PyTorchKR Papers

최신 논문

총 13,082편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2310.03414

LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction

Multi-document summarization is a challenging task due to its inherent subjective bias, highlighted by the low inter-annotator ROUGE-1 score of 0.4 among DUC-2004 reference summaries. In this work, we aim to enhance the objectivity of news summarization by focusing on the main event of a group of related news documents and presenting it coherently with sufficient context. Our primary objective is to succinctly report the main event, ensuring that the summary remains objective and informative. To achieve this, we employ an extract-rewrite approach that incorporates a main-event biased monotone-submodular function for content selection. This enables us to extract the most crucial information related to the main event from the document cluster. To ensure coherence, we utilize a fine-tuned Language Model (LLM) for rewriting the extracted content into a coherent text. The evaluation using objective metrics and human evaluators confirms the effectiveness of our approach, as it surpasses potential baselines, demonstrating excellence in both content coverage, coherence, and informativeness.

arXiv:2310.03646공식 코드 · Papers with Code

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

Sharpness-aware minimization (SAM) reports improving domain generalization by reducing the loss surface curvature in the parameter space. However, generalization during fine-tuning is often more dependent on the transferability of representations in the function space. Trust-region methods (TR) target this goal by regularizing representation curvature to reduce catastrophic forgetting of pre-trained task-agnostic information while adopting task-specific skills. We consider unifying these strategies for low curvature in both parameter space and function space to improve out-of-domain (OOD) generalization. We propose Trust Region Aware Minimization (TRAM), a SAM algorithm fine-tuning for low parameter sharpness and smooth, informative representations preserving pre-trained structure. TRAM uses a trust region bound to inform the SAM adversarial neighborhood, introducing an awareness of function curvature within optimization for flatter minima. We empirically validate TRAM in vision (cross-dataset adaptation) and text (OOD language modeling, zero-shot cross-lingual transfer) tasks where robust domain transfer and representation generality are critical. TRAM outperforms SAM- and TR-based optimization across all tasks, notably surpassing competing methods for hard transfer between anticorrelated domains. TRAM establishes a novel standard in fine-tuning for domain-generalizable models with minimal additional computation over previous sharpness-aware methods.

arXiv:2310.03424

Neural Language Model Pruning for Automatic Speech Recognition

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their contribution in terms of accuracy and inference speed. To the best of our knowledge, such in-depth analyses on large-scale recognition systems has not been reported in the literature. In addition, we propose a variant of low-rank approximation suitable for incrementally compressing models, and delivering multiple models with varied target sizes. Among other results, we show that a) data-driven pruning outperforms magnitude-driven in several scenarios; b) incremental pruning achieves higher accuracy compared to one-shot pruning, especially when targeting smaller sizes; and c) low-rank approximation presents the best trade-off between size reduction and inference speed-up for moderate compression.

arXiv:2310.03714공식 코드 · Papers with Code

DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks. Unfortunately, existing LM pipelines are typically implemented using hard-coded "prompt templates", i.e. lengthy strings discovered via trial and error. Toward a more systematic approach for developing and optimizing LM pipelines, we introduce DSPy, a programming model that abstracts LM pipelines as text transformation graphs, i.e. imperative computational graphs where LMs are invoked through declarative modules. DSPy modules are parameterized, meaning they can learn (by creating and collecting demonstrations) how to apply compositions of prompting, finetuning, augmentation, and reasoning techniques. We design a compiler that will optimize any DSPy pipeline to maximize a given metric. We conduct two case studies, showing that succinct DSPy programs can express and optimize sophisticated LM pipelines that reason about math word problems, tackle multi-hop retrieval, answer complex questions, and control agent loops. Within minutes of compiling, a few lines of DSPy allow GPT-3.5 and llama2-13b-chat to self-bootstrap pipelines that outperform standard few-shot prompting (generally by over 25% and 65%, respectively) and pipelines with expert-created demonstrations (by up to 5-46% and 16-40%, respectively). On top of that, DSPy programs compiled to open and relatively small LMs like 770M-parameter T5 and llama2-13b-chat are competitive with approaches that rely on expert-written prompt chains for proprietary GPT-3.5. DSPy is available at https://github.com/stanfordnlp/dspy

