As generative AI ('GenAI') continues to evolve, educators face the challenge of preparing students for a future where AI-assisted work is integral to professional success. This paper introduces ChatISA, an in-house, multi-model AI chatbot designed to support students and faculty in an Information Systems and Analytics (ISA) department. ChatISA comprises four primary modules: Coding Companion, Project Coach, Exam Ally, and Interview Mentor, each tailored to enhance different aspects of the educational experience. Through iterative development, student feedback, and leveraging open-source frameworks, we created a robust tool that addresses coding inquiries, project management, exam preparation, and interview readiness. The implementation of ChatISA provided valuable insights and highlighted key challenges. Our findings demonstrate the benefits of ChatISA for ISA education while underscoring the need for adaptive pedagogy and proactive engagement with AI tools to fully harness their educational potential. To support broader adoption and innovation, all code for ChatISA is made publicly available on GitHub, enabling other institutions to customize and integrate similar AI-driven educational tools within their curricula.
In this paper, we introduce MoRSE (Mixture of RAGs Security Experts), the first specialised AI chatbot for cybersecurity. MoRSE aims to provide comprehensive and complete knowledge about cybersecurity. MoRSE uses two RAG (Retrieval Augmented Generation) systems designed to retrieve and organize information from multidimensional cybersecurity contexts. MoRSE differs from traditional RAGs by using parallel retrievers that work together to retrieve semantically related information in different formats and structures. Unlike traditional Large Language Models (LLMs) that rely on Parametric Knowledge Bases, MoRSE retrieves relevant documents from Non-Parametric Knowledge Bases in response to user queries. Subsequently, MoRSE uses this information to generate accurate answers. In addition, MoRSE benefits from real-time updates to its knowledge bases, enabling continuous knowledge enrichment without retraining. We have evaluated the effectiveness of MoRSE against other state-of-the-art LLMs, evaluating the system on 600 cybersecurity specific questions. The experimental evaluation has shown that the improvement in terms of relevance and correctness of the answer is more than 10\% compared to known solutions such as GPT-4 and Mixtral 7x8.
This research introduces an innovative mathematical learning approach that integrates generative AI to cultivate a structured learning rather than quick solution. Our method combines chatbot capabilities and generative AI to offer interactive problem-solving exercises, enhancing learning through a stepby-step approach for varied problems, advocating for the responsible use of AI in education. Our approach emphasizes that immediate answers from ChatGPT can impede real learning. We introduce a reward-based system that requires students to solve mathematical problems effectively to receive the final answer. This encourages a progressive learning path from basic to complex problems, rewarding mastery with final solutions. The goal is to transition students from seeking quick fixes to engaging actively in a comprehensive learning experience.
This paper illustrates the architecture and training of Unipa-GPT, a chatbot relying on a Large Language Model, developed for assisting students in choosing a bachelor/master degree course at the University of Palermo. Unipa-GPT relies on gpt-3.5-turbo, it was presented in the context of the European Researchers' Night (SHARPER night). In our experiments we adopted both the Retrieval Augmented Generation (RAG) approach and fine-tuning to develop the system. The whole architecture of Unipa-GPT is presented, both the RAG and the fine-tuned systems are compared, and a brief discussion on their performance is reported. Further comparison with other Large Language Models and the experimental results during the SHARPER night are illustrated. Corpora and code are available on GitHub
This study consists of qualitative empirical research, conducted through exploratory tests with two different Large Language Models (LLMs) chatbots: ChatGPT and Gemini. The methodological procedure involved exploratory tests based on prompts designed with a probability question. The "Linda Problem", widely recognized in cognitive psychology, was used as a basis to create the tests, along with the development of a new problem specifically for this experiment, the "Mary Problem". The object of analysis is the dataset with the outputs provided by each chatbot interaction. The purpose of the analysis is to verify whether the chatbots mainly employ logical reasoning that aligns with probability theory or if they are more frequently affected by the stereotypical textual descriptions in the prompts. The findings provide insights about the approach each chatbot employs in handling logic and textual constructions, suggesting that, while the analyzed chatbots perform satisfactorily on a well-known probabilistic problem, they exhibit significantly lower performance on new tests that require direct application of probabilistic logic.
