arXiv subjects

Juntao Li

Publications and source records attributed to Juntao Li.

At least 73 records · Page 4Linked to original sources

arXiv2025

Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotations

Distantly supervised named entity recognition (DS-NER) has emerged as a cheap and convenient alternative to traditional human annotation methods, enabling the automatic generation of training data by aligning text with external resources. Despite the many efforts in noise measurement methods, few works focus on the latent noise distribution between different distant annotation methods. In this work, we explore the effectiveness and robustness of DS-NER by two aspects: (1) distant annotation techniques, which encompasses both traditional rule-based methods and the innovative large language model supervision approach, and (2) noise assessment, for which we introduce a novel framework. This framework addresses the challenges by distinctly categorizing them into the unlabeled-entity problem (UEP) and the noisy-entity problem (NEP), subsequently providing specialized solutions for each. Our proposed method achieves significant improvements on eight real-world distant supervision datasets originating from three different data sources and involving four distinct annotation techniques, confirming its superiority over current state-of-the-art methods.

cs.CL↗

arXiv2025

Accurate KV Cache Quantization with Outlier Tokens Tracing

The impressive capabilities of Large Language Models (LLMs) come at the cost of substantial computational resources during deployment. While KV Cache can significantly reduce recomputation during inference, it also introduces additional memory overhead. KV Cache quantization presents a promising solution, striking a good balance between memory usage and accuracy. Previous research has shown that the Keys are distributed by channel, while the Values are distributed by token. Consequently, the common practice is to apply channel-wise quantization to the Keys and token-wise quantization to the Values. However, our further investigation reveals that a small subset of unusual tokens exhibit unique characteristics that deviate from this pattern, which can substantially impact quantization accuracy. To address this, we develop a simple yet effective method to identify these tokens accurately during the decoding process and exclude them from quantization as outlier tokens, significantly improving overall accuracy. Extensive experiments show that our method achieves significant accuracy improvements under 2-bit quantization and can deliver a 6.4 times reduction in memory usage and a 2.3 times increase in throughput.

cs.CL↗

arXiv2025

Taming the Titans: A Survey of Efficient LLM Inference Serving

Large Language Models (LLMs) for Generative AI have achieved remarkable progress, evolving into sophisticated and versatile tools widely adopted across various domains and applications. However, the substantial memory overhead caused by their vast number of parameters, combined with the high computational demands of the attention mechanism, poses significant challenges in achieving low latency and high throughput for LLM inference services. Recent advancements, driven by groundbreaking research, have significantly accelerated progress in this field. This paper provides a comprehensive survey of these methods, covering fundamental instance-level approaches, in-depth cluster-level strategies, emerging scenario directions, and other miscellaneous but important areas. At the instance level, we review model placement, request scheduling, decoding length prediction, storage management, and the disaggregation paradigm. At the cluster level, we explore GPU cluster deployment, multi-instance load balancing, and cloud service solutions. For emerging scenarios, we organize the discussion around specific tasks, modules, and auxiliary methods. To ensure a holistic overview, we also highlight several niche yet critical areas. Finally, we outline potential research directions to further advance the field of LLM inference serving.

cs.CL↗

arXiv2025

OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure

Autoregressive language models demonstrate excellent performance in various scenarios. However, the inference efficiency is limited by its one-step-one-word generation mode, which has become a pressing problem recently as the models become increasingly larger. Speculative decoding employs a "draft and then verify" mechanism to allow multiple tokens to be generated in one step, realizing lossless acceleration. Existing methods mainly adopt fixed heuristic draft structures, which fail to adapt to different situations to maximize the acceptance length during verification. To alleviate this dilemma, we proposed OPT-Tree, an algorithm to construct adaptive and scalable draft trees. It searches the optimal tree structure that maximizes the mathematical expectation of the acceptance length in each decoding step. Experimental results reveal that OPT-Tree outperforms the existing draft structures and achieves a speed-up ratio of up to 3.2 compared with autoregressive decoding. If the draft model is powerful enough and the node budget is sufficient, it can generate more than ten tokens in a single step. Our code is available at https://github.com/Jikai0Wang/OPT-Tree.

cs.CL↗

arXiv2025

Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation

Despite recent advances in Large Language Models (LLMs) for code generation, the quality of LLM-generated code still faces significant challenges. One significant issue is code repetition, which refers to the model's tendency to generate structurally redundant code, resulting in inefficiencies and reduced readability. To address this, we conduct the first empirical study to investigate the prevalence and nature of repetition across 19 state-of-the-art code LLMs using three widely-used benchmarks. Our study includes both quantitative and qualitative analyses, revealing that repetition is pervasive and manifests at various granularities and extents, including character, statement, and block levels. We further summarize a taxonomy of 20 repetition patterns. Building on our findings, we propose DeRep, a rule-based technique designed to detect and mitigate repetition in generated code. We evaluate DeRep using both open-source benchmarks and in an industrial setting. Our results demonstrate that DeRep significantly outperforms baselines in reducing repetition (with an average improvements of 91.3%, 93.5%, and 79.9% in rep-3, rep-line, and sim-line metrics) and enhancing code quality (with a Pass@1 increase of 208.3% over greedy search). Furthermore, integrating DeRep improves the performance of existing repetition mitigation methods, with Pass@1 improvements ranging from 53.7% to 215.7%.

