PyTorchKR Papers

최신 논문

총 11,123편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2404.02456

PhonologyBench: Evaluating Phonological Skills of Large Language Models

Phonology, the study of speech's structure and pronunciation rules, is a critical yet often overlooked component in Large Language Model (LLM) research. LLMs are widely used in various downstream applications that leverage phonology such as educational tools and poetry generation. Moreover, LLMs can potentially learn imperfect associations between orthographic and phonological forms from the training data. Thus, it is imperative to benchmark the phonological skills of LLMs. To this end, we present PhonologyBench, a novel benchmark consisting of three diagnostic tasks designed to explicitly test the phonological skills of LLMs in English: grapheme-to-phoneme conversion, syllable counting, and rhyme word generation. Despite having no access to speech data, LLMs showcased notable performance on the PhonologyBench tasks. However, we observe a significant gap of 17% and 45% on Rhyme Word Generation and Syllable counting, respectively, when compared to humans. Our findings underscore the importance of studying LLM performance on phonological tasks that inadvertently impact real-world applications. Furthermore, we encourage researchers to choose LLMs that perform well on the phonological task that is closely related to the downstream application since we find that no single model consistently outperforms the others on all the tasks.

arXiv:2404.02261공식 코드 · Papers with Code

LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languages

Low-resource languages face significant barriers in AI development due to limited linguistic resources and expertise for data labeling, rendering them rare and costly. The scarcity of data and the absence of preexisting tools exacerbate these challenges, especially since these languages may not be adequately represented in various NLP datasets. To address this gap, we propose leveraging the potential of LLMs in the active learning loop for data annotation. Initially, we conduct evaluations to assess inter-annotator agreement and consistency, facilitating the selection of a suitable LLM annotator. The chosen annotator is then integrated into a training loop for a classifier using an active learning paradigm, minimizing the amount of queried data required. Empirical evaluations, notably employing GPT-4-Turbo, demonstrate near-state-of-the-art performance with significantly reduced data requirements, as indicated by estimated potential cost savings of at least 42.45 times compared to human annotation. Our proposed solution shows promising potential to substantially reduce both the monetary and computational costs associated with automation in low-resource settings. By bridging the gap between low-resource languages and AI, this approach fosters broader inclusion and shows the potential to enable automation across diverse linguistic landscapes.

arXiv:2404.02183공식 코드 · Papers with Code

Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization

Recent advancements in automatic code generation using large language model (LLM) agent have brought us closer to the future of automated software development. However, existing single-agent approaches face limitations in generating and improving large-scale, complex codebases due to constraints in context length. To tackle this challenge, we propose Self-Organized multi-Agent framework (SoA), a novel multi-agent framework that enables the scalable and efficient generation and optimization of large-scale code. In SoA, self-organized agents operate independently to generate and modify code components while seamlessly collaborating to construct the overall codebase. A key feature of our framework is the automatic multiplication of agents based on problem complexity, allowing for dynamic scalability. This enables the overall code volume to be increased indefinitely according to the number of agents, while the amount of code managed by each agent remains constant. We evaluate SoA on the HumanEval benchmark and demonstrate that, compared to a single-agent system, each agent in SoA handles significantly less code, yet the overall generated code is substantially greater. Moreover, SoA surpasses the powerful single-agent baseline by 5% in terms of Pass@1 accuracy.

arXiv:2404.00276공식 코드 · Papers with Code

Instruction-Driven Game Engines on Large Language Models

The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game rules and autonomously generate game-play processes. The IDGE allows users to create games by issuing simple natural language instructions, which significantly lowers the barrier for game development. We approach the learning process for IDGEs as a Next State Prediction task, wherein the model autoregressively predicts in-game states given player actions. It is a challenging task because the computation of in-game states must be precise; otherwise, slight errors could disrupt the game-play. To address this, we train the IDGE in a curriculum manner that progressively increases the model's exposure to complex scenarios. Our initial progress lies in developing an IDGE for Poker, a universally cherished card game. The engine we've designed not only supports a wide range of poker variants but also allows for high customization of rules through natural language inputs. Furthermore, it also favors rapid prototyping of new games from minimal samples, proposing an innovative paradigm in game development that relies on minimal prompt and data engineering. This work lays the groundwork for future advancements in instruction-driven game creation, potentially transforming how games are designed and played.

