Human health is increasingly threatened by exposure to hazardous substances, particularly persistent and toxic chemicals. The link between these substances, often encountered in complex mixtures, and various diseases are demonstrated in scientific studies. However, this information is scattered across several sources and hardly accessible by humans and machines. This paper evaluates current practices for publishing/accessing information on hazardous chemicals and proposes a novel platform designed to facilitate retrieval of critical chemical data in urgent situations. The platform aggregates information from multiple sources and organizes it into a structured knowledge graph. Users can access this information through a visual interface such as Neo4J Bloom and dashboards, or via natural language queries using a Chatbot. Our findings demonstrate a significant reduction in the time and effort required to access vital chemical information when datasets follow FAIR principles. Furthermore, we discuss the lessons learned from the development and implementation of this platform and provide recommendations for data owners and publishers to enhance data reuse and interoperability. This work aims to improve the accessibility and usability of chemical information by healthcare professionals, thereby supporting better health outcomes and informed decision-making in the face of patients exposed to chemical intoxication risks.
With the growing adoption and capabilities of vision-language models (VLMs) comes the need for benchmarks that capture authentic user-VLM interactions. In response, we create VisionArena, a dataset of 230K real-world conversations between users and VLMs. Collected from Chatbot Arena - an open-source platform where users interact with VLMs and submit preference votes - VisionArena spans 73K unique users, 45 VLMs, and 138 languages. Our dataset contains three subsets: VisionArena-Chat, 200k single and multi-turn conversations between a user and a VLM; VisionArena-Battle, 30K conversations comparing two anonymous VLMs with user preference votes; and VisionArena-Bench, an automatic benchmark of 500 diverse user prompts that efficiently approximate the live Chatbot Arena model rankings. Additionally, we highlight the types of question asked by users, the influence of response style on preference, and areas where models often fail. We find open-ended tasks like captioning and humor are highly style-dependent, and current VLMs struggle with spatial reasoning and planning tasks. Lastly, we show finetuning the same base model on VisionArena-Chat outperforms Llava-Instruct-158K, with a 17-point gain on MMMU and a 46-point gain on the WildVision benchmark. Dataset at https://huggingface.co/lmarena-ai
We tasked 16 state-of-the-art large language models (LLMs) with estimating the likelihood of Artificial General Intelligence (AGI) emerging by 2030. To assess the quality of these forecasts, we implemented an automated peer review process (LLM-PR). The LLMs' estimates varied widely, ranging from 3% (Reka- Core) to 47.6% (GPT-4o), with a median of 12.5%. These estimates closely align with a recent expert survey that projected a 10% likelihood of AGI by 2027, underscoring the relevance of LLMs in forecasting complex, speculative scenarios. The LLM-PR process demonstrated strong reliability, evidenced by a high Intraclass Correlation Coefficient (ICC = 0.79), reflecting notable consistency in scoring across the models. Among the models, Pplx-70b-online emerged as the top performer, while Gemini-1.5-pro-api ranked the lowest. A cross-comparison with external benchmarks, such as LMSYS Chatbot Arena, revealed that LLM rankings remained consistent across different evaluation methods, suggesting that existing benchmarks may not encapsulate some of the skills relevant for AGI prediction. We further explored the use of weighting schemes based on external benchmarks, optimizing the alignment of LLMs' predictions with human expert forecasts. This analysis led to the development of a new, 'AGI benchmark' designed to highlight performance differences in AGI-related tasks. Our findings offer insights into LLMs' capabilities in speculative, interdisciplinary forecasting tasks and emphasize the growing need for innovative evaluation frameworks for assessing AI performance in complex, uncertain real-world scenarios.
By means of pilot experiments for the language pair German and Galician, this paper examines the concept of efficiency and intelligence in lexicography and artificial intelligence, AI. The aim of the experiments is to gain empirically and statistically based insights into the lexicographical text type,dictionary article, in the responses of ChatGPT 3.5, as well as into the lexicographical data on which this chatbot was trained. Both quantitative and qualitative methods are used for this purpose. The analysis is based on the evaluation of the outputs of several sessions with the same prompt in ChatGPT 3.5. On the one hand, the algorithmic performance of intelligent systems is evaluated in comparison with data from lexicographical works. On the other hand, the ChatGPT data supplied is analysed using specific text passages of the aforementioned lexicographical text type. The results of this study not only help to evaluate the efficiency of this chatbot regarding the creation of dictionary articles, but also to delve deeper into the concept of intelligence, the thought processes and the actions to be carried out in both disciplines.
