Large language models (LLMs) are already being piloted for clinical use in hospital systems like NYU Langone, Dana-Farber and the NHS. A proposed deployment use case is psychotherapy, where a LLM-powered chatbot can treat a patient undergoing a mental health crisis. Deployment of LLMs for mental health response could hypothetically broaden access to psychotherapy and provide new possibilities for personalizing care. However, recent high-profile failures, like damaging dieting advice offered by the Tessa chatbot to patients with eating disorders, have led to doubt about their reliability in high-stakes and safety-critical settings. In this work, we develop an evaluation framework for determining whether LLM response is a viable and ethical path forward for the automation of mental health treatment. Our framework measures equity in empathy and adherence of LLM responses to motivational interviewing theory. Using human evaluation with trained clinicians and automatic quality-of-care metrics grounded in psychology research, we compare the responses provided by peer-to-peer responders to those provided by a state-of-the-art LLM. We show that LLMs like GPT-4 use implicit and explicit cues to infer patient demographics like race. We then show that there are statistically significant discrepancies between patient subgroups: Responses to Black posters consistently have lower empathy than for any other demographic group (2%-13% lower than the control group). Promisingly, we do find that the manner in which responses are generated significantly impacts the quality of the response. We conclude by proposing safety guidelines for the potential deployment of LLMs for mental health response.
We explore the usage of large language models (LLM) in human-in-the-loop human-in-the-plant cyber-physical systems (CPS) to translate a high-level prompt into a personalized plan of actions, and subsequently convert that plan into a grounded inference of sequential decision-making automated by a real-world CPS controller to achieve a control goal. We show that it is relatively straightforward to contextualize an LLM so it can generate domain-specific plans. However, these plans may be infeasible for the physical system to execute or the plan may be unsafe for human users. To address this, we propose CPS-LLM, an LLM retrained using an instruction tuning framework, which ensures that generated plans not only align with the physical system dynamics of the CPS but are also safe for human users. The CPS-LLM consists of two innovative components: a) a liquid time constant neural network-based physical dynamics coefficient estimator that can derive coefficients of dynamical models with some unmeasured state variables; b) the model coefficients are then used to train an LLM with prompts embodied with traces from the dynamical system and the corresponding model coefficients. We show that when the CPS-LLM is integrated with a contextualized chatbot such as BARD it can generate feasible and safe plans to manage external events such as meals for automated insulin delivery systems used by Type 1 Diabetes subjects.
One way to personalize chatbot interactions is by establishing common ground with the intended reader. A domain where establishing mutual understanding could be particularly impactful is vaccine concerns and misinformation. Vaccine interventions are forms of messaging which aim to answer concerns expressed about vaccination. Tailoring responses in this domain is difficult, since opinions often have seemingly little ideological overlap. We define the task of tailoring vaccine interventions to a Common-Ground Opinion (CGO). Tailoring responses to a CGO involves meaningfully improving the answer by relating it to an opinion or belief the reader holds. In this paper we introduce TAILOR-CGO, a dataset for evaluating how well responses are tailored to provided CGOs. We benchmark several major LLMs on this task; finding GPT-4-Turbo performs significantly better than others. We also build automatic evaluation metrics, including an efficient and accurate BERT model that outperforms finetuned LLMs, investigate how to successfully tailor vaccine messaging to CGOs, and provide actionable recommendations from this investigation. Code and model weights: https://github.com/rickardstureborg/tailor-cgo Dataset: https://huggingface.co/datasets/DukeNLP/tailor-cgo
Diaspora communities are disproportionately impacted by off-the-radar misinformation and often neglected by mainstream fact-checking efforts, creating a critical need to scale-up efforts of nascent fact-checking initiatives. In this paper we present SynDy, a framework for Synthetic Dynamic Dataset Generation to leverage the capabilities of the largest frontier Large Language Models (LLMs) to train local, specialized language models. To the best of our knowledge, SynDy is the first paper utilizing LLMs to create fine-grained synthetic labels for tasks of direct relevance to misinformation mitigation, namely Claim Matching, Topical Clustering, and Claim Relationship Classification. SynDy utilizes LLMs and social media queries to automatically generate distantly-supervised, topically-focused datasets with synthetic labels on these three tasks, providing essential tools to scale up human-led fact-checking at a fraction of the cost of human-annotated data. Training on SynDy's generated labels shows improvement over a standard baseline and is not significantly worse compared to training on human labels (which may be infeasible to acquire). SynDy is being integrated into Meedan's chatbot tiplines that are used by over 50 organizations, serve over 230K users annually, and automatically distribute human-written fact-checks via messaging apps such as WhatsApp. SynDy will also be integrated into our deployed Co-Insights toolkit, enabling low-resource organizations to launch tiplines for their communities. Finally, we envision SynDy enabling additional fact-checking tools such as matching new misinformation claims to high-quality explainers on common misinformation topics.
