PyTorchKR Papers

최신 논문

총 2,090편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2403.19489공식 코드 · Papers with Code

Evolving Assembly Code in an Adversarial Environment

In this work, we evolve Assembly code for the CodeGuru competition. The goal is to create a survivor -- an Assembly program that runs the longest in shared memory, by resisting attacks from adversary survivors and finding their weaknesses. For evolving top-notch solvers, we specify a Backus Normal Form (BNF) for the Assembly language and synthesize the code from scratch using Genetic Programming (GP). We evaluate the survivors by running CodeGuru games against human-written winning survivors. Our evolved programs found weaknesses in the programs they were trained against and utilized them. To push evolution further, we implemented memetic operators that utilize machine learning to explore the solution space effectively. This work has important applications for cyber-security as we utilize evolution to detect weaknesses in survivors. The Assembly BNF is domain-independent; thus, by modifying the fitness function, it can detect code weaknesses and help fix them. Finally, the CodeGuru competition offers a novel platform for analyzing GP and code evolution in adversarial environments. To support further research in this direction, we provide a thorough qualitative analysis of the evolved survivors and the weaknesses found.

arXiv:2403.19318공식 코드 · Papers with Code

TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios

We introduce TableLLM, a robust large language model (LLM) with 13 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios. We propose a distant supervision method for training, which comprises a reasoning process extension strategy, aiding in training LLMs to understand reasoning patterns more effectively as well as a cross-way validation strategy, ensuring the quality of the automatically generated data. To evaluate the performance of TableLLM, we have crafted a benchmark tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TableLLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction.Our codes and data are publicly available at https://github.com/TableLLM/TableLLM.

arXiv:2403.19646공식 코드 · Papers with Code

Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis

Monitoring changes in the Earth's surface is crucial for understanding natural processes and human impacts, necessitating precise and comprehensive interpretation methodologies. Remote sensing satellite imagery offers a unique perspective for monitoring these changes, leading to the emergence of remote sensing image change interpretation (RSICI) as a significant research focus. Current RSICI technology encompasses change detection and change captioning, each with its limitations in providing comprehensive interpretation. To address this, we propose an interactive Change-Agent, which can follow user instructions to achieve comprehensive change interpretation and insightful analysis, such as change detection and change captioning, change object counting, change cause analysis, etc. The Change-Agent integrates a multi-level change interpretation (MCI) model as the eyes and a large language model (LLM) as the brain. The MCI model contains two branches of pixel-level change detection and semantic-level change captioning, in which the BI-temporal Iterative Interaction (BI3) layer is proposed to enhance the model's discriminative feature representation capabilities. To support the training of the MCI model, we build the LEVIR-MCI dataset with a large number of change masks and captions of changes. Experiments demonstrate the SOTA performance of the MCI model in achieving both change detection and change description simultaneously, and highlight the promising application value of our Change-Agent in facilitating comprehensive interpretation of surface changes, which opens up a new avenue for intelligent remote sensing applications. To facilitate future research, we will make our dataset and codebase of the MCI model and Change-Agent publicly available at https://github.com/Chen-Yang-Liu/Change-Agent

arXiv:2403.18938공식 코드 · Papers with Code

Reshaping Free-Text Radiology Notes Into Structured Reports With Generative Transformers

BACKGROUND: Radiology reports are typically written in a free-text format, making clinical information difficult to extract and use. Recently the adoption of structured reporting (SR) has been recommended by various medical societies thanks to the advantages it offers, e.g. standardization, completeness and information retrieval. We propose a pipeline to extract information from free-text radiology reports, that fits with the items of the reference SR registry proposed by a national society of interventional and medical radiology, focusing on CT staging of patients with lymphoma. METHODS: Our work aims to leverage the potential of Natural Language Processing (NLP) and Transformer-based models to deal with automatic SR registry filling. With the availability of 174 radiology reports, we investigate a rule-free generative Question Answering approach based on a domain-specific version of T5 (IT5). Two strategies (batch-truncation and ex-post combination) are implemented to comply with the model's context length limitations. Performance is evaluated in terms of strict accuracy, F1, and format accuracy, and compared with the widely used GPT-3.5 Large Language Model. A 5-point Likert scale questionnaire is used to collect human-expert feedback on the similarity between medical annotations and generated answers. RESULTS: The combination of fine-tuning and batch splitting allows IT5 to achieve notable results; it performs on par with GPT-3.5 albeit its size being a thousand times smaller in terms of parameters. Human-based assessment scores show a high correlation (Spearman's correlation coefficients>0.88, p-values<0.001) with AI performance metrics (F1) and confirm the superior ability of LLMs (i.e., GPT-3.5, 175B of parameters) in generating plausible human-like statements.

