In this paper we argue that a jailbroken GenAI model can cause substantial harm to GenAI-powered applications and facilitate PromptWare, a new type of attack that flips the GenAI model's behavior from serving an application to attacking it. PromptWare exploits user inputs to jailbreak a GenAI model to force/perform malicious activity within the context of a GenAI-powered application. First, we introduce a naive implementation of PromptWare that behaves as malware that targets Plan & Execute architectures (a.k.a., ReAct, function calling). We show that attackers could force a desired execution flow by creating a user input that produces desired outputs given that the logic of the GenAI-powered application is known to attackers. We demonstrate the application of a DoS attack that triggers the execution of a GenAI-powered assistant to enter an infinite loop that wastes money and computational resources on redundant API calls to a GenAI engine, preventing the application from providing service to a user. Next, we introduce a more sophisticated implementation of PromptWare that we name Advanced PromptWare Threat (APwT) that targets GenAI-powered applications whose logic is unknown to attackers. We show that attackers could create user input that exploits the GenAI engine's advanced AI capabilities to launch a kill chain in inference time consisting of six steps intended to escalate privileges, analyze the application's context, identify valuable assets, reason possible malicious activities, decide on one of them, and execute it. We demonstrate the application of APwT against a GenAI-powered e-commerce chatbot and show that it can trigger the modification of SQL tables, potentially leading to unauthorized discounts on the items sold to the user.

Directly learning from examples of random difficulty levels is often challenging for both humans and machine learning models. A more effective strategy involves exposing learners to examples in a progressive order, from easy to difficult. Curriculum Learning (CL) has been proposed to implement this strategy in machine learning model training. However, two key challenges persist in CL framework design: defining the difficulty of training data and determining the appropriate amount of data to input at each training step. This paper presents a Psychology-based Unified Dynamic Framework for Curriculum Learning (PUDF), drawing inspiration from psychometrics. We quantify the difficulty of training data by applying Item Response Theory (IRT) to responses from Artificial Crowds (AC). This theory-driven IRT-AC approach leads to global (i.e., model-independent) and interpretable difficulty values. Leveraging IRT, we propose a Dynamic Data Selection via Model Ability Estimation (DDS-MAE) strategy to schedule the appropriate amount of data during model training. Since our difficulty labeling and model ability estimation are based on a consistent theory, namely IRT, their values are comparable within the same scope, potentially leading to a faster convergence compared to the other CL methods. Experimental results demonstrate that fine-tuning pre-trained language models with PUDF enhances their performance on the GLUE benchmark. Moreover, PUDF surpasses other state-of-the-art (SOTA) CL methods on the GLUE benchmark. We further explore the components of PUDF, namely the difficulty measurer (IRT-AC) and the training scheduler (DDS-MAE) qualitatively and quantitatively. Lastly, we conduct an ablation study to clarify which components of PUDF contribute to faster convergence and higher accuracy.

The Exame Nacional do Ensino M\'edio (ENEM) is a pivotal test for Brazilian students, required for admission to a significant number of universities in Brazil. The test consists of four objective high-school level tests on Math, Humanities, Natural Sciences and Languages, and one writing essay. Students' answers to the test and to the accompanying socioeconomic status questionnaire are made public every year (albeit anonymized) due to transparency policies from the Brazilian Government. In the context of large language models (LLMs), these data lend themselves nicely to comparing different groups of humans with AI, as we can have access to human and machine answer distributions. We leverage these characteristics of the ENEM dataset and compare GPT-3.5 and 4, and MariTalk, a model trained using Portuguese data, to humans, aiming to ascertain how their answers relate to real societal groups and what that may reveal about the model biases. We divide the human groups by using socioeconomic status (SES), and compare their answer distribution with LLMs for each question and for the essay. We find no significant biases when comparing LLM performance to humans on the multiple-choice Brazilian Portuguese tests, as the distance between model and human answers is mostly determined by the human accuracy. A similar conclusion is found by looking at the generated text as, when analyzing the essays, we observe that human and LLM essays differ in a few key factors, one being the choice of words where model essays were easily separable from human ones. The texts also differ syntactically, with LLM generated essays exhibiting, on average, smaller sentences and less thought units, among other differences. These results suggest that, for Brazilian Portuguese in the ENEM context, LLM outputs represent no group of humans, being significantly different from the answers from Brazilian students across all tests.

This research examines the use of Large Language Models (LLMs) in predicting time series, with a specific focus on the LLMTIME model. Despite the established effectiveness of LLMs in tasks such as text generation, language translation, and sentiment analysis, this study highlights the key challenges that large language models encounter in the context of time series prediction. We assess the performance of LLMTIME across multiple datasets and introduce classical almost periodic functions as time series to gauge its effectiveness. The empirical results indicate that while large language models can perform well in zero-shot forecasting for certain datasets, their predictive accuracy diminishes notably when confronted with diverse time series data and traditional signals. The primary finding of this study is that the predictive capacity of LLMTIME, similar to other LLMs, significantly deteriorates when dealing with time series data that contain both periodic and trend components, as well as when the signal comprises complex frequency components.

