arXiv subjects

Yuhan Chen

Publications and source records attributed to Yuhan Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems

Serving systems for Large Language Models (LLMs) are often optimized to improve quality of service (QoS) and throughput. However, due to the lack of open-source LLM serving workloads, these systems are frequently evaluated under unrealistic workload assumptions. Consequently, performance may degrade when systems are deployed in real-world scenarios. This work presents BurstGPT, an LLM serving workload with 10.31 million traces from regional Azure OpenAI GPT services over 213 days. BurstGPT captures LLM serving characteristics from user, model and system perspectives: (1) User request concurrency: burstiness variations of requests in Azure OpenAI GPT services, revealing diversified concurrency patterns in different services and model types. (2) User conversation patterns: counts and intervals within conversations for service optimizations. (3) Model response lengths: auto-regressive serving processes of GPT models, showing statistical relations between requests and their responses. (4) System response failures: failures of conversation and API services, showing intensive resource needs and limited availability of LLM services in Azure. The details of the characteristics can serve multiple purposes in LLM serving optimizations, such as system evaluation and trace provisioning. In our demo evaluation with BurstGPT, frequent variations in BurstGPT reveal declines in efficiency, stability, or reliability in realistic LLM serving. We identify that the generalization of KV cache management, scheduling and disaggregation optimizations can be improved under realistic workload evaluations. BurstGPT is publicly available now at https://github.com/HPMLL/BurstGPT and is widely used to develop prototypes of LLM serving frameworks in the industry.

cs.DC↗

arXiv2025

From Continuous to First-Order-Like: Amorphous-to-Amorphous Transition in Phase-Change Materials

Polymorphism is ubiquitous in crystalline solids. Amorphous solids, such as glassy water and silicon, may undergo amorphous-to-amorphous transitions (AATs). The nature of AATs remains ambiguous, due to diverse system-dependent behaviors and experimental challenges to characterize disordered structures. Here, we identify two ordered motifs in amorphous phase-change materials and monitor their interplay upon pressure-induced AATs. Tuning temperature, we find a crossover from continuous to first-order-like AATs. The crossover emerges at a special pressure-temperature combination, where the AAT encounters a maximum in crystallization rate. Analyzing the two ordered motifs in a two-state model, we draw a phenomenological parallel to the phase transition behavior of supercooled water near its second critical point. This analogy raises an intriguing question regarding the existence of a critical-like point within amorphous solids.

cond-mat.mtrl-sci↗

arXiv2025

Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs

Despite extensive research efforts focused on OOD detection on images, OOD detection on nodes in graph learning remains underexplored. The dependence among graph nodes hinders the trivial adaptation of existing approaches on images that assume inputs to be i.i.d. sampled, since many unique features and challenges specific to graphs are not considered, such as the heterophily issue. Recently, GNNSafe, which considers node dependence, adapted energy-based detection to the graph domain with state-of-the-art performance, however, it has two serious issues: 1) it derives node energy from classification logits without specifically tailored training for modeling data distribution, making it less effective at recognizing OOD data; 2) it highly relies on energy propagation, which is based on homophily assumption and will cause significant performance degradation on heterophilic graphs, where the node tends to have dissimilar distribution with its neighbors. To address the above issues, we suggest training EBMs by MLE to enhance data distribution modeling and remove energy propagation to overcome the heterophily issues. However, training EBMs via MLE requires performing MCMC sampling on both node feature and node neighbors, which is challenging due to the node interdependence and discrete graph topology. To tackle the sampling challenge, we introduce DeGEM, which decomposes the learning process into two parts: a graph encoder that leverages topology information for node representations and an energy head that operates in latent space. Extensive experiments validate that DeGEM, without OOD exposure during training, surpasses previous state-of-the-art methods, achieving an average AUROC improvement of 6.71% on homophilic graphs and 20.29% on heterophilic graphs, and even outperform methods trained with OOD exposure. Our code is available at: https://github.com/draym28/DeGEM.