cs.SE↗

arXiv2025

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are accessible for verification. However, its extension to broader, less structured domains remains unexplored. In this work, we investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education, where structured reference answers are typically unavailable. We reveal that binary verification judgments on broad-domain tasks exhibit high consistency across various LLMs provided expert-written reference answers exist. Motivated by this finding, we utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications, especially in free-form, unstructured answer scenarios. We further demonstrate the feasibility of training cross-domain generative reward models using relatively small (7B) LLMs without the need for extensive domain-specific annotation. Through comprehensive experiments, our RLVR framework establishes clear performance gains, significantly outperforming state-of-the-art open-source aligned models such as Qwen2.5-72B and DeepSeek-R1-Distill-Qwen-32B across domains in free-form settings. Our approach notably enhances the robustness, flexibility, and scalability of RLVR, representing a substantial step towards practical reinforcement learning applications in complex, noisy-label scenarios.

cs.CL↗

arXiv2025

Stick to Facts: Towards Fidelity-oriented Product Description Generation

Different from other text generation tasks, in product description generation, it is of vital importance to generate faithful descriptions that stick to the product attribute information. However, little attention has been paid to this problem. To bridge this gap, we propose a model named Fidelity-oriented Product Description Generator (FPDG). FPDG takes the entity label of each word into account, since the product attribute information is always conveyed by entity words. Specifically, we first propose a Recurrent Neural Network (RNN) decoder based on the Entity-label-guided Long Short-Term Memory (ELSTM) cell, taking both the embedding and the entity label of each word as input. Second, we establish a keyword memory that stores the entity labels as keys and keywords as values, allowing FPDG to attend to keywords by attending to their entity labels. Experiments conducted on a large-scale real-world product description dataset show that our model achieves state-of-the-art performance in terms of both traditional generation metrics and human evaluations. Specifically, FPDG increases the fidelity of the generated descriptions by 25%.

cs.CL↗

arXiv2025

A Survey on Foundation-Model-Based Industrial Defect Detection

As industrial products become abundant and sophisticated, visual industrial defect detection receives much attention, including two-dimensional and three-dimensional visual feature modeling. Traditional methods use statistical analysis, abnormal data synthesis modeling, and generation-based models to separate product defect features and complete defect detection. Recently, the emergence of foundation models has brought visual and textual semantic prior knowledge. Many methods are based on foundation models (FM) to improve the accuracy of detection, but at the same time, increase model complexity and slow down inference speed. Some FM-based methods have begun to explore lightweight modeling ways, which have gradually attracted attention and deserve to be systematically analyzed. In this paper, we conduct a systematic survey with comparisons and discussions of foundation model methods from different aspects and briefly review non-foundation model (NFM) methods recently published. Furthermore, we discuss the differences between FM and NFM methods from training objectives, model structure and scale, model performance, and potential directions for future exploration. Through comparison, we find FM methods are more suitable for few-shot and zero-shot learning, which are more in line with actual industrial application scenarios and worthy of in-depth research.

cs.CV↗

arXiv2025

Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization

In recent years, large language models (LLMs) have driven advances in natural language processing. Still, their growing scale has increased the computational burden, necessitating a balance between efficiency and performance. Low-rank compression, a promising technique, reduces non-essential parameters by decomposing weight matrices into products of two low-rank matrices. Yet, its application in LLMs has not been extensively studied. The key to low-rank compression lies in low-rank factorization and low-rank dimensions allocation. To address the challenges of low-rank compression in LLMs, we conduct empirical research on the low-rank characteristics of large models. We propose a low-rank compression method suitable for LLMs. This approach involves precise estimation of feature distributions through pooled covariance matrices and a Bayesian optimization strategy for allocating low-rank dimensions. Experiments on the LLaMA-2 models demonstrate that our method outperforms existing strong structured pruning and low-rank compression techniques in maintaining model performance at the same compression ratio.

