Private data, being larger and quality-higher than public data, can greatly improve large language models (LLM). However, due to privacy concerns, this data is often dispersed in multiple silos, making its secure utilization for LLM training a challenge. Federated learning (FL) is an ideal solution for training models with distributed private data, but traditional frameworks like FedAvg are unsuitable for LLM due to their high computational demands on clients. An alternative, split learning, offloads most training parameters to the server while training embedding and output layers locally, making it more suitable for LLM. Nonetheless, it faces significant challenges in security and efficiency. Firstly, the gradients of embeddings are prone to attacks, leading to potential reverse engineering of private data. Furthermore, the server's limitation of handle only one client's training request at a time hinders parallel training, severely impacting training efficiency. In this paper, we propose a Federated Learning framework for LLM, named FL-GLM, which prevents data leakage caused by both server-side and peer-client attacks while improving training efficiency. Specifically, we first place the input block and output block on local client to prevent embedding gradient attacks from server. Secondly, we employ key-encryption during client-server communication to prevent reverse engineering attacks from peer-clients. Lastly, we employ optimization methods like client-batching or server-hierarchical, adopting different acceleration methods based on the actual computational capabilities of the server. Experimental results on NLU and generation tasks demonstrate that FL-GLM achieves comparable metrics to centralized chatGLM model, validating the effectiveness of our federated learning framework.

This paper addresses the growing need for efficient large language models (LLMs) on mobile devices, driven by increasing cloud costs and latency concerns. We focus on designing top-quality LLMs with fewer than a billion parameters, a practical choice for mobile deployment. Contrary to prevailing belief emphasizing the pivotal role of data and parameter quantity in determining model quality, our investigation underscores the significance of model architecture for sub-billion scale LLMs. Leveraging deep and thin architectures, coupled with embedding sharing and grouped-query attention mechanisms, we establish a strong baseline network denoted as MobileLLM, which attains a remarkable 2.7%/4.3% accuracy boost over preceding 125M/350M state-of-the-art models. Additionally, we propose an immediate block-wise weight-sharing approach with no increase in model size and only marginal latency overhead. The resultant models, denoted as MobileLLM-LS, demonstrate a further accuracy enhancement of 0.7%/0.8% than MobileLLM 125M/350M. Moreover, MobileLLM model family shows significant improvements compared to previous sub-billion models on chat benchmarks, and demonstrates close correctness to LLaMA-v2 7B in API calling tasks, highlighting the capability of small models for common on-device use cases.

We present GSM-MC, a multiple-choice (MC) dataset constructed by collecting answers and incorrect predictions on GSM8K from 60 open-source models. Through extensive experiments, we show that LLMs' performance on the MC version of this popular benchmark is strongly correlated with their performance on the original version and is quite robust to distractor choices and option orders, while the evaluation time is reduced by a factor of up to 30. Following similar procedures, we introduce MATH-MC, constructed from MATH, and PythonIO, a new program reasoning MC dataset constructed from HumanEval and MBPP. Experimental results indicate that LLMs' performance on these MC benchmarks leaves much room for improvement. Our data and code are available at https://github.com/Geralt-Targaryen/MC-Evaluation.

Online platforms generate hundreds of billions of dollars in revenue per year by showing advertisements alongside their own content. Currently, these platforms are integrating Large Language Models (LLMs) into their services. This makes revenue generation from LLM-generated content the next major challenge in online advertising. We consider a scenario where advertisers aim to influence the responses of an LLM to align with their interests, while platforms seek to maximize advertiser value and ensure user satisfaction. We introduce an auction mechanism for this problem that operates without LLM fine-tuning or access to model weights and provably converges to the output of the optimally fine-tuned LLM for the platform's objective as computational resources increase. Our mechanism ensures that truthful reporting is a dominant strategy for advertisers and it aligns each advertiser's utility with their contribution to social welfare - an essential feature for long-term viability. Additionally, it can incorporate contextual information about the advertisers, significantly accelerating convergence. Via experiments with a publicly available LLM, we show that our mechanism significantly boosts advertiser value and platform revenue, with low computational overhead. While our motivating application is online advertising, our mechanism can be applied in any setting with monetary transfers, making it a general-purpose solution for truthfully aggregating the preferences of self-interested agents over LLM-generated replies.

Large Language Models (LLMs) have revolutionized the field of Natural Language Generation (NLG) by demonstrating an impressive ability to generate human-like text. However, their widespread usage introduces challenges that necessitate thoughtful examination, ethical scrutiny, and responsible practices. In this study, we delve into these challenges, explore existing strategies for mitigating them, with a particular emphasis on identifying AI-generated text as the ultimate solution. Additionally, we assess the feasibility of detection from a theoretical perspective and propose novel research directions to address the current limitations in this domain.

