PyTorchKR Papers

최신 논문

총 15,266편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2312.07250공식 코드 · Papers with Code

Neural Machine Translation of Clinical Text: An Empirical Investigation into Multilingual Pre-Trained Language Models and Transfer-Learning

We conduct investigations on clinical text machine translation by examining multilingual neural network models using deep learning such as Transformer based structures. Furthermore, to address the language resource imbalance issue, we also carry out experiments using a transfer learning methodology based on massive multilingual pre-trained language models (MMPLMs). The experimental results on three subtasks including 1) clinical case (CC), 2) clinical terminology (CT), and 3) ontological concept (OC) show that our models achieved top-level performances in the ClinSpEn-2022 shared task on English-Spanish clinical domain data. Furthermore, our expert-based human evaluations demonstrate that the small-sized pre-trained language model (PLM) won over the other two extra-large language models by a large margin, in the clinical domain fine-tuning, which finding was never reported in the field. Finally, the transfer learning method works well in our experimental setting using the WMT21fb model to accommodate a new language space Spanish that was not seen at the pre-training stage within WMT21fb itself, which deserves more exploitation for clinical knowledge transformation, e.g. to investigate into more languages. These research findings can shed some light on domain-specific machine translation development, especially in clinical and healthcare fields. Further research projects can be carried out based on our work to improve healthcare text analytics and knowledge transformation. Our data will be openly available for research purposes at https://github.com/HECTA-UoM/ClinicalNMT

arXiv:2312.07104공식 코드 · Papers with Code

SGLang: Efficient Execution of Structured Language Model Programs

Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming and executing these applications. We introduce SGLang, a system for efficient execution of complex language model programs. SGLang consists of a frontend language and a runtime. The frontend simplifies programming with primitives for generation and parallelism control. The runtime accelerates execution with novel optimizations like RadixAttention for KV cache reuse and compressed finite state machines for faster structured output decoding. Experiments show that SGLang achieves up to 6.4x higher throughput compared to state-of-the-art inference systems on various large language and multi-modal models on tasks including agent control, logical reasoning, few-shot learning benchmarks, JSON decoding, retrieval-augmented generation pipelines, and multi-turn chat. The code is publicly available at https://github.com/sgl-project/sglang

arXiv:2312.06974

SM70: A Large Language Model for Medical Devices

We are introducing SM70, a 70 billion-parameter Large Language Model that is specifically designed for SpassMed's medical devices under the brand name 'JEE1' (pronounced as G1 and means 'Life'). This large language model provides more accurate and safe responses to medical-domain questions. To fine-tune SM70, we used around 800K data entries from the publicly available dataset MedAlpaca. The Llama2 70B open-sourced model served as the foundation for SM70, and we employed the QLoRA technique for fine-tuning. The evaluation is conducted across three benchmark datasets - MEDQA - USMLE, PUBMEDQA, and USMLE - each representing a unique aspect of medical knowledge and reasoning. The performance of SM70 is contrasted with other notable LLMs, including Llama2 70B, Clinical Camel 70 (CC70), GPT 3.5, GPT 4, and Med-Palm, to provide a comparative understanding of its capabilities within the medical domain. Our results indicate that SM70 outperforms several established models in these datasets, showcasing its proficiency in handling a range of medical queries, from fact-based questions derived from PubMed abstracts to complex clinical decision-making scenarios. The robust performance of SM70, particularly in the USMLE and PUBMEDQA datasets, suggests its potential as an effective tool in clinical decision support and medical information retrieval. Despite its promising results, the paper also acknowledges the areas where SM70 lags behind the most advanced model, GPT 4, thereby highlighting the need for further development, especially in tasks demanding extensive medical knowledge and intricate reasoning.