This paper presents BARKPLUG V.2, a Large Language Model (LLM)-based chatbot system built using Retrieval Augmented Generation (RAG) pipelines to enhance the user experience and access to information within academic settings.The objective of BARKPLUG V.2 is to provide information to users about various campus resources, including academic departments, programs, campus facilities, and student resources at a university setting in an interactive fashion. Our system leverages university data as an external data corpus and ingests it into our RAG pipelines for domain-specific question-answering tasks. We evaluate the effectiveness of our system in generating accurate and pertinent responses for Mississippi State University, as a case study, using quantitative measures, employing frameworks such as Retrieval Augmented Generation Assessment(RAGAS). Furthermore, we evaluate the usability of this system via subjective satisfaction surveys using the System Usability Scale (SUS). Our system demonstrates impressive quantitative performance, with a mean RAGAS score of 0.96, and experience, as validated by usability assessments.
ChatGPT, the AI-powered chatbot with a massive user base of hundreds of millions, has become a global phenomenon. However, the use of Conversational AI Systems (CAISs) like ChatGPT for research in the field of Social Simulation is still limited. Specifically, there is no evidence of its usage in Agent-Based Social Simulation (ABSS) model design. While scepticism towards anything new is inherent to human nature, we firmly believe it is imperative to initiate the use of this innovative technology to support ABSS model design. This paper presents a proof-of-concept that demonstrates how CAISs can facilitate the development of innovative conceptual ABSS models in a concise timeframe and with minimal required upfront case-based knowledge. By employing advanced prompt engineering techniques and adhering to the Engineering ABSS framework, we have constructed a comprehensive prompt script that enables the design of ABSS models with or by the CAIS. The effectiveness of the script is demonstrated through an illustrative case study concerning the use of adaptive architecture in museums. Despite occasional inaccuracies and divergences in conversation, the CAIS proved to be a valuable companion for ABSS modellers.
We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpart by a large margin in the recent large language model (LLM) literature. However, existing open-source RLHF projects are still largely confined to the offline learning setting. In this technical report, we aim to fill in this gap and provide a detailed recipe that is easy to reproduce for online iterative RLHF. In particular, since online human feedback is usually infeasible for open-source communities with limited resources, we start by constructing preference models using a diverse set of open-source datasets and use the constructed proxy preference model to approximate human feedback. Then, we discuss the theoretical insights and algorithmic principles behind online iterative RLHF, followed by a detailed practical implementation. Our trained LLM achieves impressive performance on LLM chatbot benchmarks, including AlpacaEval-2, Arena-Hard, and MT-Bench, as well as other academic benchmarks such as HumanEval and TruthfulQA. We have shown that supervised fine-tuning (SFT) and iterative RLHF can obtain state-of-the-art performance with fully open-source datasets. Further, we have made our models, curated datasets, and comprehensive step-by-step code guidebooks publicly available. Please refer to https://github.com/RLHFlow/RLHF-Reward-Modeling and https://github.com/RLHFlow/Online-RLHF for more detailed information.
