In recent times, Transformer-based language models are making quite an impact in the field of natural language processing. As relevant parallels can be drawn between biological sequences and natural languages, the models used in NLP can be easily extended and adapted for various applications in bioinformatics. In this regard, this paper introduces the major developments of Transformer-based models in the recent past in the context of nucleotide sequences. We have reviewed and analysed a large number of application-based papers on this subject, giving evidence of the main characterizing features and to different approaches that may be adopted to customize such powerful computational machines. We have also provided a structured description of the functioning of Transformers, that may enable even first time users to grab the essence of such complex architectures. We believe this review will help the scientific community in understanding the various applications of Transformer-based language models to nucleotide sequences. This work will motivate the readers to build on these methodologies to tackle also various other problems in the field of bioinformatics.

We introduce a new class of attacks on commercial-scale (human-aligned) language models that induce jailbreaking through targeted bitwise corruptions in model parameters. Our adversary can jailbreak billion-parameter language models with fewer than 25 bit-flips in all cases$-$and as few as 5 in some$-$using up to 40$\times$ less bit-flips than existing attacks on computer vision models at least 100$\times$ smaller. Unlike prompt-based jailbreaks, our attack renders these models in memory 'uncensored' at runtime, allowing them to generate harmful responses without any input modifications. Our attack algorithm efficiently identifies target bits to flip, offering up to 20$\times$ more computational efficiency than previous methods. This makes it practical for language models with billions of parameters. We show an end-to-end exploitation of our attack using software-induced fault injection, Rowhammer (RH). Our work examines 56 DRAM RH profiles from DDR4 and LPDDR4X devices with different RH vulnerabilities. We show that our attack can reliably induce jailbreaking in systems similar to those affected by prior bit-flip attacks. Moreover, our approach remains effective even against highly RH-secure systems (e.g., 46$\times$ more secure than previously tested systems). Our analyses further reveal that: (1) models with less post-training alignment require fewer bit flips to jailbreak; (2) certain model components, such as value projection layers, are substantially more vulnerable than others; and (3) our method is mechanistically different than existing jailbreaks. Our findings highlight a pressing, practical threat to the language model ecosystem and underscore the need for research to protect these models from bit-flip attacks.

Modern AI assistants have made significant progress in natural language understanding and API/tool integration, with emerging efforts to incorporate diverse interfaces (such as Web interfaces) for enhanced scalability and functionality. However, current approaches that heavily rely on repeated LLM-driven HTML parsing are computationally expensive and error-prone, particularly when handling dynamic web interfaces and multi-step tasks. To overcome these challenges, we introduce PAFFA (Premeditated Actions For Fast Agents), a framework designed to enhance web interaction capabilities through an Action API Library of reusable, verified browser interaction functions. By pre-computing interaction patterns and employing two core methodologies - "Dist-Map" for task-agnostic element distillation and "Unravel" for incremental page-wise exploration - PAFFA reduces inference calls by 87% while maintaining robust performance even as website structures evolve. This framework accelerates multi-page task execution and offers a scalable solution to advance autonomous web agent research.

The alignment between human objectives and machine learning models built on these objectives is a crucial yet challenging problem for achieving Trustworthy AI, particularly when preparing for superintelligence (SI). First, given that SI does not exist today, empirical analysis for direct evidence is difficult. Second, SI is assumed to be more intelligent than humans, capable of deceiving us into underestimating its intelligence, making output-based analysis unreliable. Lastly, what kind of unexpected property SI might have is still unclear. To address these challenges, we propose the Superficial Consciousness Hypothesis under Information Integration Theory (IIT), suggesting that SI could exhibit a complex information-theoretic state like a conscious agent while unconscious. To validate this, we use a hypothetical scenario where SI can update its parameters "at will" to achieve its own objective (mesa-objective) under the constraint of the human objective (base objective). We show that a practical estimate of IIT's consciousness metric is relevant to the widely used perplexity metric, and train GPT-2 with those two objectives. Our preliminary result suggests that this SI-simulating GPT-2 could simultaneously follow the two objectives, supporting the feasibility of the Superficial Consciousness Hypothesis.

Automatic evaluation by large language models (LLMs) is a prominent topic today; however, judgment and evaluation tasks are often subjective and influenced by various factors, making adaptation challenging. While many studies demonstrate the capabilities of state-of-the-art proprietary LLMs in comparison to human evaluators, they often struggle to adapt to reference evaluators over time, a requirement for achieving personalized judgment. Additionally, numerous works have attempted to apply open LLMs as judges or evaluators, but these efforts frequently overlook the limitations of working with scarce data. Personalized judgment is inherently associated with limited data scenarios, which are common in many real-world problems. Our work aims to present a data augmentation technique to select a more effective sample from limited data in order to align an open LLM with human preference. Our work achieves approximately 7% improvements in Pearson correlation with a reference judge over the baseline,and 30% improvement over the base model (Llama3.1-8B-Instruct) in the mathematical reasoning evaluation task. demonstrating that augmenting selecting more effective preference data enables our approach to surpass baseline methods.

