Deploying large language model inference remains challenging due to their high computational overhead. Early exiting accelerates model inference by adaptively reducing the number of inference layers. Existing methods require training internal classifiers to determine whether to exit at each intermediate layer. However, such classifier-based early exiting frameworks require significant effort to design and train the classifiers. To address these limitations, this paper proposes RAEE, a training-free Retrieval-Augmented Early Exiting framework for efficient inference. First, this paper demonstrates that the early exiting problem can be modeled as a distribution prediction problem, where the distribution is approximated using similar data's existing information. Next, the paper details the process of collecting existing information to build the retrieval database. Finally, based on the pre-built retrieval database, RAEE leverages the retrieved similar data's exiting information to guide the backbone model to exit at the layer, which is predicted by the approximated distribution. Experimental results demonstrate that the proposed RAEE can significantly accelerate inference. RAEE also achieves state-of-the-art zero-shot performance on 8 classification tasks.
相關內容
While extensive research has explored the use of large language models (LLMs) for table-based reasoning, most approaches struggle with scalability when applied to large tables. To maintain the superior comprehension abilities of LLMs in these scenarios, we introduce ALTER(Augmentation for Large-Table-Based Reasoning)-a framework designed to harness the latent augmentation potential in both free-form natural language (NL) questions, via the query augmentor, and semi-structured tabular data, through the table augmentor. By utilizing only a small subset of relevant data from the table and supplementing it with pre-augmented schema, semantic, and literal information, ALTER achieves outstanding performance on table-based reasoning benchmarks. We also provide a detailed analysis of large-table scenarios, comparing different methods and various partitioning principles. In these scenarios, our method outperforms all other approaches and exhibits robustness and efficiency against perturbations.
Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging and domain-specific task, such as finance, has not been fully explored. In this paper, we present CFinBench: a meticulously crafted, the most comprehensive evaluation benchmark to date, for assessing the financial knowledge of LLMs under Chinese context. In practice, to better align with the career trajectory of Chinese financial practitioners, we build a systematic evaluation from 4 first-level categories: (1) Financial Subject: whether LLMs can memorize the necessary basic knowledge of financial subjects, such as economics, statistics and auditing. (2) Financial Qualification: whether LLMs can obtain the needed financial qualified certifications, such as certified public accountant, securities qualification and banking qualification. (3) Financial Practice: whether LLMs can fulfill the practical financial jobs, such as tax consultant, junior accountant and securities analyst. (4) Financial Law: whether LLMs can meet the requirement of financial laws and regulations, such as tax law, insurance law and economic law. CFinBench comprises 99,100 questions spanning 43 second-level categories with 3 question types: single-choice, multiple-choice and judgment. We conduct extensive experiments of 50 representative LLMs with various model size on CFinBench. The results show that GPT4 and some Chinese-oriented models lead the benchmark, with the highest average accuracy being 60.16%, highlighting the challenge presented by CFinBench. The dataset and evaluation code are available at //cfinbench.github.io/.
We consider the problem of novel-view synthesis (NVS) for dynamic scenes. Recent neural approaches have accomplished exceptional NVS results for static 3D scenes, but extensions to 4D time-varying scenes remain non-trivial. Prior efforts often encode dynamics by learning a canonical space plus implicit or explicit deformation fields, which struggle in challenging scenarios like sudden movements or generating high-fidelity renderings. In this paper, we introduce 4D Gaussian Splatting (4DRotorGS), a novel method that represents dynamic scenes with anisotropic 4D XYZT Gaussians, inspired by the success of 3D Gaussian Splatting in static scenes. We model dynamics at each timestamp by temporally slicing the 4D Gaussians, which naturally compose dynamic 3D Gaussians and can be seamlessly projected into images. As an explicit spatial-temporal representation, 4DRotorGS demonstrates powerful capabilities for modeling complicated dynamics and fine details--especially for scenes with abrupt motions. We further implement our temporal slicing and splatting techniques in a highly optimized CUDA acceleration framework, achieving real-time inference rendering speeds of up to 277 FPS on an RTX 3090 GPU and 583 FPS on an RTX 4090 GPU. Rigorous evaluations on scenes with diverse motions showcase the superior efficiency and effectiveness of 4DRotorGS, which consistently outperforms existing methods both quantitatively and qualitatively.
The scalability of large language models (LLMs) in handling high-complexity models and large-scale datasets has led to tremendous successes in pivotal domains. While there is an urgent need to acquire more training data for LLMs, a concerning reality is the depletion of high-quality public datasets within a few years. In view of this, the federated learning (FL) LLM fine-tuning paradigm recently has been proposed to facilitate collaborative LLM fine-tuning on distributed private data, where multiple data owners collaboratively fine-tune a shared LLM without sharing raw data. However, the staggering model size of LLMs imposes heavy computing and communication burdens on clients, posing significant barriers to the democratization of the FL LLM fine-tuning paradigm. To address this issue, split learning (SL) has emerged as a promising solution by offloading the primary training workload to a server via model partitioning while exchanging activation/activation's gradients with smaller data sizes rather than the entire LLM. Unfortunately, research on the SL LLM fine-tuning paradigm is still in its nascent stage. To fill this gap, in this paper, we propose the first SL LLM fine-tuning framework, named SplitLoRA. SplitLoRA is built on the split federated learning (SFL) framework, amalgamating the advantages of parallel training from FL and model splitting from SL and thus greatly enhancing the training efficiency. It is worth noting that SplitLoRA is the inaugural open-source benchmark for SL LLM fine-tuning, providing a foundation for research efforts dedicated to advancing SL LLM fine-tuning. Extensive simulations validate that SplitLoRA achieves target accuracy in significantly less time than state-of-the-art LLM fine-tuning frameworks, demonstrating the superior training performance of SplitLoRA. The project page is available at //fduinc.github.io/splitlora/.