cs.LG↗

arXiv2024

HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation

Many positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion: tokens farther away from the current position carry less relevant information. We argue that long-term decay is outdated in the era of LLMs, as LLMs are now applied to tasks demanding precise retrieval of in-context information from arbitrary positions. Firstly, we present empirical analyses on various PEs, demonstrating that models inherently learn attention with only a local-decay pattern while forming a U-shape pattern globally, contradicting the principle of long-term decay. Furthermore, we conduct a detailed analysis of rotary position encoding (RoPE, a prevalent relative positional encoding in LLMs), and found that the U-shape attention is caused by some learned components, which are also the key factor limiting RoPE's expressiveness and extrapolation.Inspired by these insights, we propose High-frequency rotary Position Encoding (HoPE). HoPE replaces the specific components in RoPE with position-independent ones, retaining only high-frequency signals, which also breaks the principle of long-term decay in theory. HoPE achieves two major advantages: (1) Without constraints imposed by long-term decay, contradictory factors that limit spontaneous attention optimization and model extrapolation performance are removed. (2) Components representing positions and semantics are are optimized. These enhances model's context awareness and extrapolation, as validated by extensive experiments.

cs.CL↗

arXiv2024

MIN: Multi-channel Interaction Network for Drug-Target Interaction with Protein Distillation

Traditional drug discovery processes are both time-consuming and require extensive professional expertise. With the accumulation of drug-target interaction (DTI) data from experimental studies, leveraging modern machine-learning techniques to discern patterns between drugs and target proteins has become increasingly feasible. In this paper, we introduce the Multi-channel Interaction Network (MIN), a novel framework designed to predict DTIs through two primary components: a representation learning module and a multi-channel interaction module. The representation learning module features a C-Score Predictor-assisted screening mechanism, which selects critical residues to enhance prediction accuracy and reduce noise. The multi-channel interaction module incorporates a structure-agnostic channel, a structure-aware channel, and an extended-mixture channel, facilitating the identification of interaction patterns at various levels for optimal complementarity. Additionally, contrastive learning is utilized to harmonize the representations of diverse data types. Our experimental evaluations on public datasets demonstrate that MIN surpasses other strong DTI prediction methods. Furthermore, the case study reveals a high overlap between the residues selected by the C-Score Predictor and those in actual binding pockets, underscoring MIN's explainability capability. These findings affirm that MIN is not only a potent tool for DTI prediction but also offers fresh insights into the prediction of protein binding sites.

q-bio.QM↗

arXiv2024

An Analysis and Mitigation of the Reversal Curse

Recent research observed a noteworthy phenomenon in large language models (LLMs), referred to as the ``reversal curse.'' The reversal curse is that when dealing with two entities, denoted as $a$ and $b$, connected by their relation $R$ and its inverse $R^{-1}$, LLMs excel in handling sequences in the form of ``$aRb$,'' but encounter challenges when processing ``$bR^{-1}a$,'' whether in generation or comprehension. For instance, GPT-4 can accurately respond to the query ``Tom Cruise's mother is?'' with ``Mary Lee Pfeiffer,'' but it struggles to provide a satisfactory answer when asked ``Mary Lee Pfeiffer's son is?'' In this paper, we undertake the first-ever study of how the reversal curse happens in LLMs. Our investigations reveal that the reversal curse can stem from the specific training objectives, which become particularly evident in the widespread use of next-token prediction within most causal language models. We hope this initial investigation can draw more attention to the reversal curse, as well as other underlying limitations in current LLMs.

cs.CL↗

arXiv2024

Palermo: Improving the Performance of Oblivious Memory using Protocol-Hardware Co-Design

Oblivious RAM (ORAM) hides the memory access patterns, enhancing data privacy by preventing attackers from discovering sensitive information based on the sequence of memory accesses. The performance of ORAM is often limited by its inherent trade-off between security and efficiency, as concealing memory access patterns imposes significant computational and memory overhead. While prior works focus on improving the ORAM performance by prefetching and eliminating ORAM requests, we find that their performance is very sensitive to workload locality behavior and incurs additional management overhead caused by the ORAM stash pressure. This paper presents Palermo: a protocol-hardware co-design to improve ORAM performance. The key observation in Palermo is that classical ORAM protocols enforce restrictive dependencies between memory operations that result in low memory bandwidth utilization. Palermo introduces a new protocol that overlaps large portions of memory operations, within a single and between multiple ORAM requests, without breaking correctness and security guarantees. Subsequently, we propose an ORAM controller architecture that executes the proposed protocol to service ORAM requests. The hardware is responsible for concurrently issuing memory requests as well as imposing the necessary dependencies to ensure a consistent view of the ORAM tree across requests. Using a rich workload mix, we demonstrate that Palermo outperforms the RingORAM baseline by 2.8x, on average, incurring a negligible area overhead of 5.78mm^2 (less than 2% in 12th generation Intel CPU after technology scaling) and 2.14W without sacrificing security. We further show that Palermo also outperforms the state-of-the-art works PageORAM, PrORAM, and IR-ORAM.

