Large language models (LLMs) have enhanced our ability to rapidly analyze and classify unstructured natural language data. However, concerns regarding cost, network limitations, and security constraints have posed challenges for their integration into work processes. In this study, we adopt a systems design approach to employing LLMs as imperfect data annotators for downstream supervised learning tasks, introducing novel system intervention measures aimed at improving classification performance. Our methodology outperforms LLM-generated labels in seven of eight tests, demonstrating an effective strategy for incorporating LLMs into the design and deployment of specialized, supervised learning models present in many industry use cases.

Retrieval augmented generation (RAG) is a process where a large language model (LLM) retrieves useful information from a database and then generates the responses. It is becoming popular in enterprise settings for daily business operations. For example, Copilot for Microsoft 365 has accumulated millions of businesses. However, the security implications of adopting such RAG-based systems are unclear. In this paper, we introduce ConfusedPilot, a class of security vulnerabilities of RAG systems that confuse Copilot and cause integrity and confidentiality violations in its responses. First, we investigate a vulnerability that embeds malicious text in the modified prompt in RAG, corrupting the responses generated by the LLM. Second, we demonstrate a vulnerability that leaks secret data, which leverages the caching mechanism during retrieval. Third, we investigate how both vulnerabilities can be exploited to propagate misinformation within the enterprise and ultimately impact its operations, such as sales and manufacturing. We also discuss the root cause of these attacks by investigating the architecture of a RAG-based system. This study highlights the security vulnerabilities in today's RAG-based systems and proposes design guidelines to secure future RAG-based systems.

Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains. We argue that although the web-crawled data often has formatting errors causing semantic inaccuracies, it can still serve as a valuable source for high-quality supervised fine-tuning in specific domains without relying on advanced models like GPT-4. To this end, we create a paired training dataset automatically by aligning web-crawled data with a smaller set of high-quality data. By training a language model on this dataset, we can convert web data with irregular formats into high-quality ones. Our experiments show that training with the model-transformed data yields better results, surpassing training with only high-quality data by an average score of 9.4% in Chinese math problems. Additionally, our 7B model outperforms several open-source models larger than 32B and surpasses well-known closed-source models such as GPT-3.5, highlighting the efficacy of our approach.

Prognosis prediction is crucial for determining optimal treatment plans for lung cancer patients. Traditionally, such predictions relied on models developed from retrospective patient data. Recently, large language models (LLMs) have gained attention for their ability to process and generate text based on extensive learned knowledge. In this study, we evaluate the potential of GPT-4o mini and GPT-3.5 in predicting the prognosis of lung cancer patients. We collected two prognosis datasets, i.e., survival and post-operative complication datasets, and designed multiple tasks to assess the models' performance comprehensively. Logistic regression models were also developed as baselines for comparison. The experimental results demonstrate that LLMs can achieve competitive, and in some tasks superior, performance in lung cancer prognosis prediction compared to data-driven logistic regression models despite not using additional patient data. These findings suggest that LLMs can be effective tools for prognosis prediction in lung cancer, particularly when patient data is limited or unavailable.

Multimodal large language models (LLMs) have achieved notable success across various domains, while research in the medical field has largely focused on unimodal images. Meanwhile, current general-domain multimodal models for videos still lack the capabilities to understand and engage in conversations about surgical videos. One major contributing factor is the absence of datasets in the surgical field. In this paper, we create a new dataset, Surg-QA, consisting of 102,000 surgical video-instruction pairs, the largest of its kind so far. To build such a dataset, we propose a novel two-stage question-answer generation pipeline with LLM to learn surgical knowledge in a structured manner from the publicly available surgical lecture videos. The pipeline breaks down the generation process into two stages to significantly reduce the task complexity, allowing us to use a more affordable, locally deployed open-source LLM than the premium paid LLM services. It also mitigates the risk of LLM hallucinations during question-answer generation, thereby enhancing the overall quality of the generated data. We further train LLaVA-Surg, a novel vision-language conversational assistant capable of answering open-ended questions about surgical videos, on this Surg-QA dataset, and conduct comprehensive evaluations on zero-shot surgical video question-answering tasks. We show that LLaVA-Surg significantly outperforms all previous general-domain models, demonstrating exceptional multimodal conversational skills in answering open-ended questions about surgical videos. We will release our code, model, and the instruction-tuning dataset.

In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, GPT-4o, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, Llama 3, and Llama 3.1 in solving some selected undergraduate-level transportation engineering problems. We introduce TransportBench, a benchmark dataset that includes a sample of transportation engineering problems on a wide range of subjects in the context of planning, design, management, and control of transportation systems. This dataset is used by human experts to evaluate the capabilities of various commercial and open-sourced LLMs, especially their accuracy, consistency, and reasoning behaviors, in solving transportation engineering problems. Our comprehensive analysis uncovers the unique strengths and limitations of each LLM, e.g. our analysis shows the impressive accuracy and some unexpected inconsistent behaviors of Claude 3.5 Sonnet in solving TransportBench problems. Our study marks a thrilling first step toward harnessing artificial general intelligence for complex transportation challenges.

