Agent-based simulation with a synthetic population can help us compare different treatment conditions while keeping everything else constant within the same population (i.e., as digital twins). Such population-scale simulations require large computational power (i.e., CPU resources) to get accurate estimates for treatment effects. We can use meta models of the simulation results to circumvent the need to simulate every treatment condition. Selecting the best estimating model at a given sample size (number of simulation runs) is a crucial problem. Depending on the sample size, the ability of the method to estimate accurately can change significantly. In this paper, we discuss different methods to explore what model works best at a specific sample size. In addition to the empirical results, we provide a mathematical analysis of the MSE equation and how its components decide which model to select and why a specific method behaves that way in a range of sample sizes. The analysis showed why the direction estimation method is better than model-based methods in larger sample sizes and how the between-group variation and the within-group variation affect the MSE equation.

Code Large Language Models (CodeLLM) such as CodeGen (Nijkamp et al., 2023), CodeLlama (Rozière et al., 2023), and StarCoder (Li et al., 2023) have revolutionized software development by automating tasks, reducing errors, and improving efficiency (OpenAI, 2023). Leveraging deep learning and vast code datasets (Nijkamp et al., 2023; Kocetkov et al., 2022), these models enhance developer productivity and make software development more accessible to a broader audience. Current CodeLLMs can broadly be divided into three main categories: pre-training from scratch (Li et al., 2023), pre-training from an existing LLM (Chen et al., 2021; Rozière et al., 2023), and Instruct Tuning (Luo et al., 2023). Models that are pre-trained from scratch require a substantial volume of data and considerable time (Li et al., 2023; Touvron et al., 2023). On the other hand, pre-training from an existing LLM leverages a pre-existing model as its foundation, which brings the benefits of shortened training times and improved efficiency with less data (Chen et al., 2021; Rozière et al., 2023).

The interest in updating Large Language Models (LLMs) without retraining from scratch is substantial, yet it comes with some challenges.This is especially true for situations demanding complex reasoning with limited samples, a scenario we refer to as the Paucity-Constrained Complex Reasoning Adaptation for LLMs (PCRA-LLM).Traditional methods like Low-Rank Adaptation (LoRA) and Retrieval-Augmented Generation (RAG) are inadequate for this critical issue, particularly evident in our exploration of a specific medical context that epitomize the PCRA-LLM's distinct needs.To address the issue, we propose a Sequential Fusion method to incorporate knowledge from complex context into LLMs. This method employs a two-stage framework: initially, it leverages general LLMs to construct knowledge graphs (KGs) for extracting knowledge from complex texts; subsequently, it updates the domain LLMs through knowledge edit. According to our method, the domain LLM achieved a 71.69\% accuracy in question answering tasks. Subsequently, we broadened our assessment to a novel dataset we developed in the economics and management field, where our method realized a 75\% accuracy. These outcomes underline the efficacy and adaptability of our approach for PCRA-LLM across various domains.

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges arising from the imprecision of manually crafted rules and inadequate risk perception in models without safety training. To address these, we introduce Guide-Align, a two-stage approach. Initially, a safety-trained model identifies potential risks and formulates specific guidelines for various inputs, establishing a comprehensive library of guidelines and a model for input-guidelines retrieval. Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values. An additional optional stage involves fine-tuning a model with well-aligned datasets generated through the process implemented in the second stage. Our method customizes guidelines to accommodate diverse inputs, thereby enhancing the fine-grainedness and comprehensiveness of the guideline library. Furthermore, it incorporates safety expertise from a safety-trained LLM through a lightweight retrieval model. We evaluate our approach on three benchmarks, demonstrating significant improvements in LLM security and quality. Notably, our fine-tuned model, Labrador, even at 13 billion parameters, outperforms GPT-3.5-turbo and surpasses GPT-4 in alignment capabilities.

Logical reasoning has been an ongoing pursuit in the field of AI. Despite significant advancements made by large language models (LLMs), they still struggle with complex logical reasoning problems. To enhance reasoning performance, one promising direction is scalable oversight, which requires LLMs to identify their own errors and then improve by themselves. Various self-verification methods have been proposed in pursuit of this goal. Nevertheless, whether existing models understand their own errors well is still under investigation. In this paper, we take a closer look at the self-verification abilities of LLMs in the context of logical reasoning, focusing on their ability to identify logical fallacies accurately. We introduce a dataset, FALLACIES, containing 232 types of reasoning fallacies categorized in a hierarchical taxonomy. By conducting exhaustive experiments on FALLACIES, we obtain comprehensive and detailed analyses of a series of models on their verification abilities. Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods. Drawing from these observations, we offer suggestions for future research and practical applications of self-verification methods.