arXiv:2312.06172

Decoupling SQL Query Hardness Parsing for Text-to-SQL

The fundamental goal of the Text-to-SQL task is to translate natural language question into SQL query. Current research primarily emphasizes the information coupling between natural language questions and schemas, and significant progress has been made in this area. The natural language questions as the primary task requirements source determines the hardness of correspond SQL queries, the correlation between the two always be ignored. However, when the correlation between questions and queries was decoupled, it may simplify the task. In this paper, we introduce an innovative framework for Text-to-SQL based on decoupling SQL query hardness parsing. This framework decouples the Text-to-SQL task based on query hardness by analyzing questions and schemas, simplifying the multi-hardness task into a single-hardness challenge. This greatly reduces the parsing pressure on the language model. We evaluate our proposed framework and achieve a new state-of-the-art performance of fine-turning methods on Spider dev.

arXiv:2312.06099

Generative Large Language Models Are All-purpose Text Analytics Engines: Text-to-text Learning Is All Your Need

Objective To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning. Methods We formulated 7 key clinical NLP tasks as text-to-text learning and solved them using one unified generative clinical LLM, GatorTronGPT, developed using GPT-3 architecture and trained with up to 20 billion parameters. We adopted soft prompts (i.e., trainable vectors) with frozen LLM, where the LLM parameters were not updated (i.e., frozen) and only the vectors of soft prompts were updated, known as prompt tuning. We added additional soft prompts as a prefix to the input layer, which were optimized during the prompt tuning. We evaluated the proposed method using 7 clinical NLP tasks and compared them with previous task-specific solutions based on Transformer models. Results and Conclusion The proposed approach achieved state-of-the-art performance for 5 out of 7 major clinical NLP tasks using one unified generative LLM. Our approach outperformed previous task-specific transformer models by ~3% for concept extraction and 7% for relation extraction applied to social determinants of health, 3.4% for clinical concept normalization, 3.4~10% for clinical abbreviation disambiguation, and 5.5~9% for natural language inference. Our approach also outperformed a previously developed prompt-based machine reading comprehension (MRC) model, GatorTron-MRC, for clinical concept and relation extraction. The proposed approach can deliver the ``one model for all`` promise from training to deployment using a unified generative LLM.

arXiv:2312.05497공식 코드 · Papers with Code

History Matters: Temporal Knowledge Editing in Large Language Model

The imperative task of revising or updating the knowledge stored within large language models arises from two distinct sources: intrinsic errors inherent in the model which should be corrected and outdated knowledge due to external shifts in the real world which should be updated. Prevailing efforts in model editing conflate these two distinct categories of edits arising from distinct reasons and directly modify the original knowledge in models into new knowledge. However, we argue that preserving the model's original knowledge remains pertinent. Specifically, if a model's knowledge becomes outdated due to evolving worldly dynamics, it should retain recollection of the historical knowledge while integrating the newfound knowledge. In this work, we introduce the task of Temporal Knowledge Editing (TKE) and establish a benchmark AToKe (Assessment of TempOral Knowledge Editing) to evaluate current model editing methods. We find that while existing model editing methods are effective at making models remember new knowledge, the edited model catastrophically forgets historical knowledge. To address this gap, we propose a simple and general framework termed Multi-Editing with Time Objective (METO) for enhancing existing editing models, which edits both historical and new knowledge concurrently and optimizes the model's prediction for the time of each fact. Our assessments demonstrate that while AToKe is still difficult, METO maintains the effectiveness of learning new knowledge and meanwhile substantially improves the performance of edited models on utilizing historical knowledge.

arXiv:2312.05483

Teamwork Dimensions Classification Using BERT

Teamwork is a necessary competency for students that is often inadequately assessed. Towards providing a formative assessment of student teamwork, an automated natural language processing approach was developed to identify teamwork dimensions of students' online team chat. Developments in the field of natural language processing and artificial intelligence have resulted in advanced deep transfer learning approaches namely the Bidirectional Encoder Representations from Transformers (BERT) model that allow for more in-depth understanding of the context of the text. While traditional machine learning algorithms were used in the previous work for the automatic classification of chat messages into the different teamwork dimensions, our findings have shown that classifiers based on the pre-trained language model BERT provides improved classification performance, as well as much potential for generalizability in the language use of varying team chat contexts and team member demographics. This model will contribute towards an enhanced learning analytics tool for teamwork assessment and feedback.