cs.CL↗

arXiv2025

Revealing and Mitigating Over-Attention in Knowledge Editing

Large Language Models have demonstrated superior performance across a wide range of tasks, but they still exhibit undesirable errors due to incorrect knowledge learned from the training data. To avoid this, knowledge editing methods emerged to precisely edit the specific model knowledge via efficiently modifying a very small percentage of parameters. % However, those methods can lead to the problem of Specificity Failure: when the content related to the edited knowledge occurs in the context, it can inadvertently corrupt other pre-existing knowledge. However, those methods can lead to the problem of Specificity Failure, where the existing knowledge and capabilities are severely degraded due to editing. Our preliminary indicates that Specificity Failure primarily stems from the model's attention heads assigning excessive attention scores to entities related to the edited knowledge, thereby unduly focusing on specific snippets within the context, which we denote as the Attention Drift phenomenon. To mitigate such Attention Drift issue, we introduce a simple yet effective method Selective Attention Drift Restriction}(SADR), which introduces an additional regularization term during the knowledge editing process to restrict changes in the attention weight distribution, thereby preventing undue focus on the edited entity. Experiments on five frequently used strong LLMs demonstrate the effectiveness of our method, where SADR can significantly mitigate Specificity Failure in the predominant knowledge editing tasks.

cs.CL↗

arXiv2025

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Large language models (LLMs) such as OpenAI's o1 have demonstrated remarkable abilities in complex reasoning tasks by scaling test-time compute and exhibiting human-like deep thinking. However, we identify a phenomenon we term underthinking, where o1-like LLMs frequently switch between different reasoning thoughts without sufficiently exploring promising paths to reach a correct solution. This behavior leads to inadequate depth of reasoning and decreased performance, particularly on challenging mathematical problems. To systematically analyze this issue, we conduct experiments on three challenging test sets and two representative open-source o1-like models, revealing that frequent thought switching correlates with incorrect responses. We introduce a novel metric to quantify underthinking by measuring token efficiency in incorrect answers. To address underthinking, we propose a decoding strategy with thought switching penalty TIP that discourages premature transitions between thoughts, encouraging deeper exploration of each reasoning path. Experimental results demonstrate that our approach improves accuracy across challenging datasets without requiring model fine-tuning. Our findings contribute to understanding reasoning inefficiencies in o1-like LLMs and offer a practical solution to enhance their problem-solving capabilities.

cs.CL↗

arXiv2025

Pulse Compression by an Optical Push Broom On a Chip

In this study, we report a first experimental demonstration of pulse compression by a gradual refractive index front moving in a periodically modulated silicon waveguide, the so-called optical push broom effect. Optical push broom captures and confines the input signal pulse in a faster propagating refractive index front, driven by a pump pulse. This is a spatio-temporal analogue of light trapping in a tapered plasmonic waveguide where light is continuously changing its wavevector approaching zero group velocity and, thus, stopped without reflection. Here the signal is accelerated by the front until the signal velocity matches the front velocity, thus stopping the light in respect to the front. We employ the slowly varying envelope approximation to model this phenomenon. Notably, we well reproduced the experimental frequency shift at the output corresponding to the temporal delay at the input.

physics.optics↗

arXiv2025

The Convergence of Dynamic Routing between Capsules

Capsule networks(CapsNet) are recently proposed neural network models with new processing layers, specifically for entity representation and discovery of images. It is well known that CapsNet have some advantages over traditional neural networks, especially in generalization capability. At the same time, some studies report negative experimental results. The causes of this contradiction have not been thoroughly analyzed. The preliminary experimental results show that the behavior of routing algorithms does not always produce good results as expected, and in most cases, different routing algorithms do not change the classification results, but simply polarize the link strength, especially when they continue to repeat without stopping. To realize the true potential of the CapsNet, deep mathematical analysis of the routing algorithms is crucial. In this paper, we will give the objective function that is minimized by the dynamic routing algorithm, which is a concave function. The dynamic routing algorithm can be regarded as nonlinear gradient method to solving an optimization algorithm under linear constraints, and its convergence can be strictly proved mathematically. Furthermore, the mathematically rigorous proof of the convergence is given for this class of iterative routing procedures. We analyze the relation between the objective function and the constraints solved by the dynamic routing algorithm in detail, and perform the corresponding routing experiment to analyze the effect of our convergence proof.

cs.LG↗

arXiv2024

LOGO -- Long cOntext aliGnment via efficient preference Optimization

Long-context models(LCMs) have shown great potential in processing long input sequences(even more than 100M tokens) conveniently and effectively. With significant progress, recent research has pointed out that LCMs can accurately locate token-level salient information within the context. Yet, the generation performance of these LCMs is far from satisfactory and might result in misaligned responses, such as hallucinations. To enhance the generation capability of LCMs, existing works have investigated the effects of data size and quality for both pre-training and instruction tuning. Though achieving meaningful improvement, previous methods fall short in either effectiveness or efficiency. In this paper, we introduce LOGO(Long cOntext aliGnment via efficient preference Optimization), a training strategy that first introduces preference optimization for long-context alignment. To overcome the GPU memory-bound issue caused by the long sequence, LOGO employs a reference-free preference optimization strategy and adopts a position synthesis method to construct the training data. By training with only 0.3B data on a single 8$\times$A800 GPU machine for 16 hours, LOGO allows the Llama-3-8B-Instruct-80K model to achieve comparable performance with GPT-4 in real-world long-context tasks while preserving the model's original capabilities on other tasks, e.g., language modeling and MMLU. Moreover, LOGO can extend the model's context window size while enhancing its generation performance.