We investigate the use of Natural Language Inference (NLI) in automating requirements engineering tasks. In particular, we focus on three tasks: requirements classification, identification of requirements specification defects, and detection of conflicts in stakeholders' requirements. While previous research has demonstrated significant benefit in using NLI as a universal method for a broad spectrum of natural language processing tasks, these advantages have not been investigated within the context of software requirements engineering. Therefore, we design experiments to evaluate the use of NLI in requirements analysis. We compare the performance of NLI with a spectrum of approaches, including prompt-based models, conventional transfer learning, Large Language Models (LLMs)-powered chatbot models, and probabilistic models. Through experiments conducted under various learning settings including conventional learning and zero-shot, we demonstrate conclusively that our NLI method surpasses classical NLP methods as well as other LLMs-based and chatbot models in the analysis of requirements specifications. Additionally, we share lessons learned characterizing the learning settings that make NLI a suitable approach for automating requirements engineering tasks.
Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural sensitivity of the chatbot's responses. These applications, however, are predicated on the ability of AI agents to reliably adopt assigned personas and mimic human interactions. To see whether LLM agents satisfy these requirements, we examine AI agent ensembles engaged in cross-national collaboration and debate by analyzing their private responses and chat transcripts. Our findings suggest that multi-agent discussions can support collective AI decisions that more often reflect diverse perspectives, yet this effect is tempered by the agents' susceptibility to conformity due to perceived peer pressure and occasional challenges in maintaining consistent personas and opinions. Instructions that encourage debate in support of one's opinions rather than collaboration increase the rate of inconstancy. Without addressing the factors we identify, the full potential of multi-agent frameworks for producing more culturally diverse AI outputs or more realistic simulations of group decision-making may remain untapped.
Instruction tuning improves the reasoning abilities of large language models (LLMs), with data quality and scalability being the crucial factors. Most instruction tuning data come from human crowd-sourcing or GPT-4 distillation. We propose a paradigm to efficiently harvest 10 million naturally existing instruction data from the pre-training web corpus to enhance LLM reasoning. Our approach involves (1) recalling relevant documents, (2) extracting instruction-response pairs, and (3) refining the extracted pairs using open-source LLMs. Fine-tuning base LLMs on this dataset, we build MAmmoTH2 models, which significantly boost performance on reasoning benchmarks. Notably, MAmmoTH2-7B's (Mistral) performance increases from 11% to 36.7% on MATH and from 36% to 68.4% on GSM8K without training on any in-domain data. Further training MAmmoTH2 on public instruction tuning datasets yields MAmmoTH2-Plus, achieving state-of-the-art performance on several reasoning and chatbot benchmarks. Our work demonstrates how to harvest large-scale, high-quality instruction data without costly human annotation or GPT-4 distillation, providing a new paradigm for building better instruction tuning data.
This research focuses on evaluating the non-commercial open-source large language models (LLMs) Meditron, MedAlpaca, Mistral, and Llama-2 for their efficacy in interpreting medical guidelines saved in PDF format. As a specific test scenario, we applied these models to the guidelines for hypertension in children and adolescents provided by the European Society of Cardiology (ESC). Leveraging Streamlit, a Python library, we developed a user-friendly medical document chatbot tool (MedDoc-Bot). This tool enables authorized users to upload PDF files and pose questions, generating interpretive responses from four locally stored LLMs. A pediatric expert provides a benchmark for evaluation by formulating questions and responses extracted from the ESC guidelines. The expert rates the model-generated responses based on their fidelity and relevance. Additionally, we evaluated the METEOR and chrF metric scores to assess the similarity of model responses to reference answers. Our study found that Llama-2 and Mistral performed well in metrics evaluation. However, Llama-2 was slower when dealing with text and tabular data. In our human evaluation, we observed that responses created by Mistral, Meditron, and Llama-2 exhibited reasonable fidelity and relevance. This study provides valuable insights into the strengths and limitations of LLMs for future developments in medical document interpretation. Open-Source Code: https://github.com/yaseen28/MedDoc-Bot
Chatbots such as GPT-4 and ChatGPT are now serving millions of users. Despite their widespread use, there remains a lack of public datasets showcasing how these tools are used by a population of users in practice. To bridge this gap, we offered free access to ChatGPT for online users in exchange for their affirmative, consensual opt-in to anonymously collect their chat transcripts and request headers. From this, we compiled WildChat, a corpus of 1 million user-ChatGPT conversations, which consists of over 2.5 million interaction turns. We compare WildChat with other popular user-chatbot interaction datasets, and find that our dataset offers the most diverse user prompts, contains the largest number of languages, and presents the richest variety of potentially toxic use-cases for researchers to study. In addition to timestamped chat transcripts, we enrich the dataset with demographic data, including state, country, and hashed IP addresses, alongside request headers. This augmentation allows for more detailed analysis of user behaviors across different geographical regions and temporal dimensions. Finally, because it captures a broad range of use cases, we demonstrate the dataset's potential utility in fine-tuning instruction-following models. WildChat is released at https://wildchat.allen.ai under AI2 ImpACT Licenses.