In this paper, we conduct an empirical analysis of how large language models (LLMs), specifically GPT-4, interpret constitutional principles in complex decision-making scenarios. We examine rulings from the Italian Constitutional Court on bioethics issues that involve trade-offs between competing values and compare model-generated legal arguments on these issues to those presented by the State, the Court, and the applicants. Our results indicate that GPT-4 consistently aligns more closely with progressive interpretations of the Constitution, often overlooking competing values and mirroring the applicants' views rather than the more conservative perspectives of the State or the Court's moderate positions. Our experiments reveal a distinct tendency of GPT-4 to favor progressive legal interpretations, underscoring the influence of underlying data biases. We thus underscore the importance of testing alignment in real-world scenarios and considering the implications of deploying LLMs in decision-making processes.

The electric vehicle (EV) battery supply chain's vulnerability to disruptions necessitates advanced predictive analytics. We present SHIELD (Schema-based Hierarchical Induction for EV supply chain Disruption), a system integrating Large Language Models (LLMs) with domain expertise for EV battery supply chain risk assessment. SHIELD combines: (1) LLM-driven schema learning to construct a comprehensive knowledge library, (2) a disruption analysis system utilizing fine-tuned language models for event extraction, multi-dimensional similarity matching for schema matching, and Graph Convolutional Networks (GCNs) with logical constraints for prediction, and (3) an interactive interface for visualizing results and incorporating expert feedback to enhance decision-making. Evaluated on 12,070 paragraphs from 365 sources (2022-2023), SHIELD outperforms baseline GCNs and LLM+prompt methods (e.g., GPT-4o) in disruption prediction. These results demonstrate SHIELD's effectiveness in combining LLM capabilities with domain expertise for enhanced supply chain risk assessment.

Recent advancements in Chain-of-Thoughts (CoT) and Program-of-Thoughts (PoT) methods have greatly enhanced language models' mathematical reasoning capabilities, facilitating their integration into instruction tuning datasets with LLMs. However, existing methods for large-scale dataset creation require substantial seed data and high computational costs for data synthesis, posing significant challenges for scalability. We introduce InfinityMATH, a scalable instruction tuning dataset for programmatic mathematical reasoning. The construction pipeline emphasizes decoupling numbers from mathematical problems to synthesize number-independent programs, enabling efficient and flexible scaling while minimizing dependency on specific numerical values. Fine-tuning experiments with open-source language and code models, such as Llama2 and CodeLlama, demonstrate the practical benefits of InfinityMATH. These fine-tuned models, showed significant relative improvements on both in-domain and out-of-domain benchmarks, ranging from 184.7% to 514.3% on average. Additionally, these models exhibited high robustness on the GSM8K+ and MATH+ benchmarks, which are enhanced version of test sets with simply the number variations. InfinityMATH ensures that models are more versatile and effective across a broader range of mathematical problems. The data is available at https://huggingface.co/datasets/flagopen/InfinityMATH.

Financial report generation using general purpose large language models pose two major challenges, including the lack of compound sentences and hallucinations. Advanced prompt engineering and retrieval augmented generation (RAG) techniques are incapable of curing the writing style discrepancies. In this work we propose a novel two-stage fine-tuning process wherein public domain financial reports are processed into prompt-completions and augmented using simple LLM prompts to then enable sectional financial report generation using minimal instructions and tabular data inputs. Our proposed fine-tuning framework results doubles the number of correct questions answers and reduces hallucinations by over 50%. Additionally, the two-stage fine tuned models have lower perplexity, improved ROUGE, TER and BLEU scores, higher creativity and knowledge density with lower uncertainty and cross entropy.

In this work, we discuss a recently popular type of recommender system: an LLM-based coding assistant. Connecting the task of providing code recommendations in multiple formats to traditional RecSys challenges, we outline several similarities and differences due to domain specifics. We emphasize the importance of providing relevant context to an LLM for this use case and discuss lessons learned from context enhancements & offline and online evaluation of such AI-assisted coding systems.

Software libraries play a critical role in the functionality, efficiency, and maintainability of software systems. As developers increasingly rely on Large Language Models (LLMs) to streamline their coding processes, the effectiveness of these models in recommending appropriate libraries becomes crucial yet remains largely unexplored. In this paper, we assess the effectiveness of ChatGPT as a software librarian and identify areas for improvement. We conducted an empirical study using GPT-3.5 Turbo to generate Python code for 10,000 Stack Overflow questions. Our findings show that ChatGPT uses third-party libraries nearly 10% more often than human developers, favoring widely adopted and well-established options. However, 14.2% of the recommended libraries had restrictive copyleft licenses, which were not explicitly communicated by ChatGPT. Additionally, 6.5% of the libraries did not work out of the box, leading to potential developer confusion and wasted time. While ChatGPT can be an effective software librarian, it should be improved by providing more explicit information on maintainability metrics and licensing. We recommend that developers implement rigorous dependency management practices and double-check library licenses before integrating LLM-generated code into their projects.