Large Language Models (LLMs) have emerged as a potential solution to assist digital health development with patient education, commonly medication-related enquires. We trained and validated Med-Pal, a medication domain-specific LLM-chatbot fine-tuned with a fine-grained and expert curated dataset from a selection of five light-weighted open-source LLMs of smaller parameter size (7 billion or less) regarding computational constraints and prioritizing operational efficiency. A multi-disciplinary team performed a clinical evaluation of LLMs responses using the SCORE criteria, focusing on safety, accuracy, bias, reproducibility, and ease of understanding. Best performing light-weighted LLM was chosen as Med-Pal for further engineering with guard-railing using adversarial prompting. Med-Pal and existing light-weighted LLMs, including pretrained Biomistral and finetuned Meerkat, were validated on an independent dataset on a broad range of medication-related questions (231 in total), 12 different question types across 14 different medication classes. Mistral-7b emerged as the top performer among selected lightweight LLMs, achieving the highest median score of 14 and 71.9% high-quality responses in accuracy and safety domains, hence chosen as the backbone LLM for Med-Pal. When compared against Biomistral, Med-pal outperformed in generating responses appropriate for patient communication, with significant reductions bias and errors typical of general LLMs. Comparable performance was observed when comparing Med-Pal with Meerkat. Med-Pal showcases the feasibility of developing and employing fine-tuned light-weighted LLMs to enhance digital health communications.
Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy and facilitate privacy research for large language models (LLMs). We run an extensive, fine-grained analysis on the personal disclosures made by real users to commercial GPT models, investigating the leakage of personally identifiable and sensitive information. To understand the contexts in which users disclose to chatbots, we develop a taxonomy of tasks and sensitive topics, based on qualitative and quantitative analysis of naturally occurring conversations. We discuss these potential privacy harms and observe that: (1) personally identifiable information (PII) appears in unexpected contexts such as in translation or code editing (48% and 16% of the time, respectively) and (2) PII detection alone is insufficient to capture the sensitive topics that are common in human-chatbot interactions, such as detailed sexual preferences or specific drug use habits. We believe that these high disclosure rates are of significant importance for researchers and data curators, and we call for the design of appropriate nudging mechanisms to help users moderate their interactions.
The Tourism and Destination Management Organization (DMO) industry is rapidly evolving to adapt to new technologies and traveler expectations. Generative Artificial Intelligence (AI) offers an astonishing and innovative opportunity to enhance the tourism experience by providing personalized, interactive and engaging assistance. In this article, we propose a generative AI-based chatbot for tourism assistance. The chatbot leverages AI ability to generate realistic and creative texts, adopting the friendly persona of the well-known Italian all-knowledgeable aunties, to provide tourists with personalized information, tailored and dynamic pre, during and post recommendations and trip plans and personalized itineraries, using both text and voice commands, and supporting different languages to satisfy Italian and foreign tourists expectations. This work is under development in the Molise CTE research project, funded by the Italian Minister of the Economic Growth (MIMIT), with the aim to leverage the best emerging technologies available, such as Cloud and AI to produce state of the art solutions in the Smart City environment.
Sustaining long-term user engagement with mobile health (mHealth) interventions while preserving their high efficacy remains an ongoing challenge in real-world well-being applications. To address this issue, we introduce a new algorithm, the Personalized, Context-Aware Recommender (PCAR), for intervention selection and evaluate its performance in a field experiment. In a four-week, in-the-wild experiment involving 29 parents of young children, we delivered personalized stress-reducing micro-interventions through a mobile chatbot. We assessed their impact on stress reduction using momentary stress level ecological momentary assessments (EMAs) before and after each intervention. Our findings demonstrate the superiority of PCAR intervention selection in enhancing the engagement and efficacy of mHealth micro-interventions to stress coping compared to random intervention selection and a control group that did not receive any intervention. Furthermore, we show that even brief, one-minute interventions can significantly reduce perceived stress levels (p=0.001). We observe that individuals are most receptive to one-minute interventions during transitional periods between activities, such as transitioning from afternoon activities to bedtime routines. Our study contributes to the literature by introducing a personalized context-aware intervention selection algorithm that improves engagement and efficacy of mHealth interventions, identifying key timing for stress interventions, and offering insights into mechanisms to improve stress coping.
Transformer-based chatbots can conduct fluent, natural-sounding conversations, but we have limited understanding of the mechanisms underlying their behavior. Prior work has taken a bottom-up approach to understanding Transformers by constructing Transformers for various synthetic and formal language tasks, such as regular expressions and Dyck languages. However, it is not obvious how to extend this approach to understand more naturalistic conversational agents. In this work, we take a step in this direction by constructing a Transformer that implements the ELIZA program, a classic, rule-based chatbot. ELIZA illustrates some of the distinctive challenges of the conversational setting, including both local pattern matching and long-term dialog state tracking. We build on constructions from prior work -- in particular, for simulating finite-state automata -- showing how simpler constructions can be composed and extended to give rise to more sophisticated behavior. Next, we train Transformers on a dataset of synthetically generated ELIZA conversations and investigate the mechanisms the models learn. Our analysis illustrates the kinds of mechanisms these models tend to prefer -- for example, models favor an induction head mechanism over a more precise, position based copying mechanism; and using intermediate generations to simulate recurrent data structures, like ELIZA's memory mechanisms. Overall, by drawing an explicit connection between neural chatbots and interpretable, symbolic mechanisms, our results offer a new setting for mechanistic analysis of conversational agents.