Teaching programming in early childhood (4-9) to enhance computational thinking has gained popularity in the recent movement of computer science for all. However, current practices ignore some fundamental issues resulting from young children's developmental readiness, such as the sustained capability to keyboarding, the decomposition of complex tasks to small tasks, the need for intuitive mapping from abstract programming to tangible outcomes, and the limited amount of screen time exposure. To address these issues in this paper, we present a novel methodology with an AI-powered integration platform to effectively teach computational thinking for young children. The system features a hybrid pedagogy that supports both the top-down and bottom-up approach for teaching computational thinking. Young children can describe their desired task in natural language, while the system can respond with an easy-to-understand program consisting of the right level of decomposed sub-tasks. A tangible robot can immediately execute the decomposed program and demonstrate the program's outcomes to young children. The system is equipped with an intelligent chatbot that can interact with young children through natural languages, and children can speak to the chatbot to complete all the needed programming tasks, while the chatbot orchestrates the execution of the program onto the robot. This would completely eliminates the need of keyboards for young children to program. By developing such a system, we aim to make the concept of computational thinking more accessible to young children, fostering a natural understanding of programming concepts without the need of explicit programming skills. Through the interactive experience provided by the robotic agent, our system seeks to engage children in an effective manner, contributing to the field of educational technology for early childhood computer science education.
This paper describes the technical and conceptual development of the LuminLab platform, an online tool that integrates a purpose-fit human-centric AI chatbot and predictive energy model into a streamlined front-end that can rapidly produce and discuss building retrofit plans in natural language. The platform provides users with the ability to engage with a range of possible retrofit pathways tailored to their individual budget and building needs on-demand. Given the complicated and costly nature of building retrofit projects, which rely on a variety of stakeholder groups with differing goals and incentives, we feel that AI-powered tools such as this have the potential to pragmatically de-silo knowledge, improve communication, and empower individual homeowners to undertake incremental retrofit projects that might not happen otherwise.
This paper explores enhancing empathy in Large Language Models (LLMs) by integrating them with physiological data. We propose a physiological computing approach that includes developing deep learning models that use physiological data for recognizing psychological states and integrating the predicted states with LLMs for empathic interaction. We showcase the application of this approach in an Empathic LLM (EmLLM) chatbot for stress monitoring and control. We also discuss the results of a pilot study that evaluates this EmLLM chatbot based on its ability to accurately predict user stress, provide human-like responses, and assess the therapeutic alliance with the user.
Large language models (LLMs) have demonstrated impressive generalization capabilities on specific tasks with human-written instruction data. However, the limited quantity, diversity, and professional expertise of such instruction data raise concerns about the performance of LLMs in psychotherapy tasks when provided with domain-specific instructions. To address this, we firstly propose Domain-Specific Assistant Instructions based on AlexanderStreet therapy, and secondly, we use an adaption fine-tuning method and retrieval augmented generation method to improve pre-trained LLMs. Through quantitative evaluation of linguistic quality using automatic and human evaluation, we observe that pre-trained LLMs on Psychotherapy Assistant Instructions outperform state-of-the-art LLMs response baselines. Our Assistant-Instruction approach offers a half-annotation method to align pre-trained LLMs with instructions and provide pre-trained LLMs with more psychotherapy knowledge.