arXiv:2312.05448

Domain Adaptation of a State of the Art Text-to-SQL Model: Lessons Learned and Challenges Found

There are many recent advanced developments for the Text-to-SQL task, where the Picard model is one of the the top performing models as measured by the Spider dataset competition. However, bringing Text-to-SQL systems to realistic use-cases through domain adaptation remains a tough challenge. We analyze how well the base T5 Language Model and Picard perform on query structures different from the Spider dataset, we fine-tuned the base model on the Spider data and on independent databases (DB). To avoid accessing the DB content online during inference, we also present an alternative way to disambiguate the values in an input question using a rule-based approach that relies on an intermediate representation of the semantic concepts of an input question. In our results we show in what cases T5 and Picard can deliver good performance, we share the lessons learned, and discuss current domain adaptation challenges.

arXiv:2312.06355

Linguistic and Structural Basis of Engineering Design Knowledge

Natural language artefact descriptions are primary carriers of engineering design knowledge, whose retrieval, representation, and reuse are fundamental to supporting knowledge-intensive tasks in the design process. In this paper, we explicate design knowledge from patented artefact descriptions as knowledge graphs and examine these to understand the linguistic and structural basis. The purpose of our work is to advance the traditional and ontological perspectives of design knowledge and to guide Large-Language Models (LLMs) on how to articulate natural language responses that reflect knowledge that is valuable in a design environment. We populate 33,881 knowledge graphs from a sample of patents stratified according to technology classes. For linguistic basis, we conduct Zipf distribution analyses on the frequencies of unique entities and relationships to identify 64 and 37 generalisable linguistic syntaxes respectively. The relationships largely represent attributes ('of'), structure ('in', 'with'), purpose ('to', 'for'), hierarchy ('include'), exemplification ('such as'), and behaviour ('to', 'from'). For structural basis, we draw inspiration from various studies on biological/ecological networks and discover motifs from patent knowledge graphs. We identify four 3-node and four 4-node subgraph patterns that could be converged and simplified into sequence [->...->], aggregation [->...<-], and hierarchy [<-...->]. Based on these results, we suggest concretisation strategies for entities and relationships and explicating hierarchical structures, potentially aiding the construction and modularisation of design knowledge.

arXiv:2312.05585

Enhancing Medical Specialty Assignment to Patients using NLP Techniques

The introduction of Large Language Models (LLMs), and the vast volume of publicly available medical data, amplified the application of NLP to the medical domain. However, LLMs are pretrained on data that are not explicitly relevant to the domain that are applied to and are often biased towards the original data they were pretrained upon. Even when pretrained on domainspecific data, these models typically require time-consuming fine-tuning to achieve good performance for a specific task. To address these limitations, we propose an alternative approach that achieves superior performance while being computationally efficient. Specifically, we utilize keywords to train a deep learning architecture that outperforms a language model pretrained on a large corpus of text. Our proposal does not require pretraining nor fine-tuning and can be applied directly to a specific setting for performing multi-label classification. Our objective is to automatically assign a new patient to the specialty of the medical professional they require, using a dataset that contains medical transcriptions and relevant keywords. To this end, we fine-tune the PubMedBERT model on this dataset, which serves as the baseline for our experiments. We then twice train/fine-tune a DNN and the RoBERTa language model, using both the keywords and the full transcriptions as input. We compare the performance of these approaches using relevant metrics. Our results demonstrate that utilizing keywords for text classification significantly improves classification performance, for both a basic DL architecture and a large language model. Our approach represents a promising and efficient alternative to traditional methods for finetuning language models on domain-specific data and has potential applications in various medical domains

