Natural language prompt optimization, or prompt engineering, has emerged as a powerful technique to unlock the potential of Large Language Models (LLMs) for various tasks. While existing methods primarily focus on maximizing a single task-specific performance metric for LLM outputs, real-world applications often require considering trade-offs between multiple objectives. In this work, we address this limitation by proposing an effective technique for multi-objective prompt optimization for LLMs. Specifically, we propose **ParetoPrompt**, a reinforcement learning~(RL) method that leverages dominance relationships between prompts to derive a policy model for prompts optimization using preference-based loss functions. By leveraging multi-objective dominance relationships, ParetoPrompt enables efficient exploration of the entire Pareto front without the need for a predefined scalarization of multiple objectives. Our experimental results show that ParetoPrompt consistently outperforms existing algorithms that use specific objective values. ParetoPrompt also yields robust performances when the objective metrics differ between training and testing.

There are various sources of ionizing radiation exposure, where medical exposure for radiation therapy or diagnosis is the most common human-made source. Understanding how gene expression is modulated after ionizing radiation exposure and investigating the presence of any dose-dependent gene expression patterns have broad implications for health risks from radiotherapy, medical radiation diagnostic procedures, as well as other environmental exposure. In this paper, we perform a comprehensive pathway-based analysis of gene expression profiles in response to low-dose radiation exposure, in order to examine the potential mechanism of gene regulation underlying such responses. To accomplish this goal, we employ a statistical framework to determine whether a specific group of genes belonging to a known pathway display coordinated expression patterns that are modulated in a manner consistent with the radiation level. Findings in our study suggest that there exist complex yet consistent signatures that reflect the molecular response to radiation exposure, which differ between low-dose and high-dose radiation.

Because protein-protein interactions (PPIs) are crucial to understand living systems, harvesting these data is essential to probe disease development and discern gene/protein functions and biological processes. Some curated datasets contain PPI data derived from the literature and other sources (e.g., IntAct, BioGrid, DIP, and HPRD). However, they are far from exhaustive, and their maintenance is a labor-intensive process. On the other hand, machine learning methods to automate PPI knowledge extraction from the scientific literature have been limited by a shortage of appropriate annotated data. This work presents a unified, multi-source PPI corpora with vetted interaction definitions augmented by binary interaction type labels and a Transformer-based deep learning method that exploits entities’ relational context information for relation representation to improve relation classification performance. The model’s performance is evaluated on four widely studied biomedical relation extraction datasets, as well as this work’s target PPI datasets, to observe the effectiveness of the representation to relation extraction tasks in various data. Results show the model outperforms prior state-of-the-art models. The code and data are available at: https://github.com/BNLNLP/PPI-Relation-Extraction

Detection of phishing emails is a topic that received a lot of attention both from academia and industry due to the devastating effects of phishing enabled data breaches have on private individual and companies. While the accuracy of phishing detection reported in the papers is impressive, the damage from the attacks continues to grow every year. One of the reasons is the diversity of attacks, especially within spear phishing and whaling. Another reason is that the natural language part of the detectors is usually devoid of semantics. In this paper we present an approach that adds semantics to highly accurate bag of words and part of speech approaches. We show that while the current approach is less accurate as a starting point, it retains its accuracy as a corpus deviates from training, while the accuracy of the original approach decreases with the amount of deviations.

This paper compares the results of computer and human efforts to determine whether an email is legitimate or a phishing attempt. For this purpose, we have run two series of experiments, one for the computer and the other for human subjects. Both experiments addressed the same corpora, one of phishing emails, and the other of legitimate ones. Both the computer and human subjects were asked to detect which emails were phishing and which were legitimate. The results are interesting, both separately and in comparison. Even at this limited, non-semantic state of computation, they indicate that human and computer competences should complement each other, and that, of course, will lead to the integration of human-accessible semantics into computation.