This paper introduces a framework that leverages Large Language Models (LLMs) to answer natural language queries about General Transit Feed Specification (GTFS) data. The framework is implemented in a chatbot called TransitGPT with open-source code. TransitGPT works by guiding LLMs to generate Python code that extracts and manipulates GTFS data relevant to a query, which is then executed on a server where the GTFS feed is stored. It can accomplish a wide range of tasks, including data retrieval, calculations, and interactive visualizations, without requiring users to have extensive knowledge of GTFS or programming. The LLMs that produce the code are guided entirely by prompts, without fine-tuning or access to the actual GTFS feeds. We evaluate TransitGPT using GPT-4o and Claude-3.5-Sonnet LLMs on a benchmark dataset of 100 tasks, to demonstrate its effectiveness and versatility. The results show that TransitGPT can significantly enhance the accessibility and usability of transit data.
The rise of "bedroom producers" has democratized music creation, while challenging producers to objectively evaluate their work. To address this, we present AI TrackMate, an LLM-based music chatbot designed to provide constructive feedback on music productions. By combining LLMs' inherent musical knowledge with direct audio track analysis, AI TrackMate offers production-specific insights, distinguishing it from text-only approaches. Our framework integrates a Music Analysis Module, an LLM-Readable Music Report, and Music Production-Oriented Feedback Instruction, creating a plug-and-play, training-free system compatible with various LLMs and adaptable to future advancements. We demonstrate AI TrackMate's capabilities through an interactive web interface and present findings from a pilot study with a music producer. By bridging AI capabilities with the needs of independent producers, AI TrackMate offers on-demand analytical feedback, potentially supporting the creative process and skill development in music production. This system addresses the growing demand for objective self-assessment tools in the evolving landscape of independent music production.
The remarkable performance of large language models (LLMs) in content generation, coding, and common-sense reasoning has spurred widespread integration into many facets of society. However, integration of LLMs raises valid questions on their reliability and trustworthiness, given their propensity to generate hallucinations: plausible, factually-incorrect responses, which are expressed with striking confidence. Previous work has shown that hallucinations and other non-factual responses generated by LLMs can be detected by examining the uncertainty of the LLM in its response to the pertinent prompt, driving significant research efforts devoted to quantifying the uncertainty of LLMs. This survey seeks to provide an extensive review of existing uncertainty quantification methods for LLMs, identifying their salient features, along with their strengths and weaknesses. We present existing methods within a relevant taxonomy, unifying ostensibly disparate methods to aid understanding of the state of the art. Furthermore, we highlight applications of uncertainty quantification methods for LLMs, spanning chatbot and textual applications to embodied artificial intelligence applications in robotics. We conclude with open research challenges in uncertainty quantification of LLMs, seeking to motivate future research.
Evaluating the reasoning abilities of large language models (LLMs) is challenging. Existing benchmarks often depend on static datasets, which are vulnerable to data contamination and may get saturated over time, or on binary live human feedback that conflates reasoning with other abilities. As the most prominent dynamic benchmark, Chatbot Arena evaluates open-ended questions in real-world settings, but lacks the granularity in assessing specific reasoning capabilities. We introduce GameArena, a dynamic benchmark designed to evaluate LLM reasoning capabilities through interactive gameplay with humans. GameArena consists of three games designed to test specific reasoning capabilities (e.g., deductive and inductive reasoning), while keeping participants entertained and engaged. We analyze the gaming data retrospectively to uncover the underlying reasoning processes of LLMs and measure their fine-grained reasoning capabilities. We collect over 2000 game sessions and provide detailed assessments of various reasoning capabilities for five state-of-the-art LLMs. Our user study with 100 participants suggests that GameArena improves user engagement compared to Chatbot Arena. For the first time, GameArena enables the collection of step-by-step LLM reasoning data in the wild.