The increasing adoption of large language models (LLMs) has created a pressing need for an efficient, secure and private serving infrastructure, which allows researchers to run open-source or custom fine-tuned LLMs and ensures users that their data remains private and is not stored without their consent. While high-performance computing (HPC) systems equipped with state-of-the-art GPUs are well-suited for training LLMs, their batch scheduling paradigm is not designed to support real-time serving of AI applications. Cloud systems, on the other hand, are well suited for web services but commonly lack access to the computational power of clusters, especially expensive and scarce high-end GPUs, which are required for optimal inference speed. We propose an architecture with an implementation consisting of a web service that runs on a cloud VM with secure access to a scalable backend running a multitude of AI models on HPC systems. By offering a web service using our HPC infrastructure to host LLMs, we leverage the trusted environment of local universities and research centers to offer a private and secure alternative to commercial LLM services. Our solution natively integrates with Slurm, enabling seamless deployment on HPC clusters and is able to run side by side with regular Slurm workloads, while utilizing gaps in the schedule created by Slurm. In order to ensure the security of the HPC system, we use the SSH ForceCommand directive to construct a robust circuit breaker, which prevents successful attacks on the web-facing server from affecting the cluster. We have successfully deployed our system as a production service, and made the source code available at //github.com/gwdg/chat-ai
Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. Therefore, understanding and explaining these models is crucial for elucidating their behaviors, limitations, and social impacts. In this paper, we introduce a taxonomy of explainability techniques and provide a structured overview of methods for explaining Transformer-based language models. We categorize techniques based on the training paradigms of LLMs: traditional fine-tuning-based paradigm and prompting-based paradigm. For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge. We also discuss metrics for evaluating generated explanations, and discuss how explanations can be leveraged to debug models and improve performance. Lastly, we examine key challenges and emerging opportunities for explanation techniques in the era of LLMs in comparison to conventional machine learning models.
The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in self-optimizing their decision-making. By introspectively examining trajectories, LLM refines its policy by generating succinct and valuable tips. Our method enhances the agent's performance in both few-shot and zero-shot learning situations by considering three essential scenarios: learning from the agent's past experiences, integrating expert demonstrations, and generalizing across diverse games. Importantly, we accomplish these improvements without fine-tuning the LLM parameters; rather, we adjust the prompt to generalize insights from the three aforementioned situations. Our framework not only supports but also emphasizes the advantage of employing LLM in in-contxt decision-making. Experiments involving over 100 games in TextWorld illustrate the superior performance of our approach.
Visual dialogue is a challenging task that needs to extract implicit information from both visual (image) and textual (dialogue history) contexts. Classical approaches pay more attention to the integration of the current question, vision knowledge and text knowledge, despising the heterogeneous semantic gaps between the cross-modal information. In the meantime, the concatenation operation has become de-facto standard to the cross-modal information fusion, which has a limited ability in information retrieval. In this paper, we propose a novel Knowledge-Bridge Graph Network (KBGN) model by using graph to bridge the cross-modal semantic relations between vision and text knowledge in fine granularity, as well as retrieving required knowledge via an adaptive information selection mode. Moreover, the reasoning clues for visual dialogue can be clearly drawn from intra-modal entities and inter-modal bridges. Experimental results on VisDial v1.0 and VisDial-Q datasets demonstrate that our model outperforms exiting models with state-of-the-art results.
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an input text with masked tokens, we rely on conventional masks to learn inter-relations between corrupted tokens and context via autoencoding, and pseudo masks to learn intra-relations between masked spans via partially autoregressive modeling. With well-designed position embeddings and self-attention masks, the context encodings are reused to avoid redundant computation. Moreover, conventional masks used for autoencoding provide global masking information, so that all the position embeddings are accessible in partially autoregressive language modeling. In addition, the two tasks pre-train a unified language model as a bidirectional encoder and a sequence-to-sequence decoder, respectively. Our experiments show that the unified language models pre-trained using PMLM achieve new state-of-the-art results on a wide range of natural language understanding and generation tasks across several widely used benchmarks.
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy. In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. Furthermore, XLNet integrates ideas from Transformer-XL, the state-of-the-art autoregressive model, into pretraining. Empirically, XLNet outperforms BERT on 20 tasks, often by a large margin, and achieves state-of-the-art results on 18 tasks including question answering, natural language inference, sentiment analysis, and document ranking.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191