arXiv:2403.18480공식 코드 · Papers with Code

Content-Based Collaborative Generation for Recommender Systems

Generative models have emerged as a promising utility to enhance recommender systems. It is essential to model both item content and user-item collaborative interactions in a unified generative framework for better recommendation. Although some existing large language model (LLM)-based methods contribute to fusing content information and collaborative signals, they fundamentally rely on textual language generation, which is not fully aligned with the recommendation task. How to integrate content knowledge and collaborative interaction signals in a generative framework tailored for item recommendation is still an open research challenge. In this paper, we propose content-based collaborative generation for recommender systems, namely ColaRec. ColaRec is a sequence-to-sequence framework which is tailored for directly generating the recommended item identifier. Precisely, the input sequence comprises data pertaining to the user's interacted items, and the output sequence represents the generative identifier (GID) for the suggested item. To model collaborative signals, the GIDs are constructed from a pretrained collaborative filtering model, and the user is represented as the content aggregation of interacted items. To this end, ColaRec captures both collaborative signals and content information in a unified framework. Then an item indexing task is proposed to conduct the alignment between the content-based semantic space and the interaction-based collaborative space. Besides, a contrastive loss is further introduced to ensure that items with similar collaborative GIDs have similar content representations. To verify the effectiveness of ColaRec, we conduct experiments on four benchmark datasets. Empirical results demonstrate the superior performance of ColaRec.

arXiv:2403.18426공식 코드 · Papers with Code

TriviaHG: A Dataset for Automatic Hint Generation from Factoid Questions

Nowadays, individuals tend to engage in dialogues with Large Language Models, seeking answers to their questions. In times when such answers are readily accessible to anyone, the stimulation and preservation of human's cognitive abilities, as well as the assurance of maintaining good reasoning skills by humans becomes crucial. This study addresses such needs by proposing hints (instead of final answers or before giving answers) as a viable solution. We introduce a framework for the automatic hint generation for factoid questions, employing it to construct TriviaHG, a novel large-scale dataset featuring 160,230 hints corresponding to 16,645 questions from the TriviaQA dataset. Additionally, we present an automatic evaluation method that measures the Convergence and Familiarity quality attributes of hints. To evaluate the TriviaHG dataset and the proposed evaluation method, we enlisted 10 individuals to annotate 2,791 hints and tasked 6 humans with answering questions using the provided hints. The effectiveness of hints varied, with success rates of 96%, 78%, and 36% for questions with easy, medium, and hard answers, respectively. Moreover, the proposed automatic evaluation methods showed a robust correlation with annotators' results. Conclusively, the findings highlight three key insights: the facilitative role of hints in resolving unknown questions, the dependence of hint quality on answer difficulty, and the feasibility of employing automatic evaluation methods for hint assessment.

