As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across disciplines such as philosophy, psychology, law, computer science, mathematics, and political science. This inconsistency complicates their application to AI, where differing interpretations lead to conflicting approaches in system design and regulation. This paper traces the historical, philosophical, and technical evolution of these concepts, emphasizing how their definitions influence AI development, deployment, and oversight. We argue that the urgency surrounding AI alignment and autonomy stems not only from technical advancements but also from the increasing deployment of AI in high-stakes decision making. Using Agentic AI as a case study, we examine the emergent properties of machine agency and autonomy, highlighting the risks of misalignment in real-world systems. Through an analysis of automation failures (Tesla Autopilot, Boeing 737 MAX), multi-agent coordination (Metas CICERO), and evolving AI architectures (DeepMinds AlphaZero, OpenAIs AutoGPT), we assess the governance and safety challenges posed by frontier AI.

This paper explores the intersection of artificial intelligence and higher education administration, focusing on liberal arts colleges (LACs). It examines AI's opportunities and challenges in academic and student affairs, legal compliance, and accreditation processes, while also addressing the ethical considerations of AI deployment in mission-driven institutions. Considering AI's value pluralism and potential allocative or representational harms caused by algorithmic bias, LACs must ensure AI aligns with its mission and principles. The study highlights other strategies for responsible AI integration, balancing innovation with institutional values.

Recently, language models (LMs) have shown impressive proficiency in code generation tasks, especially when fine-tuned on code-specific datasets, commonly known as Code LMs. However, our understanding of the internal decision-making processes of Code LMs, such as how they use their (syntactic or semantic) knowledge, remains limited, which could lead to unintended harm as they are increasingly used in real life. This motivates us to conduct one of the first Mechanistic Interpretability works to understand how Code LMs perform a syntactic completion task, specifically the closing parenthesis task, on the CodeLlama-7b model (Roziere et al. 2023). Our findings reveal that the model requires middle-later layers until it can confidently predict the correct label for the closing parenthesis task. Additionally, we identify that while both multi-head attention (MHA) and feed-forward (FF) sub-layers play essential roles, MHA is particularly crucial. Furthermore, we also discover attention heads that keep track of the number of already closed parentheses precisely but may or may not promote a correct number of closing parentheses that are still missing, leading to a positive or negative impact on the model's performance.

Recent advancements in large language models (LLMs) have shown significant potential for automating hardware description language (HDL) code generation from high-level natural language instructions. While fine-tuning has improved LLMs' performance in hardware design tasks, prior efforts have largely focused on Verilog generation, overlooking the equally critical task of Verilog understanding. Furthermore, existing models suffer from weak alignment between natural language descriptions and Verilog code, hindering the generation of high-quality, synthesizable designs. To address these issues, we present DeepRTL, a unified representation model that excels in both Verilog understanding and generation. Based on CodeT5+, DeepRTL is fine-tuned on a comprehensive dataset that aligns Verilog code with rich, multi-level natural language descriptions. We also introduce the first benchmark for Verilog understanding and take the initiative to apply embedding similarity and GPT Score to evaluate the models' understanding capabilities. These metrics capture semantic similarity more accurately than traditional methods like BLEU and ROUGE, which are limited to surface-level n-gram overlaps. By adapting curriculum learning to train DeepRTL, we enable it to significantly outperform GPT-4 in Verilog understanding tasks, while achieving performance on par with OpenAI's o1-preview model in Verilog generation tasks.

Large language models (LLMs) are increasingly deployed with hierarchical instruction schemes, where certain instructions (e.g., system-level directives) are expected to take precedence over others (e.g., user messages). Yet, we lack a systematic understanding of how effectively these hierarchical control mechanisms work. We introduce a systematic evaluation framework based on constraint prioritization to assess how well LLMs enforce instruction hierarchies. Our experiments across six state-of-the-art LLMs reveal that models struggle with consistent instruction prioritization, even for simple formatting conflicts. We find that the widely-adopted system/user prompt separation fails to establish a reliable instruction hierarchy, and models exhibit strong inherent biases toward certain constraint types regardless of their priority designation. While controlled prompt engineering and model fine-tuning show modest improvements, our results indicate that instruction hierarchy enforcement is not robustly realized, calling for deeper architectural innovations beyond surface-level modifications.

Large Language Models (LLMs) suffer from hallucination problems, which hinder their reliability in sensitive applications. In the black-box setting, several self-consistency-based techniques have been proposed for hallucination detection. We empirically study these techniques and show that they achieve performance close to that of a supervised (still black-box) oracle, suggesting little room for improvement within this paradigm. To address this limitation, we explore cross-model consistency checking between the target model and an additional verifier LLM. With this extra information, we observe improved oracle performance compared to purely self-consistency-based methods. We then propose a budget-friendly, two-stage detection algorithm that calls the verifier model only for a subset of cases. It dynamically switches between self-consistency and cross-consistency based on an uncertainty interval of the self-consistency classifier. We provide a geometric interpretation of consistency-based hallucination detection methods through the lens of kernel mean embeddings, offering deeper theoretical insights. Extensive experiments show that this approach maintains high detection performance while significantly reducing computational cost.