arXiv:2310.03708공식 코드 · Papers with Code

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

A single language model, even when aligned with labelers through reinforcement learning from human feedback (RLHF), may not suit all human preferences. Recent approaches therefore prefer customization, gathering multi-dimensional feedback, and creating distinct reward models for each dimension. Different language models are then optimized for various preferences using multi-objective RLHF (MORLHF) with varying reward weights. However, RL fine-tuning is unstable and resource-heavy, especially with diverse and usually conflicting objectives. In this paper, we present Multi-Objective Direct Preference Optimization (MODPO), an RL-free extension of Direct Preference Optimization (DPO) for multiple alignment objectives. Essentially, MODPO folds language modeling directly into reward modeling, training language models as implicit collective reward models that combine all objectives with specific weights. MODPO theoretically yields the same optimal solutions as MORLHF but is practically more stable and efficient. Empirical results in safety alignment and long-form question answering show that MODPO matches or outperforms existing methods, producing a Pareto front of language models catering to diverse preferences with three times less computational resources compared to MORLHF. Code is available at https://github.com/ZHZisZZ/modpo.

arXiv:2310.03281

A 5' UTR Language Model for Decoding Untranslated Regions of mRNA and Function Predictions

The 5' UTR, a regulatory region at the beginning of an mRNA molecule, plays a crucial role in regulating the translation process and impacts the protein expression level. Language models have showcased their effectiveness in decoding the functions of protein and genome sequences. Here, we introduced a language model for 5' UTR, which we refer to as the UTR-LM. The UTR-LM is pre-trained on endogenous 5' UTRs from multiple species and is further augmented with supervised information including secondary structure and minimum free energy. We fine-tuned the UTR-LM in a variety of downstream tasks. The model outperformed the best-known benchmark by up to 42% for predicting the Mean Ribosome Loading, and by up to 60% for predicting the Translation Efficiency and the mRNA Expression Level. The model also applies to identifying unannotated Internal Ribosome Entry Sites within the untranslated region and improves the AUPR from 0.37 to 0.52 compared to the best baseline. Further, we designed a library of 211 novel 5' UTRs with high predicted values of translation efficiency and evaluated them via a wet-lab assay. Experiment results confirmed that our top designs achieved a 32.5% increase in protein production level relative to well-established 5' UTR optimized for therapeutics.

arXiv:2310.03232

Deep Representations of First-person Pronouns for Prediction of Depression Symptom Severity

Prior work has shown that analyzing the use of first-person singular pronouns can provide insight into individuals' mental status, especially depression symptom severity. These findings were generated by counting frequencies of first-person singular pronouns in text data. However, counting doesn't capture how these pronouns are used. Recent advances in neural language modeling have leveraged methods generating contextual embeddings. In this study, we sought to utilize the embeddings of first-person pronouns obtained from contextualized language representation models to capture ways these pronouns are used, to analyze mental status. De-identified text messages sent during online psychotherapy with weekly assessment of depression severity were used for evaluation. Results indicate the advantage of contextualized first-person pronoun embeddings over standard classification token embeddings and frequency-based pronoun analysis results in predicting depression symptom severity. This suggests contextual representations of first-person pronouns can enhance the predictive utility of language used by people with depression symptoms.

arXiv:2310.03094공식 코드 · Papers with Code

Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning

Large language models (LLMs) such as GPT-4 have exhibited remarkable performance in a variety of tasks, but this strong performance often comes with the high expense of using paid API services. In this paper, we are motivated to study building an LLM cascade to save the cost of using LLMs, particularly for performing reasoning (e.g., mathematical, causal) tasks. Our cascade pipeline follows the intuition that simpler questions can be addressed by a weaker but more affordable LLM, whereas only the challenging questions necessitate the stronger and more expensive LLM. To realize this decision-making, we consider the "answer consistency" of the weaker LLM as a signal of the question difficulty and propose several methods for the answer sampling and consistency checking, including one leveraging a mixture of two thought representations (i.e., Chain-of-Thought and Program-of-Thought). Through experiments on six reasoning benchmark datasets, with GPT-3.5-turbo and GPT-4 being the weaker and stronger LLMs, respectively, we demonstrate that our proposed LLM cascades can achieve performance comparable to using solely the stronger LLM but require only 40% of its cost.

