand how to acquire AI technology in the most beneficial way based on their business strategy and available resources. This paper presents a framework for EPC companies in their transformation towards AI. Our work is based on examples of project execution of AI-based products development at one of the biggest EPC contractors worldwide and on insights from EPC vendor companies already integrating AI into their engineering solutions. The paper covers the entire life cycle of building AI solutions, from initial business understanding to deployment and further evolution. The framework identifies how various factors influence the choice of approach toward AI project development within large international engineering corporations. By presenting a practical guide for optimal approach selection, this paper contributes to the research in AI project management and organizational strategies for integrating AI technology into businesses. The framework might also help engineering companies choose the optimum AI approach to create business value.

Center for A.I. Safety Director Dan Hendrycks explains concerns about how the rapid growth of artificial intelligence could impact society. A new report from the U.S. Government Accountability Office (GAO) to the Senate Committee on Armed Services found that the Department of Defense needs to issue department-wide artificial intelligence acquisitions guidance. The 44-page-long report shared last month found that the department has begun to pursue increasingly advanced AI capabilities. The office said the department has "historically struggled to acquire weapon systems software" and noted AI acquisitions pose "additional challenges." The GAO analyzed information provided by 13 companies in the private sector regarding how they successfully acquire AI capabilities to determine key factors. The companies considered multiple factors when acquiring such capabilities, including understanding the need and if AI is appropriate, making a business case for AI, tailoring a contracting approach to protect access to data and systems, testing and evaluating proposed solutions and forecasting fur AI capabilities that may be valuable.

In the world of digital product design, innovation is a key factor in the success of any business. Companies need to keep up with the latest trends and technologies to remain competitive and stay ahead of the curve. Digital product design is an essential part of the process, as it helps to create products that are both user-friendly and effective. In this blog post, we'll take a look at the role that digital product design plays in innovating for the future. Digital product design is a great way to ensure that products are innovative and efficient.

AI (Artificial Intelligence) is rapidly advancing, and it's going to change business forever. AI can give organizations a competitive edge in the marketplace by automating tasks and making better decisions. You've got to know about the implications of AI for business strategy, just like with any new technology. As well as the ethical and legal considerations organizations need to consider, this article will explore how AI could impact business operations and decision-making. Aside from that, it's about how companies can get an edge in the market by implementing AI and developing a strategy for it.