Robots and other artificial intelligence (AI) systems are widely perceived as moral agents responsible for their actions. As AI proliferates, these perceptions may become entangled via the moral spillover of attitudes towards one AI to attitudes towards other AIs. We tested how the seemingly harmful and immoral actions of an AI or human agent spill over to attitudes towards other AIs or humans in two preregistered experiments. In Study 1 (N = 720), we established the moral spillover effect in human-AI interaction by showing that immoral actions increased attributions of negative moral agency (i.e., acting immorally) and decreased attributions of positive moral agency (i.e., acting morally) and moral patiency (i.e., deserving moral concern) to both the agent (a chatbot or human assistant) and the group to which they belong (all chatbot or human assistants). There was no significant difference in the spillover effects between the AI and human contexts. In Study 2 (N = 684), we tested whether spillover persisted when the agent was individuated with a name and described as an AI or human, rather than specifically as a chatbot or personal assistant. We found that spillover persisted in the AI context but not in the human context, possibly because AIs were perceived as more homogeneous due to their outgroup status relative to humans. This asymmetry suggests a double standard whereby AIs are judged more harshly than humans when one agent morally transgresses. With the proliferation of diverse, autonomous AI systems, HCI research and design should account for the fact that experiences with one AI could easily generalize to perceptions of all AIs and negative HCI outcomes, such as reduced trust.
The world can be a complex and difficult place to navigate. People with High-Functioning Autistic Spectrum Disorder as well as general social ineptitude often face navigation challenges that individuals of other demographics simply do not themselves. This can become even more pronounced with people of that specific group when they are in their teenage years and early adulthood (that being the usual age range of college students). When they are at such a vulnerable age, they can be far more susceptible to the struggles of becoming comfortable and content with social interactions as well as having strong relationships (outside their immediate family). Concerning this, the rapid emergence of artificial intelligence chatbots has led to many of them being used to benefit people of different ages and demographics with easy accessibility. With this, if there is anything that people with High-Functioning ASD and social ineptitude want when it comes to guidance towards self-improvement, surely easy accessibility would be one. What are the potential benefits and limitations of using a Mindstudio AI-powered chatbot to provide mental health support for teens and young adults with the aforementioned conditions? What could be done with a tool like this to help those individuals navigate ethical dilemmas within different social environments to reduce existing social tensions? This paper addresses these queries and offers insights to inform future discussions on the subject.
This paper presents a comprehensive chatbot system designed to handle a wide range of audio-related queries by integrating multiple specialized audio processing models. The proposed system uses an intent classifier, trained on a diverse audio query dataset, to route queries about audio content to expert models such as Automatic Speech Recognition (ASR), Speaker Diarization, Music Identification, and Text-to-Audio generation. A 3.8 B LLM model then takes inputs from an Audio Context Detection (ACD) module extracting audio event information from the audio and post processes text domain outputs from the expert models to compute the final response to the user. We evaluated the system on custom audio tasks and MMAU sound set benchmarks. The custom datasets were motivated by target use cases not covered in industry benchmarks and included ACD-timestamp-QA (Question Answering) as well as ACD-temporal-QA datasets to evaluate timestamp and temporal reasoning questions, respectively. First we determined that a BERT based Intent Classifier outperforms LLM-fewshot intent classifier in routing queries. Experiments further show that our approach significantly improves accuracy on some custom tasks compared to state-of-the-art Large Audio Language Models and outperforms models in the 7B parameter size range on the sound testset of the MMAU benchmark, thereby offering an attractive option for on device deployment.
Mental health has increasingly become a global issue that reveals the limitations of traditional conversational psychotherapy, constrained by location, time, expense, and privacy concerns. In response to these challenges, we introduce SoulSpeak, a Large Language Model (LLM)-enabled chatbot designed to democratize access to psychotherapy. SoulSpeak improves upon the capabilities of standard LLM-enabled chatbots by incorporating a novel dual-memory component that combines short-term and long-term context via Retrieval Augmented Generation (RAG) to offer personalized responses while ensuring the preservation of user privacy and intimacy through a dedicated privacy module. In addition, it leverages a counseling chat dataset of therapist-client interactions and various prompting techniques to align the generated responses with psychotherapeutic methods. We introduce two fine-tuned BERT models to evaluate the system against existing LLMs and human therapists: the Conversational Psychotherapy Preference Model (CPPM) to simulate human preference among responses and another to assess response relevance to user input. CPPM is useful for training and evaluating psychotherapy-focused language models independent from SoulSpeak, helping with the constrained resources available for psychotherapy. Furthermore, the effectiveness of the dual-memory component and the robustness of the privacy module are also examined. Our findings highlight the potential and challenge of enhancing mental health care by offering an alternative that combines the expertise of traditional therapy with the advantages of LLMs, providing a promising way to address the accessibility and personalization gap in current mental health services.