Large Language Models (LLMs) are frequently discussed in academia and the general public as support tools for virtually any use case that relies on the production of text, including software engineering. Currently there is much debate, but little empirical evidence, regarding the practical usefulness of LLM-based tools such as ChatGPT for engineers in industry. We conduct an observational study of 24 professional software engineers who have been using ChatGPT over a period of one week in their jobs, and qualitatively analyse their dialogues with the chatbot as well as their overall experience (as captured by an exit survey). We find that, rather than expecting ChatGPT to generate ready-to-use software artifacts (e.g., code), practitioners more often use ChatGPT to receive guidance on how to solve their tasks or learn about a topic in more abstract terms. We also propose a theoretical framework for how (i) purpose of the interaction, (ii) internal factors (e.g., the user's personality), and (iii) external factors (e.g., company policy) together shape the experience (in terms of perceived usefulness and trust). We envision that our framework can be used by future research to further the academic discussion on LLM usage by software engineering practitioners, and to serve as a reference point for the design of future empirical LLM research in this domain.
Existing English-teaching chatbots rarely incorporate empathy explicitly in their feedback, but empathetic feedback could help keep students engaged and reduce learner anxiety. Toward this end, we propose the task of negative emotion detection via audio, for recognizing empathetic feedback opportunities in language learning. We then build the first spoken English-teaching chatbot with adaptive, empathetic feedback. This feedback is synthesized through automatic prompt optimization of ChatGPT and is evaluated with English learners. We demonstrate the effectiveness of our system through a preliminary user study.
The ubiquity of smartphones has led to an increase in on demand healthcare being supplied. For example, people can share their illness-related experiences with others similar to themselves, and healthcare experts can offer advice for better treatment and care for remediable, terminal and mental illnesses. As well as this human-to-human communication, there has been an increased use of human-to-computer digital health messaging, such as chatbots. These can prove advantageous as they offer synchronous and anonymous feedback without the need for a human conversational partner. However, there are many subtleties involved in human conversation that a computer agent may not properly exhibit. For example, there are various conversational styles, etiquettes, politeness strategies or empathic responses that need to be chosen appropriately for the conversation. Encouragingly, computers are social actors (CASA) posits that people apply the same social norms to computers as they would do to people. On from this, previous studies have focused on applying conversational strategies to computer agents to make them embody more favourable human characteristics. However, if a computer agent fails in this regard it can lead to negative reactions from users. Therefore, in this dissertation we describe a series of studies we carried out to lead to more effective human-to-computer digital health messaging. In our first study, we use the crowd [...] Our second study investigates the effect of a health chatbot's conversational style [...] In our final study, we investigate the format used by a chatbot when [...] In summary, we have researched how to create more effective digital health interventions starting from generating health messages, to choosing an appropriate formality of messaging, and finally to formatting messages which reference a user's previous utterances.
Recent advancements in LLMs have shown their significant potential in tasks like text summarization and generation. Yet, they often encounter difficulty while solving complex physics problems that require arithmetic calculation and a good understanding of concepts. Moreover, many physics problems include images that contain important details required to understand the problem's context. We propose an LMM-based chatbot to answer multimodal physics MCQs. For domain adaptation, we utilize the MM-PhyQA dataset comprising Indian high school-level multimodal physics problems. To improve the LMM's performance, we experiment with two techniques, RLHF (Reinforcement Learning from Human Feedback) and Image Captioning. In image captioning, we add a detailed explanation of the diagram in each image, minimizing hallucinations and image processing errors. We further explore the integration of Reinforcement Learning from Human Feedback (RLHF) methodology inspired by the ranking approach in RLHF to enhance the human-like problem-solving abilities of the models. The RLHF approach incorporates human feedback into the learning process of LLMs, improving the model's problem-solving skills, truthfulness, and reasoning capabilities, minimizing the hallucinations in the answers, and improving the quality instead of using vanilla-supervised fine-tuned models. We employ the LLaVA open-source model to answer multimodal physics MCQs and compare the performance with and without using RLHF.