Probabilistic world models increase data efficiency of model-based reinforcement learning (MBRL) by guiding the policy with their epistemic uncertainty to improve exploration and acquire new samples. Moreover, the uncertainty-aware learning procedures in probabilistic approaches lead to robust policies that are less sensitive to noisy observations compared to uncertainty unaware solutions. We propose to combine trajectory sampling and deep Gaussian covariance network (DGCN) for a data-efficient solution to MBRL problems in an optimal control setting. We compare trajectory sampling with density-based approximation for uncertainty propagation using three different probabilistic world models; Gaussian processes, Bayesian neural networks, and DGCNs. We provide empirical evidence using four different well-known test environments, that our method improves the sample-efficiency over other combinations of uncertainty propagation methods and probabilistic models. During our tests, we place particular emphasis on the robustness of the learned policies with respect to noisy initial states.

Behavior-driven development (BDD) is an Agile testing methodology fostering collaboration among developers, QA analysts, and stakeholders. In this manuscript, we propose a novel approach to enhance BDD practices using large language models (LLMs) to automate acceptance test generation. Our study uses zero and few-shot prompts to evaluate LLMs such as GPT-3.5, GPT-4, Llama-2-13B, and PaLM-2. The paper presents a detailed methodology that includes the dataset, prompt techniques, LLMs, and the evaluation process. The results demonstrate that GPT-3.5 and GPT-4 generate error-free BDD acceptance tests with better performance. The few-shot prompt technique highlights its ability to provide higher accuracy by incorporating examples for in-context learning. Furthermore, the study examines syntax errors, validation accuracy, and comparative analysis of LLMs, revealing their effectiveness in enhancing BDD practices. However, our study acknowledges that there are limitations to the proposed approach. We emphasize that this approach can support collaborative BDD processes and create opportunities for future research into automated BDD acceptance test generation using LLMs.

The rapid advancement of artificial intelligence (AI) and the expanding integration of large language models (LLMs) have ignited a debate about their application in education. This study delves into university instructors' experiences and attitudes toward AI language models, filling a gap in the literature by analyzing educators' perspectives on AI's role in the classroom and its potential impacts on teaching and learning. The objective of this research is to investigate the level of awareness, overall sentiment towardsadoption, and the factors influencing these attitudes for LLMs and generative AI-based tools in higher education. Data was collected through a survey using a Likert scale, which was complemented by follow-up interviews to gain a more nuanced understanding of the instructors' viewpoints. The collected data was processed using statistical and thematic analysis techniques. Our findings reveal that educators are increasingly aware of and generally positive towards these tools. We find no correlation between teaching style and attitude toward generative AI. Finally, while CS educators show far more confidence in their technical understanding of generative AI tools and more positivity towards them than educators in other fields, they show no more confidence in their ability to detect AI-generated work.

Large Language Models (LLMs) have achieved impressive performance across various reasoning tasks. However, even state-of-the-art LLMs such as ChatGPT are prone to logical errors during their reasoning processes. Existing solutions, such as deploying task-specific verifiers or voting over multiple reasoning paths, either require extensive human annotations or fail in scenarios with inconsistent responses. To address these challenges, we introduce RankPrompt, a new prompting method that enables LLMs to self-rank their responses without additional resources. RankPrompt breaks down the ranking problem into a series of comparisons among diverse responses, leveraging the inherent capabilities of LLMs to generate chains of comparison as contextual exemplars. Our experiments across 11 arithmetic and commonsense reasoning tasks show that RankPrompt significantly enhances the reasoning performance of ChatGPT and GPT-4, with improvements of up to 13%. Moreover, RankPrompt excels in LLM-based automatic evaluations for open-ended tasks, aligning with human judgments 74% of the time in the AlpacaEval dataset. It also exhibits robustness to variations in response order and consistency. Collectively, our results validate RankPrompt as an effective method for eliciting high-quality feedback from language models.

Prior research has found that differences in the early period of neural network training significantly impact the performance of in-distribution (ID) tasks. However, neural networks are often sensitive to out-of-distribution (OOD) data, making them less reliable in downstream applications. Yet, the impact of the early training period on OOD generalization remains understudied due to its complexity and lack of effective analytical methodologies. In this work, we investigate the relationship between learning dynamics and OOD generalization during the early period of neural network training. We utilize the trace of Fisher Information and sharpness, with a focus on gradual unfreezing (i.e. progressively unfreezing parameters during training) as the methodology for investigation. Through a series of empirical experiments, we show that 1) selecting the number of trainable parameters at different times during training, i.e. realized by gradual unfreezing -- has a minuscule impact on ID results, but greatly affects the generalization to OOD data; 2) the absolute values of sharpness and trace of Fisher Information at the initial period of training are not indicative for OOD generalization, but the relative values could be; 3) the trace of Fisher Information and sharpness may be used as indicators for the removal of interventions during early period of training for better OOD generalization.