arXiv:2312.05516

Stateful Large Language Model Serving with Pensieve

Large Language Models (LLMs) are wildly popular today and it is important to serve them efficiently. Existing LLM serving systems are stateless across requests. Consequently, when LLMs are used in the common setting of multi-turn conversations, a growing log of the conversation history must be processed alongside any request by the serving system at each turn, resulting in repeated processing. In this paper, we design $Pensieve$, a system optimized for multi-turn conversation LLM serving. $Pensieve$ maintains the conversation state across requests by caching previously processed history to avoid duplicate processing. $Pensieve$'s multi-tier caching strategy can utilize both GPU and CPU memory to efficiently store and retrieve cached data. $Pensieve$ also generalizes the recent PagedAttention kernel to support attention between multiple input tokens with a GPU cache spread over non-contiguous memory. Our evaluation shows that $Pensieve$ can achieve $1.14$-$3.0\times$ the throughput of vLLM and TensorRT-LLM and significantly reduce latency.

arXiv:2312.05356

Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation

Language Models (LMs) have become widely used in software engineering, especially for tasks such as code generation, where they are referred to as code LMs. These models have proven effective in generating code, making it easier for developers to automate coding activities. However, research has highlighted a significant limitation: despite their effectiveness, LMs often produce code that is incorrect, buggy, or not fully functional. Updating these models with limited data can be prohibitively challenging, yet it is essential to maximize their utility. This may require hot-fix techniques (updating models with limited data) to resolve. In this paper, we propose \ul{M}odel \ul{I}mprovement via \ul{N}euron \ul{T}argeting (\textsc{MINT}), a novel approach for repairing code LMs. MINT leverages the semantic property of language models to perform neuron-level repairs in a novel way. Further, by analyzing the relationships between the model's latent representations, the incorrect outputs, and the desired outputs, \textsc{MINT} determines which neurons are worth updating. This approach ensures that only the neurons crucial to the model's failure are targeted, avoiding unnecessary changes and allowing for a more efficient and precise repair process. \textsc{MINT} is effective, efficient, and reliable, capable of correcting a neural model by patching a minimum number of neurons (usually one or two neurons). Our approach is evaluated on three coding tasks: line-level code generation, shellcode generation, and intent-to-bash translation. The experimental results demonstrate that the proposed approach significantly outperforms the state-of-the-art in both effectiveness and efficiency measures. In addition, we analyze and discuss the side effects of model repair techniques, including the balance between generalization and specificity, and the performance after multiple repairs in succession.

arXiv:2312.06635공식 코드 · Papers with Code

Gated Linear Attention Transformers with Hardware-Efficient Training

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention generally underperforms ordinary softmax attention. Moreover, current implementations of linear attention lack I/O-awareness and are thus slower than highly optimized implementations of softmax attention. This work describes a hardware-efficient algorithm for linear attention that trades off memory movement against parallelizability. The resulting implementation, dubbed FLASHLINEARATTENTION, is faster than FLASHATTENTION-2 (Dao, 2023) as a standalone layer even on short sequence lengths (e.g., 1K). We then generalize this algorithm to a more expressive variant of linear attention with data-dependent gates. When used as a replacement for the standard attention layer in Transformers, the resulting gated linear attention (GLA) Transformer is found to perform competitively against the LLaMA-architecture Transformer (Touvron et al., 2023) as well recent linear-time-inference baselines such as RetNet (Sun et al., 2023a) and Mamba (Gu & Dao, 2023) on moderate-scale language modeling experiments. GLA Transformer is especially effective at length generalization, enabling a model trained on 2K to generalize to sequences longer than 20K without significant perplexity degradations. For training speed, the GLA Transformer has higher throughput than a similarly-sized Mamba model.

arXiv:2312.06134

Order Matters in the Presence of Dataset Imbalance for Multilingual Learning

In this paper, we empirically study the optimization dynamics of multi-task learning, particularly focusing on those that govern a collection of tasks with significant data imbalance. We present a simple yet effective method of pre-training on high-resource tasks, followed by fine-tuning on a mixture of high/low-resource tasks. We provide a thorough empirical study and analysis of this method's benefits showing that it achieves consistent improvements relative to the performance trade-off profile of standard static weighting. We analyze under what data regimes this method is applicable and show its improvements empirically in neural machine translation (NMT) and multi-lingual language modeling.