arXiv:2310.03052공식 코드 · Papers with Code

Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture

Making neural networks remember over the long term has been a longstanding issue. Although several external memory techniques have been introduced, most focus on retaining recent information in the short term. Regardless of its importance, information tends to be fatefully forgotten over time. We present Memoria, a memory system for artificial neural networks, drawing inspiration from humans and applying various neuroscientific and psychological theories. The experimental results prove the effectiveness of Memoria in the diverse tasks of sorting, language modeling, and classification, surpassing conventional techniques. Engram analysis reveals that Memoria exhibits the primacy, recency, and temporal contiguity effects which are characteristics of human memory.

arXiv:2310.03018공식 코드 · Papers with Code

Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages

We introduce a new zero resource code-switched speech benchmark designed to directly assess the code-switching capabilities of self-supervised speech encoders. We showcase a baseline system of language modeling on discrete units to demonstrate how the code-switching abilities of speech encoders can be assessed in a zero-resource manner. Our experiments encompass a variety of well-known speech encoders, including Wav2vec 2.0, HuBERT, XLSR, etc. We examine the impact of pre-training languages and model size on benchmark performance. Notably, though our results demonstrate that speech encoders with multilingual pre-training, exemplified by XLSR, outperform monolingual variants (Wav2vec 2.0, HuBERT) in code-switching scenarios, there is still substantial room for improvement in their code-switching linguistic abilities.

arXiv:2310.03003

From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference

Large language models (LLMs) have exploded in popularity due to their new generative capabilities that go far beyond prior state-of-the-art. These technologies are increasingly being leveraged in various domains such as law, finance, and medicine. However, these models carry significant computational challenges, especially the compute and energy costs required for inference. Inference energy costs already receive less attention than the energy costs of training LLMs -- despite how often these large models are called on to conduct inference in reality (e.g., ChatGPT). As these state-of-the-art LLMs see increasing usage and deployment in various domains, a better understanding of their resource utilization is crucial for cost-savings, scaling performance, efficient hardware usage, and optimal inference strategies. In this paper, we describe experiments conducted to study the computational and energy utilization of inference with LLMs. We benchmark and conduct a preliminary analysis of the inference performance and inference energy costs of different sizes of LLaMA -- a recent state-of-the-art LLM -- developed by Meta AI on two generations of popular GPUs (NVIDIA V100 \& A100) and two datasets (Alpaca and GSM8K) to reflect the diverse set of tasks/benchmarks for LLMs in research and practice. We present the results of multi-node, multi-GPU inference using model sharding across up to 32 GPUs. To our knowledge, our work is the one of the first to study LLM inference performance from the perspective of computational and energy resources at this scale.

arXiv:2310.02549

Heterogeneous Federated Learning Using Knowledge Codistillation

Federated Averaging, and many federated learning algorithm variants which build upon it, have a limitation: all clients must share the same model architecture. This results in unused modeling capacity on many clients, which limits model performance. To address this issue, we propose a method that involves training a small model on the entire pool and a larger model on a subset of clients with higher capacity. The models exchange information bidirectionally via knowledge distillation, utilizing an unlabeled dataset on a server without sharing parameters. We present two variants of our method, which improve upon federated averaging on image classification and language modeling tasks. We show this technique can be useful even if only out-of-domain or limited in-domain distillation data is available. Additionally, the bi-directional knowledge distillation allows for domain transfer between the models when different pool populations introduce domain shift.

