Learning performance data (e.g., quiz scores and attempts) is significant for understanding learner engagement and knowledge mastery level. However, the learning performance data collected from Intelligent Tutoring Systems (ITSs) often suffers from sparsity, impacting the accuracy of learner modeling and knowledge assessments. To address this, we introduce the 3DG framework (3-Dimensional tensor for Densification and Generation), a novel approach combining tensor factorization with advanced generative models, including Generative Adversarial Network (GAN) and Generative Pre-trained Transformer (GPT), for enhanced data imputation and augmentation. The framework operates by first representing the data as a three-dimensional tensor, capturing dimensions of learners, questions, and attempts. It then densifies the data through tensor factorization and augments it using Generative AI models, tailored to individual learning patterns identified via clustering. Applied to data from an AutoTutor lesson by the Center for the Study of Adult Literacy (CSAL), the 3DG framework effectively generated scalable, personalized simulations of learning performance. Comparative analysis revealed GAN's superior reliability over GPT-4 in this context, underscoring its potential in addressing data sparsity challenges in ITSs and contributing to the advancement of personalized educational technology.

This report examines a novel risk associated with current (and projected) AI tools. Making effective decisions about future actions requires us to reason under uncertainty (RUU), and doing so is essential to many critical real world problems. Overfaced by this challenge, there is growing demand for AI tools like LLMs to assist decision-makers. Having evidenced this demand and the incentives behind it, we expose a growing risk: we 1) do not currently sufficiently understand LLM capabilities in this regard, and 2) have no guarantees of performance given fundamental computational explosiveness and deep uncertainty constraints on accuracy. This report provides an exposition of what makes RUU so challenging for both humans and machines, and relates these difficulties to prospective AI timelines and capabilities. Having established this current potential misuse risk, we go on to expose how this seemingly additive risk (more misuse additively contributed to potential harm) in fact has multiplicative properties. Specifically, we detail how this misuse risk connects to a wider network of underlying structural risks (e.g., shifting incentives, limited transparency, and feedback loops) to produce non-linear harms. We go on to provide a solutions roadmap that targets multiple leverage points in the structure of the problem. This includes recommendations for all involved actors (prospective users, developers, and policy-makers) and enfolds insights from areas including Decision-making Under Deep Uncertainty and complex systems theory. We argue this report serves not only to raise awareness (and subsequently mitigate/correct) of a current, novel AI risk, but also awareness of the underlying class of structural risks by illustrating how their interconnected nature poses twin-dangers of camouflaging their presence, whilst amplifying their potential effects.

Generative AI and LLMs in particular are heavily used nowadays for various document processing tasks such as question answering and summarization. However, different LLMs come with different capabilities for different tasks as well as with different costs, tokenization, and latency. In fact, enterprises are already incurring huge costs of operating or using LLMs for their respective use cases. In this work, we propose optimizing the usage costs of LLMs by estimating their output quality (without actually invoking the LLMs), and then solving an optimization routine for the LLM selection to either keep costs under a budget, or minimize the costs, in a quality and latency aware manner. We propose a model to predict the output quality of LLMs on document processing tasks like summarization, followed by an LP rounding algorithm to optimize the selection of LLMs. We study optimization problems trading off the quality and costs, both theoretically and empirically. We further propose a sentence simplification model for reducing the number of tokens in a controlled manner. Additionally, we propose several deterministic heuristics for reducing tokens in a quality aware manner, and study the related optimization problem of applying the heuristics optimizing the quality and cost trade-off. We perform extensive empirical validation of our methods on not only enterprise datasets but also on open-source datasets, annotated by us, and show that we perform much better compared to closest baselines. Our methods reduce costs by 40%- 90% while improving quality by 4%-7%. We will release the annotated open source datasets to the community for further research and exploration.

Large Language Models (LLMs) like gpt-3.5-turbo and claude-instant-1.2 have become instrumental in interpreting and executing semantic-based tasks. Unfortunately, these models' inherent biases, akin to human cognitive biases, adversely affect their performance. Particularly affected is object selection from lists; a fundamental operation in digital navigation and decision-making. This research critically examines these biases and quantifies the effects on a representative list selection task. To explore these biases, we conducted a series of controlled experiments, manipulating temperature, list length, object identity, object type, prompt complexity, and model. This enabled us to isolate and measure the influence of the biases on selection behavior. Our findings show that bias structure is strongly dependent on the model, with object type modulating the magnitude of the effect. With a strong primacy effect, causing the first objects in a list to be disproprotionately represented in outputs. Furthermore the usage of guard rails, a prompt engineering method of ensuring a response structure, can increase bias and decrease instruction adherence when combined with a selection task. The bias is ablated when the guard rail step is separated from the list sampling step, lowering the complexity of each individual task. The implications of this research are two-fold, practically providing a guide for designing unbiased LLM applications and theoretically suggesting that LLMs experience a form of cognitive load compensated for by increasing bias.