Upon release, ChatGPT3.5 shocked the software engineering community by its ability to generate answers to specialized questions about coding. Immediately, many educators wondered if it was possible to use the chatbot as a support tool that helps students answer their programming questions. This article evaluates this possibility at three levels: fundamental Computer Science knowledge (basic algorithms and data structures), core competency (design patterns), and advanced knowledge (quantum computing). In each case, we ask normalized questions several times to ChatGPT3.5, then look at the correctness of answers, and finally check if this creates issues. The main result is that the performances of ChatGPT3.5 degrades drastically as the specialization of the domain increases: for basic algorithms it returns answers that are almost always correct, for design patterns the generated code contains many code smells and is generally of low quality, but it is still sometimes able to fix it (if asked), and for quantum computing it is often blatantly wrong.
With the rise of online education platforms, there is a growing abundance of educational content across various domain. It can be difficult to navigate the numerous available resources to find the most suitable training, especially in domains that include many interconnected areas, such as ICT. In this study, we propose a domain-specific chatbot application that requires limited resources, utilizing versions of the Phi language model to help learners with educational content. In the proposed method, Phi-2 and Phi-3 models were fine-tuned using QLoRA. The data required for fine-tuning was obtained from the Huawei Talent Platform, where courses are available at different levels of expertise in the field of computer science. RAG system was used to support the model, which was fine-tuned by 500 Q&A pairs. Additionally, a total of 420 Q&A pairs of content were extracted from different formats such as JSON, PPT, and DOC to create a vector database to be used in the RAG system. By using the fine-tuned model and RAG approach together, chatbots with different competencies were obtained. The questions and answers asked to the generated chatbots were saved separately and evaluated using ROUGE, BERTScore, METEOR, and BLEU metrics. The precision value of the Phi-2 model supported by RAG was 0.84 and the F1 score was 0.82. In addition to a total of 13 different evaluation metrics in 4 different categories, the answers of each model were compared with the created content and the most appropriate method was selected for real-life applications.
We introduce GLM-4-Voice, an intelligent and human-like end-to-end spoken chatbot. It supports both Chinese and English, engages in real-time voice conversations, and varies vocal nuances such as emotion, intonation, speech rate, and dialect according to user instructions. GLM-4-Voice uses an ultra-low bitrate (175bps), single-codebook speech tokenizer with 12.5Hz frame rate derived from an automatic speech recognition (ASR) model by incorporating a vector-quantized bottleneck into the encoder. To efficiently transfer knowledge from text to speech modalities, we synthesize speech-text interleaved data from existing text pre-training corpora using a text-to-token model. We continue pre-training from the pre-trained text language model GLM-4-9B with a combination of unsupervised speech data, interleaved speech-text data, and supervised speech-text data, scaling up to 1 trillion tokens, achieving state-of-the-art performance in both speech language modeling and spoken question answering. We then fine-tune the pre-trained model with high-quality conversational speech data, achieving superior performance compared to existing baselines in both conversational ability and speech quality. The open models can be accessed through https://github.com/THUDM/GLM-4-Voice and https://huggingface.co/THUDM/glm-4-voice-9b.
This technical report presents Yi-Lightning, our latest flagship large language model (LLM). It achieves exceptional performance, ranking 6th overall on Chatbot Arena, with particularly strong results (2nd to 4th place) in specialized categories including Chinese, Math, Coding, and Hard Prompts. Yi-Lightning leverages an enhanced Mixture-of-Experts (MoE) architecture, featuring advanced expert segmentation and routing mechanisms coupled with optimized KV-caching techniques. Our development process encompasses comprehensive pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF), where we devise deliberate strategies for multi-stage training, synthetic data construction, and reward modeling. Furthermore, we implement RAISE (Responsible AI Safety Engine), a four-component framework to address safety issues across pre-training, post-training, and serving phases. Empowered by our scalable super-computing infrastructure, all these innovations substantially reduce training, deployment and inference costs while maintaining high-performance standards. With further evaluations on public academic benchmarks, Yi-Lightning demonstrates competitive performance against top-tier LLMs, while we observe a notable disparity between traditional, static benchmark results and real-world, dynamic human preferences. This observation prompts a critical reassessment of conventional benchmarks' utility in guiding the development of more intelligent and powerful AI systems for practical applications. Yi-Lightning is now available through our developer platform at https://platform.lingyiwanwu.com.