arXiv:2310.02367공식 코드 · Papers with Code

Linear Recurrent Units for Sequential Recommendation

State-of-the-art sequential recommendation relies heavily on self-attention-based recommender models. Yet such models are computationally expensive and often too slow for real-time recommendation. Furthermore, the self-attention operation is performed at a sequence-level, thereby making low-cost incremental inference challenging. Inspired by recent advances in efficient language modeling, we propose linear recurrent units for sequential recommendation (LRURec). Similar to recurrent neural networks, LRURec offers rapid inference and can achieve incremental inference on sequential inputs. By decomposing the linear recurrence operation and designing recursive parallelization in our framework, LRURec provides the additional benefits of reduced model size and parallelizable training. Moreover, we optimize the architecture of LRURec by implementing a series of modifications to address the lack of non-linearity and improve training dynamics. To validate the effectiveness of our proposed LRURec, we conduct extensive experiments on multiple real-world datasets and compare its performance against state-of-the-art sequential recommenders. Experimental results demonstrate the effectiveness of LRURec, which consistently outperforms baselines by a significant margin. Results also highlight the efficiency of LRURec with our parallelized training paradigm and fast inference on long sequences, showing its potential to further enhance user experience in sequential recommendation.

arXiv:2310.02804공식 코드 · Papers with Code

DOMINO: A Dual-System for Multi-step Visual Language Reasoning

Visual language reasoning requires a system to extract text or numbers from information-dense images like charts or plots and perform logical or arithmetic reasoning to arrive at an answer. To tackle this task, existing work relies on either (1) an end-to-end vision-language model trained on a large amount of data, or (2) a two-stage pipeline where a captioning model converts the image into text that is further read by another large language model to deduce the answer. However, the former approach forces the model to answer a complex question with one single step, and the latter approach is prone to inaccurate or distracting information in the converted text that can confuse the language model. In this work, we propose a dual-system for multi-step multimodal reasoning, which consists of a "System-1" step for visual information extraction and a "System-2" step for deliberate reasoning. Given an input, System-2 breaks down the question into atomic sub-steps, each guiding System-1 to extract the information required for reasoning from the image. Experiments on chart and plot datasets show that our method with a pre-trained System-2 module performs competitively compared to prior work on in- and out-of-distribution data. By fine-tuning the System-2 module (LLaMA-2 70B) on only a small amount of data on multi-step reasoning, the accuracy of our method is further improved and surpasses the best fully-supervised end-to-end approach by 5.7% and a pipeline approach with FlanPaLM (540B) by 7.5% on a challenging dataset with human-authored questions.

arXiv:2310.02421

Can a student Large Language Model perform as well as it's teacher?

The burgeoning complexity of contemporary deep learning models, while achieving unparalleled accuracy, has inadvertently introduced deployment challenges in resource-constrained environments. Knowledge distillation, a technique aiming to transfer knowledge from a high-capacity "teacher" model to a streamlined "student" model, emerges as a promising solution to this dilemma. This paper provides a comprehensive overview of the knowledge distillation paradigm, emphasizing its foundational principles such as the utility of soft labels and the significance of temperature scaling. Through meticulous examination, we elucidate the critical determinants of successful distillation, including the architecture of the student model, the caliber of the teacher, and the delicate balance of hyperparameters. While acknowledging its profound advantages, we also delve into the complexities and challenges inherent in the process. Our exploration underscores knowledge distillation's potential as a pivotal technique in optimizing the trade-off between model performance and deployment efficiency.

arXiv:2310.02409

Dodo: Dynamic Contextual Compression for Decoder-only LMs

Transformer-based language models (LMs) are inefficient in long contexts. We propose Dodo, a solution for context compression. Instead of one vector per token in a standard transformer model, Dodo represents text with a dynamic number of hidden states at each layer, reducing the cost of self-attention to a fraction of typical time and space. Moreover, off-the-shelf models such as LLaMA can be adapted to Dodo by efficient parameter tuning methods such as LoRA. In use, Dodo can act as either an autoregressive LM or a context compressor for downstream tasks. We demonstrate through experiments in language modeling, question answering, and summarization that Dodo retains capabilities in these tasks, while drastically reducing the overhead during decoding. For example, in the autoencoding task, Dodo shrinks context at a 20x compression ratio with a BLEU score of 98% for reconstruction, achieving nearly lossless encoding.