arXiv:2404.02905공식 코드 · Papers with Code

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction". This simple, intuitive methodology allows autoregressive (AR) transformers to learn visual distributions fast and generalize well: VAR, for the first time, makes GPT-like AR models surpass diffusion transformers in image generation. On ImageNet 256x256 benchmark, VAR significantly improve AR baseline by improving Frechet inception distance (FID) from 18.65 to 1.73, inception score (IS) from 80.4 to 350.2, with around 20x faster inference speed. It is also empirically verified that VAR outperforms the Diffusion Transformer (DiT) in multiple dimensions including image quality, inference speed, data efficiency, and scalability. Scaling up VAR models exhibits clear power-law scaling laws similar to those observed in LLMs, with linear correlation coefficients near -0.998 as solid evidence. VAR further showcases zero-shot generalization ability in downstream tasks including image in-painting, out-painting, and editing. These results suggest VAR has initially emulated the two important properties of LLMs: Scaling Laws and zero-shot task generalization. We have released all models and codes to promote the exploration of AR/VAR models for visual generation and unified learning.

arXiv:2404.02838

I-Design: Personalized LLM Interior Designer

Interior design allows us to be who we are and live how we want - each design is as unique as our distinct personality. However, it is not trivial for non-professionals to express and materialize this since it requires aligning functional and visual expectations with the constraints of physical space; this renders interior design a luxury. To make it more accessible, we present I-Design, a personalized interior designer that allows users to generate and visualize their design goals through natural language communication. I-Design starts with a team of large language model agents that engage in dialogues and logical reasoning with one another, transforming textual user input into feasible scene graph designs with relative object relationships. Subsequently, an effective placement algorithm determines optimal locations for each object within the scene. The final design is then constructed in 3D by retrieving and integrating assets from an existing object database. Additionally, we propose a new evaluation protocol that utilizes a vision-language model and complements the design pipeline. Extensive quantitative and qualitative experiments show that I-Design outperforms existing methods in delivering high-quality 3D design solutions and aligning with abstract concepts that match user input, showcasing its advantages across detailed 3D arrangement and conceptual fidelity.

arXiv:2404.00209공식 코드 · Papers with Code

EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs

Narrative reasoning relies on the understanding of eventualities in story contexts, which requires a wealth of background world knowledge. To help machines leverage such knowledge, existing solutions can be categorized into two groups. Some focus on implicitly modeling eventuality knowledge by pretraining language models (LMs) with eventuality-aware objectives. However, this approach breaks down knowledge structures and lacks interpretability. Others explicitly collect world knowledge of eventualities into structured eventuality-centric knowledge graphs (KGs). However, existing research on leveraging these knowledge sources for free-texts is limited. In this work, we propose an initial comprehensive framework called EventGround, which aims to tackle the problem of grounding free-texts to eventuality-centric KGs for contextualized narrative reasoning. We identify two critical problems in this direction: the event representation and sparsity problems. We provide simple yet effective parsing and partial information extraction methods to tackle these problems. Experimental results demonstrate that our approach consistently outperforms baseline models when combined with graph neural network (GNN) or large language model (LLM) based graph reasoning models. Our framework, incorporating grounded knowledge, achieves state-of-the-art performance while providing interpretable evidence.

arXiv:2404.00189

GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs

This study introduces GPTA, a Large Language Model assistance training framework, that enhances the training of downstream task models via prefix prompt. By minimizing data exposure to LLM, the framework addresses the security and legal challenges of applying LLM in downstream task model training. GPTA utilizes a new synergistic training approach, optimizing the downstream models with parameter gradients and LLMs with the novel ``dialogue gradient''. The framework not only demonstrates significant improvements in model performance across six NLP benchmark datasets, but also reduces overfitting in low-resource scenarios effectively. The detailed analyses further validate that our pioneer framework provides a cost-efficient and adaptive method for downstream task model training with LLM support.

arXiv:2404.01399공식 코드 · Papers with Code

Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?