To help the open-source community have a better understanding of Mixture-of-Experts (MoE) based large language models (LLMs), we train and release OpenMoE, a series of fully open-sourced and reproducible decoder-only MoE LLMs, ranging from 650M to 34B parameters and trained on up to over 1T tokens. Our investigation confirms that MoE-based LLMs can offer a more favorable cost-effectiveness trade-off than dense LLMs, highlighting the potential effectiveness for future LLM development. One more important contribution of this study is an in-depth analysis of the routing mechanisms within our OpenMoE models, leading to three significant findings: Context-Independent Specialization, Early Routing Learning, and Drop-towards-the-End. We discovered that routing decisions in MoE models are predominantly based on token IDs, with minimal context relevance. The token-to-expert assignments are determined early in the pre-training phase and remain largely unchanged. This imperfect routing can result in performance degradation, particularly in sequential tasks like multi-turn conversations, where tokens appearing later in a sequence are more likely to be dropped. Finally, we rethink our design based on the above-mentioned observations and analysis. To facilitate future MoE LLM development, we propose potential strategies for mitigating the issues we found and further improving off-the-shelf MoE LLM designs.

Quantum computing is a growing field that promises many real-world applications such as quantum cryptography or quantum finance. The number of people able to use quantum computing is however still very small. This limitation comes from the difficulty to understand the concepts and to know how to start coding. Therefore, there is a need for tools that can assist non-expert in overcoming this complexity. One possibility would be to use existing conversational agents. Unfortunately ChatGPT and other Large-Language Models produce inaccurate results. This article presents C4Q, a chatbot that answers accurately basic questions and guides users when trying to code quantum programs. Contrary to other approaches C4Q uses a pre-trained large language model only to discover and classify user requests. It then generates an accurate answer using an own engine. Thanks to this architectural design, C4Q's answers are always correct, and thus C4Q can become a support tool that makes quantum computing more available to non-experts.

In this work, we aim to develop LLM agents to mitigate social norm violations in negotiations in a multi-agent setting. We simulate real-world negotiations by letting two large Language Models (LLMs) play the roles of two negotiators in each conversation. A third LLM acts as a remediation agent to rewrite utterances violating norms for improving negotiation outcomes. As it is a novel task, no manually constructed data is available. To address this limitation, we introduce a value impact based In-Context Learning (ICL) method to identify high-quality ICL examples for the LLM-based remediation agents, where the value impact function measures the quality of negotiation outcomes. We show the connection of this method to policy learning and provide rich empirical evidence to demonstrate its effectiveness in negotiations across three different topics: product sale, housing price, and salary negotiation. The source code and the generated dataset will be publicly available upon acceptance.

In today's globalized world, bridging the cultural divide is more critical than ever for forging meaningful connections. The Socially-Aware Dialogue Assistant System (SADAS) is our answer to this global challenge, and it's designed to ensure that conversations between individuals from diverse cultural backgrounds unfold with respect and understanding. Our system's novel architecture includes: (1) identifying the categories of norms present in the dialogue, (2) detecting potential norm violations, (3) evaluating the severity of these violations, (4) implementing targeted remedies to rectify the breaches, and (5) articulates the rationale behind these corrective actions. We employ a series of State-Of-The-Art (SOTA) techniques to build different modules, and conduct numerous experiments to select the most suitable backbone model for each of the modules. We also design a human preference experiment to validate the overall performance of the system. We will open-source our system (including source code, tools and applications), hoping to advance future research. A demo video of our system can be found at:~\url{https://youtu.be/JqetWkfsejk}. We have released our code and software at:~\url{https://github.com/AnonymousEACLDemo/SADAS}.

Purpose: Large Language Models (LLMs) hold significant promise for medical applications. Retrieval Augmented Generation (RAG) emerges as a promising approach for customizing domain knowledge in LLMs. This case study presents the development and evaluation of an LLM-RAG pipeline tailored for healthcare, focusing specifically on preoperative medicine. Methods: We developed an LLM-RAG model using 35 preoperative guidelines and tested it against human-generated responses, with a total of 1260 responses evaluated. The RAG process involved converting clinical documents into text using Python-based frameworks like LangChain and Llamaindex, and processing these texts into chunks for embedding and retrieval. Vector storage techniques and selected embedding models to optimize data retrieval, using Pinecone for vector storage with a dimensionality of 1536 and cosine similarity for loss metrics. Human-generated answers, provided by junior doctors, were used as a comparison. Results: The LLM-RAG model generated answers within an average of 15-20 seconds, significantly faster than the 10 minutes typically required by humans. Among the basic LLMs, GPT4.0 exhibited the best accuracy of 80.1%. This accuracy was further increased to 91.4% when the model was enhanced with RAG. Compared to the human-generated instructions, which had an accuracy of 86.3%, the performance of the GPT4.0 RAG model demonstrated non-inferiority (p=0.610). Conclusions: In this case study, we demonstrated a LLM-RAG model for healthcare implementation. The pipeline shows the advantages of grounded knowledge, upgradability, and scalability as important aspects of healthcare LLM deployment.

Large Language Models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and question-answering. Nowadays, LLM is becoming a very popular tool in computerized language processing tasks, with the capability to analyze complicated linguistic patterns and provide relevant and appropriate responses depending on the context. While offering significant advantages, these models are also vulnerable to security and privacy attacks, such as jailbreaking attacks, data poisoning attacks, and Personally Identifiable Information (PII) leakage attacks. This survey provides a thorough review of the security and privacy challenges of LLMs for both training data and users, along with the application-based risks in various domains, such as transportation, education, and healthcare. We assess the extent of LLM vulnerabilities, investigate emerging security and privacy attacks for LLMs, and review the potential defense mechanisms. Additionally, the survey outlines existing research gaps in this domain and highlights future research directions.