cs.CR↗

arXiv2024

Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification

Graph Neural Networks (GNNs) have shown superior performance in node classification. However, GNNs perform poorly in the Few-Shot Node Classification (FSNC) task that requires robust generalization to make accurate predictions for unseen classes with limited labels. To tackle the challenge, we propose the integration of Sharpness-Aware Minimization (SAM)--a technique designed to enhance model generalization by finding a flat minimum of the loss landscape--into GNN training. The standard SAM approach, however, consists of two forward-backward steps in each training iteration, doubling the computational cost compared to the base optimizer (e.g., Adam). To mitigate this drawback, we introduce a novel algorithm, Fast Graph Sharpness-Aware Minimization (FGSAM), that integrates the rapid training of Multi-Layer Perceptrons (MLPs) with the superior performance of GNNs. Specifically, we utilize GNNs for parameter perturbation while employing MLPs to minimize the perturbed loss so that we can find a flat minimum with good generalization more efficiently. Moreover, our method reutilizes the gradient from the perturbation phase to incorporate graph topology into the minimization process at almost zero additional cost. To further enhance training efficiency, we develop FGSAM+ that executes exact perturbations periodically. Extensive experiments demonstrate that our proposed algorithm outperforms the standard SAM with lower computational costs in FSNC tasks. In particular, our FGSAM+ as a SAM variant offers a faster optimization than the base optimizer in most cases. In addition to FSNC, our proposed methods also demonstrate competitive performance in the standard node classification task for heterophilic graphs, highlighting the broad applicability. The code is available at https://github.com/draym28/FGSAM_NeurIPS24.

cs.LG↗

arXiv2024

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness

Many studies have revealed that large language models (LLMs) exhibit uneven awareness of different contextual positions. Their limited context awareness can lead to overlooking critical information and subsequent task failures. While several approaches have been proposed to enhance LLMs' context awareness, achieving both effectiveness and efficiency remains challenging. In this paper, for LLMs utilizing RoPE as position embeddings, we introduce a novel method called "Mixture of In-Context Experts" (MoICE) to address this challenge. MoICE comprises two key components: a router integrated into each attention head within LLMs and a lightweight router-only training optimization strategy: (1) MoICE views each RoPE angle as an `in-context' expert, demonstrated to be capable of directing the attention of a head to specific contextual positions. Consequently, each attention head flexibly processes tokens using multiple RoPE angles dynamically selected by the router to attend to the needed positions. This approach mitigates the risk of overlooking essential contextual information. (2) The router-only training strategy entails freezing LLM parameters and exclusively updating routers for only a few steps. When applied to open-source LLMs including Llama and Mistral, MoICE surpasses prior methods across multiple tasks on long context understanding and generation, all while maintaining commendable inference efficiency.

cs.CL↗

arXiv2024

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

In this paper, we present the first structural binarization method for LLM compression to less than 1-bit precision. Although LLMs have achieved remarkable performance, their memory-bound nature during the inference stage hinders the adoption of resource-constrained devices. Reducing weights to 1-bit precision through binarization substantially enhances computational efficiency. We observe that some weights in binarized LLMs can be randomly flipped without significant performance degradation, suggesting the potential for further compression. To exploit this, our STBLLM employs an N:M sparsity technique to achieve structural binarization of the weights. Specifically, we introduce a novel Standardized Importance (SI) metric, which considers weight magnitude and input feature norm to more accurately assess weight significance. Then, we propose a layer-wise approach, allowing different layers of the LLM to be sparsified with varying N:M ratios, thereby balancing compression and accuracy. Furthermore, we implement a fine-grained grouping strategy for less important weights, applying distinct quantization schemes to sparse, intermediate, and dense regions. Finally, we design a specialized CUDA kernel to support structural binarization. We conduct extensive experiments on LLaMA-1/2/3, OPT family, and Mistral to evaluate the effectiveness of STBLLM. The results demonstrate that our approach performs better than other compressed binarization LLM methods while significantly reducing memory requirements.