Large Language Models (LLMs) have advanced various Natural Language Processing (NLP) tasks, such as text generation and translation, among others. However, these models often generate texts that can perpetuate biases. Existing approaches to mitigate these biases usually compromise knowledge retention. This study explores whether LLMs can produce safe, unbiased outputs without sacrificing knowledge or comprehension. We introduce the Safe and Responsible Large Language Model (\textbf{SR}$_{\text{LLM}}$), which has been instruction fine-tuned atop of a safe fine-tuned auto-regressive decoder-only LLM to reduce biases in generated texts. We developed a specialized dataset with examples of unsafe and corresponding safe variations to train \textbf{SR}$_{\text{LLM}}$ to identify and correct biased text. Experiments on our specialized dataset and out-of-distribution test sets reveal that \textbf{SR}$_{\text{LLM}}$ effectively reduces biases while preserving knowledge integrity. This performance surpasses that of traditional fine-tuning of smaller language models and base LLMs that merely reply on prompting techniques. Our findings demonstrate that instruction fine-tuning on custom datasets tailored for tasks such as debiasing is a highly effective strategy for minimizing bias in LLM while preserving their inherent knowledge and capabilities. The code and dataset are accessible at \href{https://github.com/shainarazavi/Safe-Responsible-LLM}{SR-LLM}

arXiv:2404.01204

The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis

Uncovering early-stage metrics that reflect final model performance is one core principle for large-scale pretraining. The existing scaling law demonstrates the power-law correlation between pretraining loss and training flops, which serves as an important indicator of the current training state for large language models. However, this principle only focuses on the model's compression properties on the training data, resulting in an inconsistency with the ability improvements on the downstream tasks. Some follow-up works attempted to extend the scaling-law to more complex metrics (such as hyperparameters), but still lacked a comprehensive analysis of the dynamic differences among various capabilities during pretraining. To address the aforementioned limitations, this paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints. Through this analysis, we confirm that specific downstream metrics exhibit similar training dynamics across models of different sizes, up to 67 billion parameters. In addition to our core findings, we've reproduced Amber and OpenLLaMA, releasing their intermediate checkpoints. This initiative offers valuable resources to the research community and facilitates the verification and exploration of LLM pretraining by open-source researchers. Besides, we provide empirical summaries, including performance comparisons of different models and capabilities, and tuition of key metrics for different training phases. Based on these findings, we provide a more user-friendly strategy for evaluating the optimization state, offering guidance for establishing a stable pretraining process.

arXiv:2404.01165공식 코드 · Papers with Code

LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models

The modeling of environmental ecosystems plays a pivotal role in the sustainable management of our planet. Accurate prediction of key environmental variables over space and time can aid in informed policy and decision-making, thus improving people's livelihood. Recently, deep learning-based methods have shown promise in modeling the spatial-temporal relationships for predicting environmental variables. However, these approaches often fall short in handling incomplete features and distribution shifts, which are commonly observed in environmental data due to the substantial cost of data collection and malfunctions in measuring instruments. To address these issues, we propose LITE -- a multimodal large language model for environmental ecosystems modeling. Specifically, LITE unifies different environmental variables by transforming them into natural language descriptions and line graph images. Then, LITE utilizes unified encoders to capture spatial-temporal dynamics and correlations in different modalities. During this step, the incomplete features are imputed by a sparse Mixture-of-Experts framework, and the distribution shift is handled by incorporating multi-granularity information from past observations. Finally, guided by domain instructions, a language model is employed to fuse the multimodal representations for the prediction. Our experiments demonstrate that LITE significantly enhances performance in environmental spatial-temporal prediction across different domains compared to the best baseline, with a 41.25% reduction in prediction error. This justifies its effectiveness. Our data and code are available at https://github.com/hrlics/LITE.

arXiv:2404.01157

Green AI: Exploring Carbon Footprints, Mitigation Strategies, and Trade Offs in Large Language Model Training

Prominent works in the field of Natural Language Processing have long attempted to create new innovative models by improving upon previous model training approaches, altering model architecture, and developing more in-depth datasets to better their performance. However, with the quickly advancing field of NLP comes increased greenhouse gas emissions, posing concerns over the environmental damage caused by training LLMs. Gaining a comprehensive understanding of the various costs, particularly those pertaining to environmental aspects, that are associated with artificial intelligence serves as the foundational basis for ensuring safe AI models. Currently, investigations into the CO2 emissions of AI models remain an emerging area of research, and as such, in this paper, we evaluate the CO2 emissions of well-known large language models, which have an especially high carbon footprint due to their significant amount of model parameters. We argue for the training of LLMs in a way that is responsible and sustainable by suggesting measures for reducing carbon emissions. Furthermore, we discuss how the choice of hardware affects CO2 emissions by contrasting the CO2 emissions during model training for two widely used GPUs. Based on our results, we present the benefits and drawbacks of our proposed solutions and make the argument for the possibility of training more environmentally safe AI models without sacrificing their robustness and performance.