Assessing the effectiveness of large language models (LLMs) presents substantial challenges. The method of conducting human-annotated battles in an online Chatbot Arena is a highly effective evaluative technique. However, this approach is limited by the costs and time required for human annotation. In this paper, we introduce Arena Learning, an innovative offline strategy designed to simulate these arena battles using AI-driven annotations to evaluate battle outcomes, thus facilitating the continuous improvement of the target model through both supervised fine-tuning and reinforcement learning. Arena Learning comprises two key elements. First, it ensures precise evaluations and maintains consistency between offline simulations and online competitions via WizardArena, a pipeline developed to accurately predict the Elo rankings of various models using a meticulously designed offline test set. Our results demonstrate that WizardArena's predictions closely align with those from the online Arena. Second, it involves the continuous improvement of training data based on the battle results and the refined model. We establish a data flywheel to iteratively update the training data by highlighting the weaknesses of the target model based on its battle results, enabling it to learn from the strengths of multiple different models. We apply Arena Learning to train our target model, WizardLM-$\beta$, and demonstrate significant performance enhancements across various metrics. This fully automated training and evaluation pipeline sets the stage for continuous advancements in various LLMs via post-training. Notably, Arena Learning plays a pivotal role in the success of WizardLM-2, and this paper serves both as an exploration of its efficacy and a foundational study for future discussions related to WizardLM-2 and its derivatives.
We present ACME: A Chatbot for asylum-seeking Migrants in Europe. ACME relies on computational argumentation and aims to help migrants identify the highest level of protection they can apply for. This would contribute to a more sustainable migration by reducing the load on territorial commissions, Courts, and humanitarian organizations supporting asylum applicants. We describe the background context, system architecture, underlying technologies, and a case study used to validate the tool with domain experts.
Training large language models (LLMs) and multimodal LLMs necessitates significant computing resources, and existing publicly available LLMs are typically pre-trained on diverse, privately curated datasets spanning various tasks. For instance, LLaMA, Vicuna, and LLaVA are three LLM variants trained with LLaMA base models using very different training recipes, tasks, and data modalities. The training cost and complexity for such LLM variants grow rapidly. In this study, we propose to use a soup strategy to assemble these LLM variants into a single well-generalized multimodal LLM (SoupLM) in a cost-efficient manner. Assembling these LLM variants efficiently brings knowledge and specialities trained from different domains and data modalities into an integrated one (e.g., chatbot speciality from user-shared conversations for Vicuna, and visual capacity from vision-language data for LLaVA), therefore, to avoid computing costs of repetitive training on several different domains. We propose series of soup strategies to systematically benchmark performance gains across various configurations, and probe the soup behavior across base models in the interpolation space.
This work explores the capability of conversational chatbots powered by large language models (LLMs), to understand and characterize predicate symmetry, a cognitive linguistic function traditionally believed to be an inherent human trait. Leveraging in-context learning (ICL), a paradigm shift enabling chatbots to learn new tasks from prompts without re-training, we assess the symmetrical reasoning of five chatbots: ChatGPT 4, Huggingface chat AI, Microsoft's Copilot AI, LLaMA through Perplexity, and Gemini Advanced. Using the Symmetry Inference Sentence (SIS) dataset by Tanchip et al. (2020), we compare chatbot responses against human evaluations to gauge their understanding of predicate symmetry. Experiment results reveal varied performance among chatbots, with some approaching human-like reasoning capabilities. Gemini, for example, reaches a correlation of 0.85 with human scores, while providing a sounding justification for each symmetry evaluation. This study underscores the potential and limitations of LLMs in mirroring complex cognitive processes as symmetrical reasoning.
Large Language Models have found application in various mundane and repetitive tasks including Human Resource (HR) support. We worked with the domain experts of SAP SE to develop an HR support chatbot as an efficient and effective tool for addressing employee inquiries. We inserted a human-in-the-loop in various parts of the development cycles such as dataset collection, prompt optimization, and evaluation of generated output. By enhancing the LLM-driven chatbot's response quality and exploring alternative retrieval methods, we have created an efficient, scalable, and flexible tool for HR professionals to address employee inquiries effectively. Our experiments and evaluation conclude that GPT-4 outperforms other models and can overcome inconsistencies in data through internal reasoning capabilities. Additionally, through expert analysis, we infer that reference-free evaluation metrics such as G-Eval and Prometheus demonstrate reliability closely aligned with that of human evaluation.