This paper aims to improve the performance of large language models by addressing the variable computational demands in inference steps, where some tokens require more computational resources than others. We present HARP, a simple modification to "off-the-shelf" Transformer forward pass. Drawing from hesitation and the framing effect in decision-making, HARP selectively applies additional computation when the model encounters uncertainty during token generation. Our method mimics human cognitive processes by pausing at difficult decision points and reframing inputs for a different perspective. Unlike other approaches, HARP is model-agnostic, training-free, and easy to implement. We thoroughly evaluate our method across various downstream tasks and model sizes, demonstrating performance improvements up to +5.16%. Notably, HARP achieves these gains while maintaining inference times twice faster than beam search. Simple and yet with significant gains, HARP offers a practical solution for enhancing the performance of Transformer-based language models with minimal computational impact.

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to the real-world applications. Existing work faces challenges in both training efficiency and generalization capabilities (i.e., Reinforcement Learning from Human Feedback and Red-Teaming). Developing effective strategies to enable LLMs to resist continuously evolving jailbreak attempts represents a significant challenge. To address this challenge, we propose a novel defensive paradigm called GuidelineLLM, which assists LLMs in recognizing queries that may have harmful content. Before LLMs respond to a query, GuidelineLLM first identifies potential risks associated with the query, summarizes these risks into guideline suggestions, and then feeds these guidelines to the responding LLMs. Importantly, our approach eliminates the necessity for additional safety fine-tuning of the LLMs themselves; only the GuidelineLLM requires fine-tuning. This characteristic enhances the general applicability of GuidelineLLM across various LLMs. Experimental results demonstrate that GuidelineLLM can significantly reduce the attack success rate (ASR) against the LLMs (an average reduction of 34.17\% ASR) while maintaining the helpfulness of the LLMs in handling benign queries. Code is available at https://github.com/sqzhang-lazy/GuidelineLLM.

This study explores the integration of Agent AI with LangGraph to enhance real-time data analysis systems in big data environments. The proposed framework overcomes limitations of static workflows, inefficient stateful computations, and lack of human intervention by leveraging LangGraph's graph-based workflow construction and dynamic decision-making capabilities. LangGraph allows large language models (LLMs) to dynamically determine control flows, invoke tools, and assess the necessity of further actions, improving flexibility and efficiency. The system architecture incorporates Apache Spark Streaming, Kafka, and LangGraph to create a high-performance sentiment analysis system. LangGraph's capabilities include precise state management, dynamic workflow construction, and robust memory checkpointing, enabling seamless multi-turn interactions and context retention. Human-in-the-loop mechanisms are integrated to refine sentiment analysis, particularly in ambiguous or high-stakes scenarios, ensuring greater reliability and contextual relevance. Key features such as real-time state streaming, debugging via LangGraph Studio, and efficient handling of large-scale data streams make this framework ideal for adaptive decision-making. Experimental results confirm the system's ability to classify inquiries, detect sentiment trends, and escalate complex issues for manual review, demonstrating a synergistic blend of LLM capabilities and human oversight. This work presents a scalable, adaptable, and reliable solution for real-time sentiment analysis and decision-making, advancing the use of Agent AI and LangGraph in big data applications.

Automated Rule Checking (ARC) plays a crucial role in advancing the construction industry by addressing the laborious, inconsistent, and error-prone nature of traditional model review conducted by industry professionals. Manual assessment against intricate sets of rules often leads to significant project delays and expenses. In response to these challenges, ARC offers a promising solution to improve efficiency and compliance in design within the construction sector. However, the main challenge of ARC lies in translating regulatory text into a format suitable for computer processing. Current methods for rule interpretation require extensive manual labor, thereby limiting their practicality. To address this issue, our study introduces a novel approach that decomposes ARC into two distinct tasks: rule information extraction and verification code generation. Leveraging generative pre-trained transformers, our method aims to streamline the interpretation of regulatory texts and simplify the process of generating model compliance checking code. Through empirical evaluation and case studies, we showcase the effectiveness and potential of our approach in automating code compliance checking, enhancing the efficiency and reliability of construction projects.

Recent studies have demonstrated outstanding capabilities of large language models (LLMs) in software engineering domain, covering numerous tasks such as code generation and comprehension. While the benefit of LLMs for coding task is well noted, it is perceived that LLMs are vulnerable to adversarial attacks. In this paper, we study the specific LLM vulnerability to imperceptible character attacks, a type of prompt-injection attack that uses special characters to befuddle an LLM whilst keeping the attack hidden to human eyes. We devise four categories of attacks and investigate their effects on the performance outcomes of tasks relating to code analysis and code comprehension. Two generations of ChatGPT are included to evaluate the impact of advancements made to contemporary models. Our experimental design consisted of comparing perturbed and unperturbed code snippets and evaluating two performance outcomes, which are model confidence using log probabilities of response, and correctness of response. We conclude that earlier version of ChatGPT exhibits a strong negative linear correlation between the amount of perturbation and the performance outcomes, while the recent ChatGPT presents a strong negative correlation between the presence of perturbation and performance outcomes, but no valid correlational relationship between perturbation budget and performance outcomes. We anticipate this work contributes to an in-depth understanding of leveraging LLMs for coding tasks. It is suggested future research should delve into how to create LLMs that can return a correct response even if the prompt exhibits perturbations.