cs.CL↗

arXiv2024

Revealing and Mitigating the Local Pattern Shortcuts of Mamba

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an advanced model built upon State Space Models(SSMs) that offers linear complexity and constant memory. Although Mamba is reported to match or surpass the performance of attention-based models, our analysis reveals a performance gap: Mamba excels in tasks that involve localized key information but faces challenges with tasks that require handling distributed key information. Our controlled experiments suggest that this inconsistency arises from Mamba's reliance on local pattern shortcuts, which enable the model to remember local key information within its limited memory but hinder its ability to retain more dispersed information. Therefore, we introduce a global selection module into the Mamba model to address this issue. Experiments on both existing and proposed synthetic tasks, as well as real-world tasks, demonstrate the effectiveness of our method. Notably, with the introduction of only 4M extra parameters, our approach enables the Mamba model(130M) to achieve a significant improvement on tasks with distributed information, increasing its performance from 0 to 80.54 points.

cs.CL↗

arXiv2024

CMD: a framework for Context-aware Model self-Detoxification

Text detoxification aims to minimize the risk of language models producing toxic content. Existing detoxification methods of directly constraining the model output or further training the model on the non-toxic corpus fail to achieve a decent balance between detoxification effectiveness and generation quality. This issue stems from the neglect of constrain imposed by the context since language models are designed to generate output that closely matches the context while detoxification methods endeavor to ensure the safety of the output even if it semantically deviates from the context. In view of this, we introduce a Context-aware Model self-Detoxification~(CMD) framework that pays attention to both the context and the detoxification process, i.e., first detoxifying the context and then making the language model generate along the safe context. Specifically, CMD framework involves two phases: utilizing language models to synthesize data and applying these data for training. We also introduce a toxic contrastive loss that encourages the model generation away from the negative toxic samples. Experiments on various LLMs have verified the effectiveness of our MSD framework, which can yield the best performance compared to baselines.

cs.CL↗

arXiv2024

L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?

Long-context models (LCMs) have made remarkable strides in recent years, offering users great convenience for handling tasks that involve long context, such as document summarization. As the community increasingly prioritizes the faithfulness of generated results, merely ensuring the accuracy of LCM outputs is insufficient, as it is quite challenging for humans to verify the results from the extremely lengthy context. Yet, although some efforts have been made to assess whether LCMs respond truly based on the context, these works either are limited to specific tasks or heavily rely on external evaluation resources like GPT4.In this work, we introduce L-CiteEval, a comprehensive multi-task benchmark for long-context understanding with citations, aiming to evaluate both the understanding capability and faithfulness of LCMs. L-CiteEval covers 11 tasks from diverse domains, spanning context lengths from 8K to 48K, and provides a fully automated evaluation suite. Through testing with 11 cutting-edge closed-source and open-source LCMs, we find that although these models show minor differences in their generated results, open-source models substantially trail behind their closed-source counterparts in terms of citation accuracy and recall. This suggests that current open-source LCMs are prone to responding based on their inherent knowledge rather than the given context, posing a significant risk to the user experience in practical applications. We also evaluate the RAG approach and observe that RAG can significantly improve the faithfulness of LCMs, albeit with a slight decrease in the generation quality. Furthermore, we discover a correlation between the attention mechanisms of LCMs and the citation generation process.

cs.CL↗

arXiv2024

MemLong: Memory-Augmented Retrieval for Long Text Modeling

Recent advancements in Large Language Models (LLMs) have yielded remarkable success across diverse fields. However, handling long contexts remains a significant challenge for LLMs due to the quadratic time and space complexity of attention mechanisms and the growing memory consumption of the key-value cache during generation. This work introduces MemLong: Memory-Augmented Retrieval for Long Text Generation, a method designed to enhance the capabilities of long-context language modeling by utilizing an external retriever for historical information retrieval. MemLong combines a non-differentiable ``ret-mem'' module with a partially trainable decoder-only language model and introduces a fine-grained, controllable retrieval attention mechanism that leverages semantic-level relevant chunks. Comprehensive evaluations on multiple long-context language modeling benchmarks demonstrate that MemLong consistently outperforms other state-of-the-art LLMs. More importantly, MemLong can extend the context length on a single 3090 GPU from 4k up to 80k. Our code is available at https://github.com/Bui1dMySea/MemLong

cs.CL↗