arXiv:2310.02304공식 코드 · Papers with Code

Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation

Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as Python. In this work, we use a language-model-infused scaffolding program to improve itself. We start with a seed "improver" that improves an input program according to a given utility function by querying an LM several times and returning the best solution. We then run this seed improver to improve itself. Across a small set of downstream tasks, the resulting improved improver generates programs with significantly better performance than its seed improver. A variety of self-improvement strategies are proposed by the language model, including beam search, genetic algorithms, and simulated annealing. Since the language models themselves are not altered, this is not full recursive self-improvement. Nonetheless, it demonstrates that a modern language model, GPT-4 in our experiments, is capable of writing code that can call itself to improve itself. We consider concerns around the development of self-improving technologies and evaluate the frequency with which the generated code bypasses a sandbox.

arXiv:2310.01889공식 코드 · Papers with Code

Ring Attention with Blockwise Transformers for Near-Infinite Context

Transformers have emerged as the architecture of choice for many state-of-the-art AI models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands imposed by Transformers limit their ability to handle long sequences, thereby posing challenges in utilizing videos, actions, and other long-form sequences and modalities in complex environments. We present a novel approach, Ring Attention with Blockwise Transformers (Ring Attention), which leverages blockwise computation of self-attention and feedforward to distribute long sequences across multiple devices while fully overlapping the communication of key-value blocks with the computation of blockwise attention. Our approach enables training and inference of sequences that are up to device count times longer than those achievable by prior memory-efficient Transformers, without resorting to approximations or incurring additional communication and computation overheads. Extensive experiments on language modeling and reinforcement learning tasks demonstrate the effectiveness of our approach in allowing millions of tokens context size and improving performance.

arXiv:2310.01749공식 코드 · Papers with Code

Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns

Attention, specifically scaled dot-product attention, has proven effective for natural language, but it does not have a mechanism for handling hierarchical patterns of arbitrary nesting depth, which limits its ability to recognize certain syntactic structures. To address this shortcoming, we propose stack attention: an attention operator that incorporates stacks, inspired by their theoretical connections to context-free languages (CFLs). We show that stack attention is analogous to standard attention, but with a latent model of syntax that requires no syntactic supervision. We propose two variants: one related to deterministic pushdown automata (PDAs) and one based on nondeterministic PDAs, which allows transformers to recognize arbitrary CFLs. We show that transformers with stack attention are very effective at learning CFLs that standard transformers struggle on, achieving strong results on a CFL with theoretically maximal parsing difficulty. We also show that stack attention is more effective at natural language modeling under a constrained parameter budget, and we include results on machine translation.

arXiv:2310.01429

Chatmap : Large Language Model Interaction with Cartographic Data

The swift advancement and widespread availability of foundational Large Language Models (LLMs), complemented by robust fine-tuning methodologies, have catalyzed their adaptation for innovative and industrious applications. Enabling LLMs to recognize and interpret geospatial data, while offering a linguistic access to vast cartographic datasets, is of significant importance. OpenStreetMap (OSM) is the most ambitious open-source global initiative offering detailed urban and rural geographic data, curated by a community of over 10 million contributors, which constitutes a great potential for LLM applications. In this study, we demonstrate the proof of concept and details of the process of fine-tuning a relatively small scale (1B parameters) LLM with a relatively small artificial dataset curated by a more capable teacher model, in order to provide a linguistic interface to the OSM data of an arbitrary urban region. Through this interface, users can inquire about a location's attributes, covering a wide spectrum of concepts, such as its touristic appeal or the potential profitability of various businesses in that vicinity. The study aims to provide an initial guideline for such generative artificial intelligence (AI) adaptations and demonstrate early signs of useful emerging abilities in this context even in minimal computational settings. The embeddings of artificially curated prompts including OSM data are also investigated in detail, which might be instrumental for potential geospatially aware urban Retrieval Augmented Generation (RAG) applications.