cs.LG↗

arXiv2024

Understanding the Performance and Estimating the Cost of LLM Fine-Tuning

Due to the cost-prohibitive nature of training Large Language Models (LLMs), fine-tuning has emerged as an attractive alternative for specializing LLMs for specific tasks using limited compute resources in a cost-effective manner. In this paper, we characterize sparse Mixture of Experts (MoE) based LLM fine-tuning to understand their accuracy and runtime performance on a single GPU. Our evaluation provides unique insights into the training efficacy of sparse and dense versions of MoE models, as well as their runtime characteristics, including maximum batch size, execution time breakdown, end-to-end throughput, GPU hardware utilization, and load distribution. Our study identifies the optimization of the MoE layer as crucial for further improving the performance of LLM fine-tuning. Using our profiling results, we also develop and validate an analytical model to estimate the cost of LLM fine-tuning on the cloud. This model, based on parameters of the model and GPU architecture, estimates LLM throughput and the cost of training, aiding practitioners in industry and academia to budget the cost of fine-tuning a specific model.

cs.CL↗

arXiv2024

YuLan: An Open-source Large Language Model

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports, the lack of training details hinders further research and development. This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters. The base model of YuLan is pre-trained on approximately $1.7$T tokens derived from a diverse corpus, including massive English, Chinese, and multilingual texts. We design a three-stage pre-training method to enhance YuLan's overall capabilities. Subsequent phases of training incorporate instruction-tuning and human alignment, employing a substantial volume of high-quality synthesized data. To facilitate the learning of complex and long-tail knowledge, we devise a curriculum-learning framework throughout across these stages, which helps LLMs learn knowledge in an easy-to-hard manner. YuLan's training is finished on Jan, 2024 and has achieved performance on par with state-of-the-art LLMs across various English and Chinese benchmarks. This paper outlines a comprehensive technical roadmap for developing LLMs from scratch. Our model and codes are available at https://github.com/RUC-GSAI/YuLan-Chat.

cs.CL↗

arXiv2024

Low mach Number Limit of the Viscous and Heat Conductive Flow with general pressure law on torus

We prove the low Mach number limit from compressible Navier-Stokes-Fourier system with the general pressure law around a constant state on the torus $\mathbb{T}^N_a$. We view this limit as a special case of the weakly nonlinear-dissipative approximation of the general hyperbolic-parabolic system with entropy. In particular, we consider the ill-prepared initial data, for which the group of fast acoustic waves is needed to be filtered. This extends the previous works, in particular Danchin [ Amer. J. Math. 124 (2002), 1153-1219] in two ways: 1. We treat the fully general non-isentropic flow, i.e. the pressure depends on the density $ρ$ and temperature $θ$ by basic thermodynamic law. We illustrate the role played by the entropy structure of the system in the coupling of the acoustic waves and incompressible flow, and the construction of the filtering group. 2. We refine the small divisor estimate, which helps us to give the first explicit convergence rate of the filtered acoustic waves whose propogation is governed by non-local averaged system. In previous works, only convergence rate of incompressible limit was obtained.

math.AP↗

arXiv2024

Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning

In this paper, by treating in-context learning (ICL) as a meta-optimization process, we explain why LLMs are sensitive to the order of ICL examples. This understanding leads us to the development of Batch-ICL, an effective, efficient, and order-agnostic inference algorithm for ICL. Differing from the standard N-shot learning approach, Batch-ICL employs $N$ separate 1-shot forward computations and aggregates the resulting meta-gradients. These aggregated meta-gradients are then applied to the forward computation of a zero-shot query to generate the final prediction. This batch processing approach renders the LLM agnostic to the order of ICL examples. Through extensive experiments and analysis, we demonstrate that Batch-ICL consistently outperforms most permutations of ICL examples. In some cases, it even exceeds the performance of the best order for standard ICL, all while reducing the computational resources required. Furthermore, we develop a novel variant of Batch-ICL featuring multiple "epochs" of meta-optimization. This variant implicitly explores permutations of ICL examples, further enhancing ICL performance.