Natural language processing skills of Large Language Models (LLMs) are unprecedented, having wide diffusion and application in different tasks. This pilot study focuses on specializing ChatGPT behavior through a Retrieval-Augmented Generation (RAG) system using the OpenAI custom GPTs feature. The purpose of our chatbot, called Unimib Assistant, is to provide information and solutions to the specific needs of University of Milano-Bicocca (Unimib) students through a question-answering approach. We provided the system with a prompt highlighting its specific purpose and behavior, as well as university-related documents and links obtained from an initial need-finding phase, interviewing six students. After a preliminary customization phase, a qualitative usability test was conducted with six other students to identify the strengths and weaknesses of the chatbot, with the goal of improving it in a subsequent redesign phase. While the chatbot was appreciated for its user-friendly experience, perceived general reliability, well-structured responses, and conversational tone, several significant technical and functional limitations emerged. In particular, the satisfaction and overall experience of the users was impaired by the system's inability to always provide fully accurate information. Moreover, it would often neglect to report relevant information even if present in the materials uploaded and prompt given. Furthermore, it sometimes generated unclickable links, undermining its trustworthiness, since providing the source of information was an important aspect for our users. Further in-depth studies and feedback from other users as well as implementation iterations are planned to refine our Unimib Assistant.
This paper presents the iterative development of Habit Coach, a GPT-based chatbot designed to support users in habit change through personalized interaction. Employing a user-centered design approach, we developed the chatbot using a Retrieval-Augmented Generation (RAG) system, which enables behavior personalization without retraining the underlying language model (GPT-4). The system leverages document retrieval and specialized prompts to tailor interactions, drawing from Cognitive Behavioral Therapy (CBT) and narrative therapy techniques. A key challenge in the development process was the difficulty of translating declarative knowledge into effective interaction behaviors. In the initial phase, the chatbot was provided with declarative knowledge about CBT via reference textbooks and high-level conversational goals. However, this approach resulted in imprecise and inefficient behavior, as the GPT model struggled to convert static information into dynamic and contextually appropriate interactions. This highlighted the limitations of relying solely on declarative knowledge to guide chatbot behavior, particularly in nuanced, therapeutic conversations. Over four iterations, we addressed this issue by gradually transitioning towards procedural knowledge, refining the chatbot's interaction strategies, and improving its overall effectiveness. In the final evaluation, 5 participants engaged with the chatbot over five consecutive days, receiving individualized CBT interventions. The Self-Report Habit Index (SRHI) was used to measure habit strength before and after the intervention, revealing a reduction in habit strength post-intervention. These results underscore the importance of procedural knowledge in driving effective, personalized behavior change support in RAG-based systems.
This paper aims to provide a comparison between texts produced by French and Italian politicians on polarizing issues, such as immigration and the European Union, and their chatbot counterparts created with ChatGPT 3.5. In this study, we focus on implicit communication, in particular on presuppositions and their functions in discourse, which have been considered in the literature as a potential linguistic feature of manipulation. This study also aims to contribute to the emerging literature on the pragmatic competences of Large Language Models.
Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are constrained by the limited availability of unsupervised speech data and parallel speech-text data, which are significantly less abundant than text pre-training data, thereby limiting their scalability as LLMs. We propose a novel approach to scaling speech-text pre-training by leveraging large-scale synthetic interleaved data derived from text corpora, eliminating the need for parallel speech-text datasets. Our method efficiently constructs speech-text interleaved data by sampling text spans from existing text corpora and synthesizing corresponding speech spans using a text-to-token model, bypassing the need to generate actual speech. We also employ a supervised speech tokenizer derived from an automatic speech recognition (ASR) model by incorporating a vector-quantized bottleneck into the encoder. This supervised training approach results in discrete speech tokens with strong semantic preservation even at lower frame rates (e.g. 12.5Hz), while still maintaining speech reconstruction quality. Starting from a pre-trained language model and scaling our pre-training to 1 trillion tokens (with 600B synthetic interleaved speech-text data), we achieve state-of-the-art performance in speech language modeling and spoken question answering, improving performance on spoken questions tasks from the previous SOTA of 13% (Moshi) to 31%. We further demonstrate that by fine-tuning the pre-trained model with speech dialogue data, we can develop an end-to-end spoken chatbot that achieves competitive performance comparable to existing baselines in both conversational abilities and speech quality, even operating exclusively in the speech domain.