arXiv:2312.06122공식 코드 · Papers with Code

GTA: Gated Toxicity Avoidance for LM Performance Preservation

Caution: This paper includes offensive words that could potentially cause unpleasantness. The fast-paced evolution of generative language models such as GPT-4 has demonstrated outstanding results in various NLP generation tasks. However, due to the potential generation of offensive words related to race or gender, various Controllable Text Generation (CTG) methods have been proposed to mitigate the occurrence of harmful words. However, existing CTG methods not only reduce toxicity but also negatively impact several aspects of the language model's generation performance, including topic consistency, grammar, and perplexity. This paper explores the limitations of previous methods and introduces a novel solution in the form of a simple Gated Toxicity Avoidance (GTA) that can be applied to any CTG method. We also evaluate the effectiveness of the proposed GTA by comparing it with state-of-the-art CTG methods across various datasets. Our findings reveal that gated toxicity avoidance efficiently achieves comparable levels of toxicity reduction to the original CTG methods while preserving the generation performance of the language model.

arXiv:2312.05605

TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence Processing

MEGA is a recent transformer-based architecture, which utilizes a linear recurrent operator whose parallel computation, based on the FFT, scales as $O(LlogL)$, with $L$ being the sequence length. We build upon their approach by replacing the linear recurrence with a special temporal convolutional network which permits larger receptive field size with shallower networks, and reduces the computational complexity to $O(L)$. The resulting model is called TCNCA, a Temporal Convolutional Network with Chunked Attention. We evaluate TCNCA on EnWik8 language modeling, long-range-arena (LRA) sequence classification, as well as a synthetic reasoning benchmark associative recall. On EnWik8, TCNCA outperforms MEGA, reaching a lower loss with $1.37\times$/$1.24\times$ faster forward/backward pass during training. The dilated convolutions used in TCNCA are consistently and significantly faster operations than the FFT-based parallelized recurrence in GPUs, making them a scalable candidate for handling very large sequence lengths: they are up to $7.07\times$/$2.86\times$ faster in the forward/backward pass for sequences up to 131k. Further on LRA, TCNCA achieves, on average, $1.28\times$ speed-up during inference with similar accuracy to what MEGA achieves. On associative recall, we find that even a simplified version of TCNCA, without excessive multiplicative and additive interactions, remains superior or competitive to MEGA on a range of sequence lengths and vocabulary sizes.

arXiv:2312.06093공식 코드 · Papers with Code

PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models

The proliferation of social media has given rise to a new form of communication: memes. Memes are multimodal and often contain a combination of text and visual elements that convey meaning, humor, and cultural significance. While meme analysis has been an active area of research, little work has been done on unsupervised multimodal topic modeling of memes, which is important for content moderation, social media analysis, and cultural studies. We propose \textsf{PromptMTopic}, a novel multimodal prompt-based model designed to learn topics from both text and visual modalities by leveraging the language modeling capabilities of large language models. Our model effectively extracts and clusters topics learned from memes, considering the semantic interaction between the text and visual modalities. We evaluate our proposed model through extensive experiments on three real-world meme datasets, which demonstrate its superiority over state-of-the-art topic modeling baselines in learning descriptive topics in memes. Additionally, our qualitative analysis shows that \textsf{PromptMTopic} can identify meaningful and culturally relevant topics from memes. Our work contributes to the understanding of the topics and themes of memes, a crucial form of communication in today's society.\\ \red{\textbf{Disclaimer: This paper contains sensitive content that may be disturbing to some readers.}}

