In the contemporary digital landscape, media content stands as the foundation for political news analysis, offering invaluable insights sourced from various channels like news articles, social media updates, speeches, and reports. Natural Language Processing (NLP) has revolutionized Political Information Extraction (IE), automating tasks such as Event Extraction (EE) from these diverse media outlets. While traditional NLP methods often necessitate specialized expertise to build rule-based systems or train machine learning models with domain-specific datasets, the emergence of Large Language Models (LLMs) driven by Generative Artificial Intelligence (GenAI) presents a promising alternative. These models offer accessibility, alleviating challenges associated with model construction from scratch and reducing the dependency on extensive datasets during the training phase, thus facilitating rapid implementation. However, challenges persist in handling domain-specific tasks, leading to the development of the Retrieval-Augmented Generation (RAG) framework. RAG enhances LLMs by integrating external data retrieval, enriching their contextual understanding, and expanding their knowledge base beyond pre-existing training data. To illustrate RAG's efficacy, we introduce the Political EE system, specifically tailored to extract political event information from news articles. Understanding these political insights is essential for remaining informed about the latest political advancements, whether on a national or global scale.

Businesses heavily rely on data sourced from various channels like news articles, financial reports, and consumer reviews to drive their operations, enabling informed decision-making and identifying opportunities. However, traditional manual methods for data extraction are often time-consuming and resource-intensive, prompting the adoption of digital transformation initiatives to enhance efficiency. Yet, concerns persist regarding the sustainability of such initiatives and their alignment with the United Nations (UN)'s Sustainable Development Goals (SDGs). This research aims to explore the integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) as a sustainable solution for Information Extraction (IE) and processing. The research methodology involves reviewing existing solutions for business decision-making, noting that many systems require training new machine learning models, which are resource-intensive and have significant environmental impacts. Instead, we propose a sustainable business solution using pre-existing LLMs that can work with diverse datasets. We link domain-specific datasets to tailor LLMs to company needs and employ a Multi-Agent architecture to divide tasks such as information retrieval, enrichment, and classification among specialized agents. This approach optimizes the extraction process and improves overall efficiency. Through the utilization of these technologies, businesses can optimize resource utilization, improve decision-making processes, and contribute to sustainable development goals, thereby fostering environmental responsibility within the corporate sector.

AI humanizers are a new class of online software tools meant to paraphrase and rewrite AI-generated text in a way that allows them to evade AI detection software. We study 19 AI humanizer and paraphrasing tools and qualitatively assess their effects and faithfulness in preserving the meaning of the original text. We show that many existing AI detectors fail to detect humanized text. Finally, we demonstrate a robust model that can detect humanized AI text while maintaining a low false positive rate using a data-centric augmentation approach. We attack our own detector, training our own fine-tuned model optimized against our detector's predictions, and show that our detector's cross-humanizer generalization is sufficient to remain robust to this attack.

Software testing is a crucial but time-consuming aspect of software development, and recently, Large Language Models (LLMs) have gained popularity for automated test case generation. However, because LLMs are trained on vast amounts of open-source code, they often generate test cases that do not adhere to best practices and may even contain test smells (anti-patterns). To address this issue, we propose Reinforcement Learning from Static Quality Metrics (RLSQM), wherein we utilize Reinforcement Learning to generate high-quality unit tests based on static analysis-based quality metrics. First, we analyzed LLM-generated tests and show that LLMs frequently do generate undesirable test smells -- up to 37% of the time. Then, we implemented lightweight static analysis-based reward model and trained LLMs using this reward model to optimize for five code quality metrics. Our experimental results demonstrate that the RL-optimized Codex model consistently generated higher-quality test cases than the base LLM, improving quality metrics by up to 23%, and generated nearly 100% syntactically-correct code. RLSQM also outperformed GPT-4 on all code quality metrics, in spite of training a substantially cheaper Codex model. We provide insights into how reliably utilize RL to improve test generation quality and show that RLSQM is a significant step towards enhancing the overall efficiency and reliability of automated software testing. Our data are available at https://doi.org/10.6084/m9.figshare.25983166.

Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, directly collecting human preferences can be expensive, time-consuming, and can have high variance. An appealing alternative is to distill preferences from LMs as a source of synthetic annotations as they are more consistent, cheaper, and scale better than human annotation; however, they are also prone to biases and errors. In this work, we introduce a routing framework that combines inputs from humans and LMs to achieve better annotation quality, while reducing the total cost of human annotation. The crux of our approach is to identify preference instances that will benefit from human annotations. We formulate this as an optimization problem: given a preference dataset and an evaluation metric, we train a performance prediction model to predict a reward model's performance on an arbitrary combination of human and LM annotations and employ a routing strategy that selects a combination that maximizes predicted performance. We train the performance prediction model on MultiPref, a new preference dataset with 10K instances paired with human and LM labels. We show that the selected hybrid mixture of LM and direct human preferences using our routing framework achieves better reward model performance compared to using either one exclusively. We simulate selective human preference collection on three other datasets and show that our method generalizes well to all three. We analyze features from the routing model to identify characteristics of instances that can benefit from human feedback, e.g., prompts with a moderate safety concern or moderate intent complexity. We release the dataset, annotation platform, and source code used in this study to foster more efficient and accurate preference collection in the future.

Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks, quickly becoming one of the most prevalent AI workloads. Yet the substantial memory requirement of LLMs significantly hinders their deployment for end users. Post-training quantization (PTQ) serves as one of the most hardware-efficient methods to mitigate the memory and computational demands of LLMs. Although the traditional integer (INT) datatype has received widespread adoption in PTQ methods, floating-point (FP) quantization has emerged as a viable alternative thanks to its effectiveness in fitting LLM numerical distributions. However, the FP datatype in sign-magnitude binary representation contains both positive and negative zero, which constrains its representation capability, particularly under low precision (3 and 4 bits). In this paper, we extend the basic FP datatype to perform Redundant Zero Remapping (RaZeR), which remaps the negative zero FP encoding to a set of pre-defined special values to maximally utilize FP quantization encodings and to better fit LLM numerical distributions. Through careful selection of special values, RaZeR outperforms conventional asymmetric INT quantization while achieving high computational efficiency. We demonstrate that RaZeR can be seamlessly integrated with quantization algorithms for both weights and KV-cache, including advanced methods with clipping and transformations, and consistently achieve better model accuracy. Additionally, we implement a fast GEMV kernel with fused dequantization that efficiently converts the 4-bit RaZeR value to FP16 through novel bit-level manipulation. On modern GPUs, our evaluation shows that RaZeR improves the GEMV speed by up to 7.56$\times$ compared to the FP16 implementation, while achieving up to 2.72$\times$ speedup in the LLM decoding throughput.

Designing effective prompts is essential to guiding large language models (LLMs) toward desired responses. Automated prompt engineering aims to reduce reliance on manual effort by streamlining the design, refinement, and optimization of natural language prompts. This paper proposes an optimal learning framework for automated prompt engineering, designed to sequentially identify effective prompt features while efficiently allocating a limited evaluation budget. We introduce a feature-based method to express prompts, which significantly broadens the search space. Bayesian regression is employed to utilize correlations among similar prompts, accelerating the learning process. To efficiently explore the large space of prompt features for a high quality prompt, we adopt the forward-looking Knowledge-Gradient (KG) policy for sequential optimal learning. The KG policy is computed efficiently by solving mixed-integer second-order cone optimization problems, making it scalable and capable of accommodating prompts characterized only through constraints. We demonstrate that our method significantly outperforms a set of benchmark strategies assessed on instruction induction tasks. The results highlight the advantages of using the KG policy for prompt learning given a limited evaluation budget. Our framework provides a solution to deploying automated prompt engineering in a wider range applications where prompt evaluation is costly.

This paper evaluates questions generated by LLMs from context, comparing them to human-generated questions across six dimensions. We introduce an automated LLM-based evaluation method, focusing on aspects like question length, type, context coverage, and answerability. Our findings highlight unique characteristics of LLM-generated questions, contributing insights that can support further research in question quality and downstream applications.

The alignment of large language models (LLMs) with human values is critical as these models become increasingly integrated into various societal and decision-making processes. Traditional methods, such as reinforcement learning from human feedback (RLHF), achieve alignment by fine-tuning model parameters, but these approaches are often computationally expensive and impractical when models are frozen or inaccessible for parameter modification. In contrast, prompt optimization is a viable alternative to RLHF for LLM alignment. While the existing literature has shown empirical promise of prompt optimization, its theoretical underpinning remains under-explored. We address this gap by formulating prompt optimization as an optimization problem and try to provide theoretical insights into the optimality of such a framework. To analyze the performance of the prompt optimization, we study theoretical suboptimality bounds and provide insights in terms of how prompt optimization depends upon the given prompter and target model. We also provide empirical validation through experiments on various datasets, demonstrating that prompt optimization can effectively align LLMs, even when parameter fine-tuning is not feasible.

Retrieval-augmented generation (RAG) has recently become a very popular task for Large Language Models (LLMs). Evaluating them on multi-turn RAG conversations, where the system is asked to generate a response to a question in the context of a preceding conversation is an important and often overlooked task with several additional challenges. We present MTRAG: an end-to-end human-generated multi-turn RAG benchmark that reflects several real-world properties across diverse dimensions for evaluating the full RAG pipeline. MTRAG contains 110 conversations averaging 7.7 turns each across four domains for a total of 842 tasks. We also explore automation paths via synthetic data and LLM-as-a-Judge evaluation. Our human and automatic evaluations show that even state-of-the-art LLM RAG systems struggle on MTRAG. We demonstrate the need for strong retrieval and generation systems that can handle later turns, unanswerable questions, non-standalone questions, and multiple domains. MTRAG is available at https://github.com/ibm/mt-rag-benchmark.