arXiv:2404.01037공식 코드 · Papers with Code

ARAGOG: Advanced RAG Output Grading

Retrieval-Augmented Generation (RAG) is essential for integrating external knowledge into Large Language Model (LLM) outputs. While the literature on RAG is growing, it primarily focuses on systematic reviews and comparisons of new state-of-the-art (SoTA) techniques against their predecessors, with a gap in extensive experimental comparisons. This study begins to address this gap by assessing various RAG methods' impacts on retrieval precision and answer similarity. We found that Hypothetical Document Embedding (HyDE) and LLM reranking significantly enhance retrieval precision. However, Maximal Marginal Relevance (MMR) and Cohere rerank did not exhibit notable advantages over a baseline Naive RAG system, and Multi-query approaches underperformed. Sentence Window Retrieval emerged as the most effective for retrieval precision, despite its variable performance on answer similarity. The study confirms the potential of the Document Summary Index as a competent retrieval approach. All resources related to this research are publicly accessible for further investigation through our GitHub repository ARAGOG (https://github.com/predlico/ARAGOG). We welcome the community to further this exploratory study in RAG systems.

arXiv:2404.00950

AISPACE at SemEval-2024 task 8: A Class-balanced Soft-voting System for Detecting Multi-generator Machine-generated Text

SemEval-2024 Task 8 provides a challenge to detect human-written and machine-generated text. There are 3 subtasks for different detection scenarios. This paper proposes a system that mainly deals with Subtask B. It aims to detect if given full text is written by human or is generated by a specific Large Language Model (LLM), which is actually a multi-class text classification task. Our team AISPACE conducted a systematic study of fine-tuning transformer-based models, including encoderonly, decoder-only and encoder-decoder models. We compared their performance on this task and identified that encoder-only models performed exceptionally well. We also applied a weighted Cross Entropy loss function to address the issue of data imbalance of different class samples. Additionally, we employed softvoting strategy over multi-models ensemble to enhance the reliability of our predictions. Our system ranked top 1 in Subtask B, which sets a state-of-the-art benchmark for this new challenge.

arXiv:2404.00589공식 코드 · Papers with Code

Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing

Handling graph data is one of the most difficult tasks. Traditional techniques, such as those based on geometry and matrix factorization, rely on assumptions about the data relations that become inadequate when handling large and complex graph data. On the other hand, deep learning approaches demonstrate promising results in handling large graph data, but they often fall short of providing interpretable explanations. To equip the graph processing with both high accuracy and explainability, we introduce a novel approach that harnesses the power of a large language model (LLM), enhanced by an uncertainty-aware module to provide a confidence score on the generated answer. We experiment with our approach on two graph processing tasks: few-shot knowledge graph completion and graph classification. Our results demonstrate that through parameter efficient fine-tuning, the LLM surpasses state-of-the-art algorithms by a substantial margin across ten diverse benchmark datasets. Moreover, to address the challenge of explainability, we propose an uncertainty estimation based on perturbation, along with a calibration scheme to quantify the confidence scores of the generated answers. Our confidence measure achieves an AUC of 0.8 or higher on seven out of the ten datasets in predicting the correctness of the answer generated by LLM.

arXiv:2404.00566공식 코드 · Papers with Code

CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks

To adequately test modern code generation systems, evaluation benchmarks must execute and test the code generated by the system. However, these execution and testing requirements have largely limited benchmarks to settings where code is easily executable or has human-written tests. To facilitate evaluation of code generation systems across diverse scenarios, we present CodeBenchGen, a framework to create scalable execution-based benchmarks from naturally occurring code sources. Specifically, we leverage a large language model (LLM) to sandbox arbitrary pieces of code into evaluation examples, including test cases for execution-based evaluation. We illustrate the usefulness of our framework by creating a dataset, Exec-CSN, which includes 1,931 examples involving 293 libraries converted from code in 367 GitHub repositories taken from the Code- SearchNet dataset. To demonstrate the solvability of examples in Exec-CSN, we present a human study demonstrating that 81.3% of the examples can be solved by humans and 61% are rated as "requires effort to solve". We conduct code generation experiments on open-source and proprietary models and analyze the performance of both humans and models. We provide code and data at: https://github.com/yiqingxyq/CodeBenchGen.