Large language models (LLMs) have become increasingly popular. Their emergent capabilities can be attributed to their massive training datasets. However, these datasets often contain undesirable or inappropriate content, e.g., harmful texts, personal information, and copyrighted material. This has promoted research into machine unlearning that aims to remove information from trained models. In particular, approximate unlearning seeks to achieve information removal by strategically editing the model rather than complete model retraining. Recent work has shown that soft token attacks (STA) can successfully extract purportedly unlearned information from LLMs, thereby exposing limitations in current unlearning methodologies. In this work, we reveal that STAs are an inadequate tool for auditing unlearning. Through systematic evaluation on common unlearning benchmarks (Who Is Harry Potter? and TOFU), we demonstrate that such attacks can elicit any information from the LLM, regardless of (1) the deployed unlearning algorithm, and (2) whether the queried content was originally present in the training corpus. Furthermore, we show that STA with just a few soft tokens (1-10) can elicit random strings over 400-characters long. Thus showing that STAs are too powerful, and misrepresent the effectiveness of the unlearning methods. Our work highlights the need for better evaluation baselines, and more appropriate auditing tools for assessing the effectiveness of unlearning in LLMs.

Neural code models (NCMs) have demonstrated extraordinary capabilities in code intelligence tasks. Meanwhile, the security of NCMs and NCMs-based systems has garnered increasing attention. In particular, NCMs are often trained on large-scale data from potentially untrustworthy sources, providing attackers with the opportunity to manipulate them by inserting crafted samples into the data. This type of attack is called a code poisoning attack (also known as a backdoor attack). It allows attackers to implant backdoors in NCMs and thus control model behavior, which poses a significant security threat. However, there is still a lack of effective techniques for detecting various complex code poisoning attacks. In this paper, we propose an innovative and lightweight technique for code poisoning detection named KillBadCode. KillBadCode is designed based on our insight that code poisoning disrupts the naturalness of code. Specifically, KillBadCode first builds a code language model (CodeLM) on a lightweight $n$-gram language model. Then, given poisoned data, KillBadCode utilizes CodeLM to identify those tokens in (poisoned) code snippets that will make the code snippets more natural after being deleted as trigger tokens. Considering that the removal of some normal tokens in a single sample might also enhance code naturalness, leading to a high false positive rate (FPR), we aggregate the cumulative improvement of each token across all samples. Finally, KillBadCode purifies the poisoned data by removing all poisoned samples containing the identified trigger tokens. The experimental results on two code poisoning attacks and four code intelligence tasks demonstrate that KillBadCode significantly outperforms four baselines. More importantly, KillBadCode is very efficient, with a minimum time consumption of only 5 minutes, and is 25 times faster than the best baseline on average.

Dynamical systems theory provides a framework for analyzing iterative processes and evolution over time. Within such systems, repetitive transformations can lead to stable configurations, known as attractors, including fixed points and limit cycles. Applying this perspective to large language models (LLMs), which iteratively map input text to output text, provides a principled approach to characterizing long-term behaviors. Successive paraphrasing serves as a compelling testbed for exploring such dynamics, as paraphrases re-express the same underlying meaning with linguistic variation. Although LLMs are expected to explore a diverse set of paraphrases in the text space, our study reveals that successive paraphrasing converges to stable periodic states, such as 2-period attractor cycles, limiting linguistic diversity. This phenomenon is attributed to the self-reinforcing nature of LLMs, as they iteratively favour and amplify certain textual forms over others. This pattern persists with increasing generation randomness or alternating prompts and LLMs. These findings underscore inherent constraints in LLM generative capability, while offering a novel dynamical systems perspective for studying their expressive potential.

We propose TETRIS, a novel method that optimizes the total throughput of batch speculative decoding in multi-request settings. Unlike existing methods that optimize for a single request or a group of requests as a whole, TETRIS actively selects the most promising draft tokens (for every request in a batch) to be accepted when verified in parallel, resulting in fewer rejected tokens and hence less wasted computing resources. Such an effective resource utilization to achieve fast inference in large language models (LLMs) is especially important to service providers with limited inference capacity. Compared to baseline speculative decoding, TETRIS yields a consistently higher acceptance rate and more effective utilization of the limited inference capacity. We show theoretically and empirically that TETRIS outperforms baseline speculative decoding and existing methods that dynamically select draft tokens, leading to a more efficient batch inference in LLMs.