In the rapidly evolving field of natural language processing, dialogue systems primarily employ a single-step dialogue paradigm. Although this paradigm is efficient, it lacks the depth and fluidity of human interactions and does not appear natural. We introduce a novel \textbf{Step}-by-Step Dialogue Paradigm (Stephanie), designed to mimic the ongoing dynamic nature of human conversations. By employing a dual learning strategy and a further-split post-editing method, we generated and utilized a high-quality step-by-step dialogue dataset to fine-tune existing large language models, enabling them to perform step-by-step dialogues. We thoroughly present Stephanie. Tailored automatic and human evaluations are conducted to assess its effectiveness compared to the traditional single-step dialogue paradigm. We will release code, Stephanie datasets, and Stephanie LLMs to facilitate the future of chatbot eras.
The development of chatbots requires collecting a large number of human-chatbot dialogues to reflect the breadth of users' sociodemographic backgrounds and conversational goals. However, the resource requirements to conduct the respective user studies can be prohibitively high and often only allow for a narrow analysis of specific dialogue goals and participant demographics. In this paper, we propose LLM Roleplay: a goal-oriented, persona-based method to automatically generate diverse multi-turn dialogues simulating human-chatbot interaction. LLM Roleplay can be applied to generate dialogues with any type of chatbot and uses large language models (LLMs) to play the role of textually described personas. To validate our method, we collect natural human-chatbot dialogues from different sociodemographic groups and conduct a user study to compare these with our generated dialogues. We evaluate the capabilities of state-of-the-art LLMs in maintaining a conversation during their embodiment of a specific persona and find that our method can simulate human-chatbot dialogues with a high indistinguishability rate.
Large Language Models (LLMs) have showcased remarkable capabilities in various Natural Language Processing tasks. For automatic open-domain dialogue evaluation in particular, LLMs have been seamlessly integrated into evaluation frameworks, and together with human evaluation, compose the backbone of most evaluations. However, existing evaluation benchmarks often rely on outdated datasets and evaluate aspects like Fluency and Relevance, which fail to adequately capture the capabilities and limitations of state-of-the-art chatbot models. This paper critically examines current evaluation benchmarks, highlighting that the use of older response generators and quality aspects fail to accurately reflect modern chatbot capabilities. A small annotation experiment on a recent LLM-generated dataset (SODA) reveals that LLM evaluators such as GPT-4 struggle to detect actual deficiencies in dialogues generated by current LLM chatbots.
Persuasion plays a pivotal role in a wide range of applications from health intervention to the promotion of social good. Persuasive chatbots employed responsibly for social good can be an enabler of positive individual and social change. Existing methods rely on fine-tuning persuasive chatbots with task-specific training data which is costly, if not infeasible, to collect. Furthermore, they employ only a handful of pre-defined persuasion strategies. We propose PersuaBot, a zero-shot chatbot based on Large Language Models (LLMs) that is factual and more persuasive by leveraging many more nuanced strategies. PersuaBot uses an LLM to first generate natural responses, from which the strategies used are extracted. To combat hallucination of LLMs, Persuabot replace any unsubstantiated claims in the response with retrieved facts supporting the extracted strategies. We applied our chatbot, PersuaBot, to three significantly different domains needing persuasion skills: donation solicitation, recommendations, and health intervention. Our experiments on simulated and human conversations show that our zero-shot approach is more persuasive than prior work, while achieving factual accuracy surpassing state-of-the-art knowledge-oriented chatbots.
The rapid advancement of large language models (LLMs) has facilitated their transformation into conversational chatbots that can grasp contextual nuances and generate pertinent sentences, closely mirroring human values through advanced techniques such as instruction tuning and reinforcement learning from human feedback (RLHF). However, the computational efficiency required for LLMs, achieved through techniques like post-training quantization (PTQ), presents challenges such as token-flipping that can impair chatbot performance. In response, we propose a novel preference alignment approach, quantization-aware direct preference optimization (QDPO), that aligns quantized LLMs with their full-precision counterparts, improving conversational abilities. Evaluated on two instruction-tuned LLMs in various languages, QDPO demonstrated superior performance in improving conversational abilities compared to established PTQ and knowledge-distillation fine-tuning techniques, marking a significant step forward in the development of efficient and effective conversational LLMs.