arXiv:2312.05777공식 코드 · Papers with Code

Negative Pre-aware for Noisy Cross-modal Matching

Cross-modal noise-robust learning is a challenging task since noisy correspondence is hard to recognize and rectify. Due to the cumulative and unavoidable negative impact of unresolved noise, existing methods cannot maintain a stable performance when the noise increases. In this paper, we present a novel Negative Pre-aware Cross-modal (NPC) matching solution for large visual-language model fine-tuning on noisy downstream tasks. It is featured in two aspects: (1) For noise recognition and resistance, previous methods usually directly filter out a noise subset, we propose to estimate the negative impact of each sample. It does not need additional correction mechanisms that may predict unreliable correction results, leading to self-reinforcing error. We assign a confidence weight to each sample according to its negative impact in the training process. This adaptively adjusts the contribution of each sample to avoid noisy accumulation. (2) For maintaining stable performance with increasing noise, we utilize the memorization effect of DNNs by maintaining a memory bank. Specifically, we apply GMM to select high-confident clean samples as the memory entry, where the memory entry is used to estimate the negative impact of each sample. Since clean samples are easier distinguished by GMM with increasing noise, the memory bank can still maintain high quality at a high noise ratio. Compared to the correction mechanism focusing on noise samples, memory bank-based estimation is more robust, which makes the model performance stable on noisy datasets. Extensive experiments demonstrate that our method significantly improves matching accuracy and performance stability at increasing noise ratio. Our approach also surpasses the state-of-the-art methods by a large margin. The code is available at: https://github.com/ZhangXu0963/NPC.

arXiv:2312.05693공식 코드 · Papers with Code

Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge

Large Language Models (LLMs) stand out for their impressive performance in intricate language modeling tasks. However, their demanding computational and memory needs pose obstacles for broad use on edge devices. Quantization is then introduced to boost LLMs' on-device efficiency. Recent works show that 8-bit or lower weight quantization is feasible with minimal impact on end-to-end task performance, while the activation is still not quantized. On the other hand, mainstream commodity edge devices still struggle to execute these sub-8-bit quantized networks effectively. In this paper, we propose Agile-Quant, an activation-guided quantization framework for popular Large Language Models (LLMs), and implement an end-to-end accelerator on multiple edge devices for faster inference. Considering the hardware profiling and activation analysis, we first introduce a basic activation quantization strategy to balance the trade-off of task performance and real inference speed. Then we leverage the activation-aware token pruning technique to reduce the outliers and the adverse impact on attentivity. Ultimately, we utilize the SIMD-based 4-bit multiplier and our efficient TRIP matrix multiplication to implement the accelerator for LLMs on the edge. We apply our framework on different scales of LLMs including LLaMA, OPT, and BLOOM with 4-bit or 8-bit for the activation and 4-bit for the weight quantization. Experiments show that Agile-Quant achieves simultaneous quantization of model weights and activations while maintaining task performance comparable to existing weight-only quantization methods. Moreover, in the 8- and 4-bit scenario, Agile-Quant achieves an on-device speedup of up to 2.55x compared to its FP16 counterparts across multiple edge devices, marking a pioneering advancement in this domain. Code: https://github.com/shawnricecake/agile-quant

arXiv:2312.05657

PerfRL: A Small Language Model Framework for Efficient Code Optimization

Code optimization is a challenging task requiring a substantial level of expertise from developers. Nonetheless, this level of human capacity is not sufficient considering the rapid evolution of new hardware architectures and software environments. In light of this, recent research proposes adopting machine learning and artificial intelligence techniques to automate the code optimization process. In this paper, we introduce PerfRL, an innovative framework designed to tackle the problem of code optimization. Our framework leverages the capabilities of small language models (SLMs) and reinforcement learning (RL), facilitating a system where SLMs can assimilate feedback from their environment during the fine-tuning phase, notably through unit tests. When benchmarked against existing models, PerfRL demonstrates superior efficiency in terms of speed and computational resource usage, attributed to its reduced need for training steps and its compatibility with SLMs. Furthermore, it substantially diminishes the risk of logical and syntactical errors. To evaluate our framework, we conduct experiments on the PIE dataset using a lightweight large language model (i.e., CodeT5) and a new reinforcement learning algorithm, namely RRHF. For evaluation purposes, we use a list of evaluation metrics related to optimization quality and speedup. The evaluation results show that our approach achieves similar or better results compared to state-of-the-art models using shorter training times and smaller pre-trained models.