arXiv:2404.00419공식 코드 · Papers with Code

Do Vision-Language Models Understand Compound Nouns?

Open-vocabulary vision-language models (VLMs) like CLIP, trained using contrastive loss, have emerged as a promising new paradigm for text-to-image retrieval. However, do VLMs understand compound nouns (CNs) (e.g., lab coat) as well as they understand nouns (e.g., lab)? We curate Compun, a novel benchmark with 400 unique and commonly used CNs, to evaluate the effectiveness of VLMs in interpreting CNs. The Compun benchmark challenges a VLM for text-to-image retrieval where, given a text prompt with a CN, the task is to select the correct image that shows the CN among a pair of distractor images that show the constituent nouns that make up the CN. Next, we perform an in-depth analysis to highlight CLIPs' limited understanding of certain types of CNs. Finally, we present an alternative framework that moves beyond hand-written templates for text prompts widely used by CLIP-like models. We employ a Large Language Model to generate multiple diverse captions that include the CN as an object in the scene described by the caption. Our proposed method improves CN understanding of CLIP by 8.25% on Compun. Code and benchmark are available at: https://github.com/sonalkum/Compun

arXiv:2404.00361

Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generation

Data augmentation (DA) is crucial to mitigate model training instability and over-fitting problems in low-resource open-domain dialogue generation. However, traditional DA methods often neglect semantic data diversity, restricting the overall quality. Recently, large language models (LLM) have been used for DA to generate diversified dialogues. However, they have limited controllability and tend to generate dialogues with a distribution shift compared to the seed dialogues. To maximize the augmentation diversity and address the controllability problem, we propose \textbf{S}ummary-based \textbf{D}ialogue \textbf{A}ugmentation with LLM (SDA). Our approach enhances the controllability of LLM by using dialogue summaries as a planning tool. Based on summaries, SDA can generate high-quality and diverse dialogue data even with a small seed dataset. To evaluate the efficacy of data augmentation methods for open-domain dialogue, we designed a clustering-based metric to characterize the semantic diversity of the augmented dialogue data. The experimental results show that SDA can augment high-quality and semantically diverse dialogues given a small seed dataset and an LLM, and the augmented data can boost the performance of open-domain dialogue models.

arXiv:2404.00282

Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods

With extensive pre-trained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects such as multi-task learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared to conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to systematically categorize LLMs' functionalities in RL, including four roles: information processor, reward designer, decision-maker, and generator. For each role, we summarize the methodologies, analyze the specific RL challenges that are mitigated, and provide insights into future directions. Lastly, a comparative analysis of each role, potential applications, prospective opportunities, and challenges of the LLM-enhanced RL are discussed. By proposing this taxonomy, we aim to provide a framework for researchers to effectively leverage LLMs in the RL field, potentially accelerating RL applications in complex applications such as robotics, autonomous driving, and energy systems.

arXiv:2404.00246공식 코드 · Papers with Code

Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World

Language agents that interact with the world on their own have great potential for automating digital tasks. While large language model (LLM) agents have made progress in understanding and executing tasks such as textual games and webpage control, many real-world tasks also require collaboration with humans or other LLMs in equal roles, which involves intent understanding, task coordination, and communication. To test LLM's ability to collaborate, we design a blocks-world environment, where two agents, each having unique goals and skills, build a target structure together. To complete the goals, they can act in the world and communicate in natural language. Under this environment, we design increasingly challenging settings to evaluate different collaboration perspectives, from independent to more complex, dependent tasks. We further adopt chain-of-thought prompts that include intermediate reasoning steps to model the partner's state and identify and correct execution errors. Both human-machine and machine-machine experiments show that LLM agents have strong grounding capacities, and our approach significantly improves the evaluation metric.