cs.LG↗

arXiv2024

Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use

In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demanding a high degree of context awareness, such as utilizing LLMs for tool-use. Specifically, the crucial information in the context will be potentially overlooked by model when it is positioned in the trough zone of the attention waveform, leading to decreased performance. To address this issue, we propose a novel inference method named Attention Buckets. It allows LLMs to process their input through multiple parallel processes. Each process utilizes a distinct base angle for the rotary position embedding, thereby creating a unique attention waveform. By compensating an attention trough of a particular process with an attention peak of another process, our approach enhances LLM's awareness to various contextual positions, thus mitigating the risk of overlooking crucial information. In the largest tool-use benchmark, our method elevates a 7B model to achieve state-of-the-art performance, comparable to that of GPT-4. On other benchmarks and some RAG tasks, which also demand a thorough understanding of contextual content, Attention Buckets also exhibited notable enhancements in performance.

cs.CL↗

arXiv2024

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models

In this paper, we delve into several mechanisms employed by Transformer-based language models (LLMs) for factual recall tasks. We outline a pipeline consisting of three major steps: (1) Given a prompt ``The capital of France is,'' task-specific attention heads extract the topic token, such as ``France,'' from the context and pass it to subsequent MLPs. (2) As attention heads' outputs are aggregated with equal weight and added to the residual stream, the subsequent MLP acts as an ``activation,'' which either erases or amplifies the information originating from individual heads. As a result, the topic token ``France'' stands out in the residual stream. (3) A deep MLP takes ``France'' and generates a component that redirects the residual stream towards the direction of the correct answer, i.e., ``Paris.'' This procedure is akin to applying an implicit function such as ``get\_capital($X$),'' and the argument $X$ is the topic token information passed by attention heads. To achieve the above quantitative and qualitative analysis for MLPs, we proposed a novel analytic method aimed at decomposing the outputs of the MLP into components understandable by humans. Additionally, we observed a universal anti-overconfidence mechanism in the final layer of models, which suppresses correct predictions. We mitigate this suppression by leveraging our interpretation to improve factual recall confidence. The above interpretations are evaluated across diverse tasks spanning various domains of factual knowledge, using various language models from the GPT-2 families, 1.3B OPT, up to 7B Llama-2, and in both zero- and few-shot setups.

cs.CL↗

arXiv2024

MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability

Large Language Models (LLMs) are increasingly deployed in various applications. As their usage grows, concerns regarding their safety are rising, especially in maintaining harmless responses when faced with malicious instructions. Many defense strategies have been developed to enhance the safety of LLMs. However, our research finds that existing defense strategies lead LLMs to predominantly adopt a rejection-oriented stance, thereby diminishing the usability of their responses to benign instructions. To solve this problem, we introduce the MoGU framework, designed to enhance LLMs' safety while preserving their usability. Our MoGU framework transforms the base LLM into two variants: the usable LLM and the safe LLM, and further employs dynamic routing to balance their contribution. When encountering malicious instructions, the router will assign a higher weight to the safe LLM to ensure that responses are harmless. Conversely, for benign instructions, the router prioritizes the usable LLM, facilitating usable and helpful responses. On various open-sourced LLMs, we compare multiple defense strategies to verify the superiority of our MoGU framework. Besides, our analysis provides key insights into the effectiveness of MoGU and verifies that our designed routing mechanism can effectively balance the contribution of each variant by assigning weights. Our work released the safer Llama2, Vicuna, Falcon, Dolphin, and Baichuan2.

cs.CL↗

arXiv2024

LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering

In this paper, the LCV2 modular method is proposed for the Grounded Visual Question Answering task in the vision-language multimodal domain. This approach relies on a frozen large language model (LLM) as intermediate mediator between the off-the-shelf VQA model and the off-the-shelf visual grounding (VG) model, where the LLM transforms and conveys textual information between the two modules based on a designed prompt. LCV2 establish an integrated plug-and-play framework without the need for any pre-training process. This framework can be deployed for VQA Grounding tasks under low computational resources. The modularized model within the framework allows application with various state-of-the-art pre-trained models, exhibiting significant potential to be advance with the times. Experimental implementations were conducted under constrained computational and memory resources, evaluating the proposed method's performance on benchmark datasets including GQA, CLEVR, and VizWiz-VQA-Grounding. Comparative analyses with baseline methods demonstrate the robust competitiveness of LCV2.

cs.CV↗