In this report, we pose the following question: Who is the most intelligent AI model to date, as measured by the OlympicArena (an Olympic-level, multi-discipline, multi-modal benchmark for superintelligent AI)? We specifically focus on the most recently released models: Claude-3.5-Sonnet, Gemini-1.5-Pro, and GPT-4o. For the first time, we propose using an Olympic medal Table approach to rank AI models based on their comprehensive performance across various disciplines. Empirical results reveal: (1) Claude-3.5-Sonnet shows highly competitive overall performance over GPT-4o, even surpassing GPT-4o on a few subjects (i.e., Physics, Chemistry, and Biology). (2) Gemini-1.5-Pro and GPT-4V are ranked consecutively just behind GPT-4o and Claude-3.5-Sonnet, but with a clear performance gap between them. (3) The performance of AI models from the open-source community significantly lags behind these proprietary models. (4) The performance of these models on this benchmark has been less than satisfactory, indicating that we still have a long way to go before achieving superintelligence. We remain committed to continuously tracking and evaluating the performance of the latest powerful models on this benchmark (available at https://github.com/GAIR-NLP/OlympicArena).

Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical application of downstream tasks. Existing parameter-efficient fine-tuning (PEFT) methods such as Low-Rank Adaptation (LoRA) rely on a bypass framework that ignores the differential parameter budget requirements across weight matrices, which may lead to suboptimal fine-tuning outcomes. To address this issue, we introduce the Dynamic Low-Rank Adaptation (DoRA) method. DoRA decomposes high-rank LoRA layers into structured single-rank components, allowing for dynamic pruning of parameter budget based on their importance to specific tasks during training, which makes the most of the limited parameter budget. Experimental results demonstrate that DoRA can achieve competitive performance compared with LoRA and full model fine-tuning, and outperform various strong baselines with the same storage parameter budget. Our code is available at https://github.com/MIkumikumi0116/DoRA

The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention. Existing works mainly adopt the close-ended question-answering (QA) task with answer options for evaluation. However, many clinical decisions involve answering open-ended questions without pre-set options. To better understand LLMs in the clinic, we construct a benchmark ClinicBench. We first collect eleven existing datasets covering diverse clinical language generation, understanding, and reasoning tasks. Furthermore, we construct six novel datasets and complex clinical tasks that are close to real-world practice, i.e., referral QA, treatment recommendation, hospitalization (long document) summarization, patient education, pharmacology QA and drug interaction for emerging drugs. We conduct an extensive evaluation of twenty-two LLMs under both zero-shot and few-shot settings. Finally, we invite medical experts to evaluate the clinical usefulness of LLMs.

In the rapidly evolving landscape of artificial intelligence (AI), the collaboration between human intelligence and AI systems, known as Human-AI (HAI) Teaming, has emerged as a cornerstone for advancing problem-solving and decision-making processes. The advent of Large Pre-trained Models (LPtM) has significantly transformed this landscape, offering unprecedented capabilities by leveraging vast amounts of data to understand and predict complex patterns. This paper surveys the pivotal integration of LPtMs with HAI, emphasizing how these models enhance collaborative intelligence beyond traditional approaches. It examines the potential of LPtMs in augmenting human capabilities, discussing this collaboration for AI model improvements, effective teaming, ethical considerations, and their broad applied implications in various sectors. Through this exploration, the study sheds light on the transformative impact of LPtM-enhanced HAI Teaming, providing insights for future research, policy development, and strategic implementations aimed at harnessing the full potential of this collaboration for research and societal benefit.

Large Language Models (LLMs) have made significant progress in code generation, providing developers with unprecedented automated programming support. However, LLMs often generate code that is syntactically correct and even semantically plausible but may not execute as expected or meet specified requirements. This phenomenon of hallucinations in the code domain has not been systematically explored. To enhance the community's understanding and research on this issue, we introduce the concept of code hallucinations and propose a classification method for code hallucination based on execution verification. We classify code hallucinations into four main types: mapping, naming, resource, and logic hallucinations, with each category further divided into different subcategories to understand and address the unique challenges faced by LLMs in code generation with finer granularity. Additionally, we develop a dynamic detection algorithm named CodeHalu to quantify code hallucinations and establish the CodeHaluEval benchmark, which includes 8,883 samples from 699 tasks to systematically and quantitatively evaluate code hallucinations. By evaluating 17 popular LLMs on this benchmark, we reveal significant differences in their accuracy and reliability in code generation and provide detailed insights for further improving the code generation capabilities of LLMs. The CodeHalu benchmark and code are publicly available at https://github.com/yuchen814/CodeHalu.