Although Large Language Models(LLMs) can generate coherent and contextually relevant text, they often struggle to recognise the intent behind the human user's query. Natural Language Understanding (NLU) models, however, interpret the purpose and key information of user's input to enable responsive interactions. Existing NLU models generally map individual utterances to a dual-level semantic frame, involving sentence-level intent and word-level slot labels. However, real-life conversations primarily consist of multi-turn conversations, involving the interpretation of complex and extended dialogues. Researchers encounter challenges addressing all facets of multi-turn dialogue conversations using a unified single NLU model. This paper introduces a novel approach, MIDAS, leveraging a multi-level intent, domain, and slot knowledge distillation for multi-turn NLU. To achieve this, we construct distinct teachers for varying levels of conversation knowledge, namely, sentence-level intent detection, word-level slot filling, and conversation-level domain classification. These teachers are then fine-tuned to acquire specific knowledge of their designated levels. A multi-teacher loss is proposed to facilitate the combination of these multi-level teachers, guiding a student model in multi-turn dialogue tasks. The experimental results demonstrate the efficacy of our model in improving the overall multi-turn conversation understanding, showcasing the potential for advancements in NLU models through the incorporation of multi-level dialogue knowledge distillation techniques.

The performance of ChatGPT\copyright{} and other LLMs has improved tremendously, and in online environments, they are increasingly likely to be used in a wide variety of situations, such as ChatBot on web pages, call center operations using voice interaction, and dialogue functions using agents. In the offline environment, multimodal dialogue functions are also being realized, such as guidance by Artificial Intelligence agents (AI agents) using tablet terminals and dialogue systems in the form of LLMs mounted on robots. In this multimodal dialogue, mutual emotion recognition between the AI and the user will become important. So far, there have been methods for expressing emotions on the part of the AI agent or for recognizing them using textual or voice information of the user's utterances, but methods for AI agents to recognize emotions from the user's facial expressions have not been studied. In this study, we examined whether or not LLM-based AI agents can interact with users according to their emotional states by capturing the user in dialogue with a camera, recognizing emotions from facial expressions, and adding such emotion information to prompts. The results confirmed that AI agents can have conversations according to the emotional state for emotional states with relatively high scores, such as Happy and Angry.

Large language models (LLMs) have emerged as powerful tools in various domains. Recent studies have shown that LLMs can surpass humans in certain tasks, such as predicting the outcomes of neuroscience studies. What role does this leave for humans in the overall decision process? One possibility is that humans, despite performing worse than LLMs, can still add value when teamed with them. A human and machine team can surpass each individual teammate when team members' confidence is well-calibrated and team members diverge in which tasks they find difficult (i.e., calibration and diversity are needed). We simplified and extended a Bayesian approach to combining judgments using a logistic regression framework that integrates confidence-weighted judgments for any number of team members. Using this straightforward method, we demonstrated in a neuroscience forecasting task that, even when humans were inferior to LLMs, their combination with one or more LLMs consistently improved team performance. Our hope is that this simple and effective strategy for integrating the judgments of humans and machines will lead to productive collaborations.

Recent advances in large language models (LLMs) have increased the demand for comprehensive benchmarks to evaluate their capabilities as human-like agents. Existing benchmarks, while useful, often focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes. This lack of granularity makes it difficult to deeply discern where failures stem from. Additionally, setting up these environments requires considerable effort, and issues of unreliability and reproducibility sometimes arise, especially in interactive tasks. To address these limitations, we introduce the Massive Multitask Agent Understanding (MMAU) benchmark, featuring comprehensive offline tasks that eliminate the need for complex environment setups. It evaluates models across five domains, including Tool-use, Directed Acyclic Graph (DAG) QA, Data Science and Machine Learning coding, Contest-level programming and Mathematics, and covers five essential capabilities: Understanding, Reasoning, Planning, Problem-solving, and Self-correction. With a total of 20 meticulously designed tasks encompassing over 3K distinct prompts, MMAU provides a comprehensive framework for evaluating the strengths and limitations of LLM agents. By testing 18 representative models on MMAU, we provide deep and insightful analyses. Ultimately, MMAU not only sheds light on the capabilities and limitations of LLM agents but also enhances the interpretability of their performance. Datasets and evaluation scripts of MMAU are released at https://github.com/apple/axlearn/tree/main/docs/research/mmau.