arXiv:2403.18348공식 코드 · Papers with Code

Sequential Recommendation with Latent Relations based on Large Language Model

Sequential recommender systems predict items that may interest users by modeling their preferences based on historical interactions. Traditional sequential recommendation methods rely on capturing implicit collaborative filtering signals among items. Recent relation-aware sequential recommendation models have achieved promising performance by explicitly incorporating item relations into the modeling of user historical sequences, where most relations are extracted from knowledge graphs. However, existing methods rely on manually predefined relations and suffer the sparsity issue, limiting the generalization ability in diverse scenarios with varied item relations. In this paper, we propose a novel relation-aware sequential recommendation framework with Latent Relation Discovery (LRD). Different from previous relation-aware models that rely on predefined rules, we propose to leverage the Large Language Model (LLM) to provide new types of relations and connections between items. The motivation is that LLM contains abundant world knowledge, which can be adopted to mine latent relations of items for recommendation. Specifically, inspired by that humans can describe relations between items using natural language, LRD harnesses the LLM that has demonstrated human-like knowledge to obtain language knowledge representations of items. These representations are fed into a latent relation discovery module based on the discrete state variational autoencoder (DVAE). Then the self-supervised relation discovery tasks and recommendation tasks are jointly optimized. Experimental results on multiple public datasets demonstrate our proposed latent relations discovery method can be incorporated with existing relation-aware sequential recommendation models and significantly improve the performance. Further analysis experiments indicate the effectiveness and reliability of the discovered latent relations.

arXiv:2403.18325공식 코드 · Papers with Code

Common Sense Enhanced Knowledge-based Recommendation with Large Language Model

Knowledge-based recommendation models effectively alleviate the data sparsity issue leveraging the side information in the knowledge graph, and have achieved considerable performance. Nevertheless, the knowledge graphs used in previous work, namely metadata-based knowledge graphs, are usually constructed based on the attributes of items and co-occurring relations (e.g., also buy), in which the former provides limited information and the latter relies on sufficient interaction data and still suffers from cold start issue. Common sense, as a form of knowledge with generality and universality, can be used as a supplement to the metadata-based knowledge graph and provides a new perspective for modeling users' preferences. Recently, benefiting from the emergent world knowledge of the large language model, efficient acquisition of common sense has become possible. In this paper, we propose a novel knowledge-based recommendation framework incorporating common sense, CSRec, which can be flexibly coupled to existing knowledge-based methods. Considering the challenge of the knowledge gap between the common sense-based knowledge graph and metadata-based knowledge graph, we propose a knowledge fusion approach based on mutual information maximization theory. Experimental results on public datasets demonstrate that our approach significantly improves the performance of existing knowledge-based recommendation models.

arXiv:2403.18680공식 코드 · Papers with Code

Non-Linear Inference Time Intervention: Improving LLM Truthfulness

In this work, we explore LLM's internal representation space to identify attention heads that contain the most truthful and accurate information. We further developed the Inference Time Intervention (ITI) framework, which lets bias LLM without the need for fine-tuning. The improvement manifests in introducing a non-linear multi-token probing and multi-token intervention: Non-Linear ITI (NL-ITI), which significantly enhances performance on evaluation benchmarks. NL-ITI is tested on diverse multiple-choice datasets, including TruthfulQA, on which we report over 16% relative MC1 (accuracy of model pointing to the correct answer) improvement with respect to the baseline ITI results. Moreover, we achieved a 10% relative improvement over the recently released Truth Forest (TrFf) method that also focused on ITI improvement.

arXiv:2403.18593공식 코드 · Papers with Code

Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding

The tokenizer, as one of the fundamental components of large models, has long been overlooked or even misunderstood in visual tasks. One key factor of the great comprehension power of the large language model is that natural language tokenizers utilize meaningful words or subwords as the basic elements of language. In contrast, mainstream visual tokenizers, represented by patch-based methods such as Patch Embed, rely on meaningless rectangular patches as basic elements of vision, which cannot serve as effectively as words or subwords in language. Starting from the essence of the tokenizer, we defined semantically independent regions (SIRs) for vision. We designed a simple HOmogeneous visual tOKenizer: HOOK. HOOK mainly consists of two modules: the Object Perception Module (OPM) and the Object Vectorization Module (OVM). To achieve homogeneity, the OPM splits the image into 4*4 pixel seeds and then utilizes the attention mechanism to perceive SIRs. The OVM employs cross-attention to merge seeds within the same SIR. To achieve adaptability, the OVM defines a variable number of learnable vectors as cross-attention queries, allowing for the adjustment of token quantity. We conducted experiments on the NWPU-RESISC45, WHU-RS19 classification dataset, and GID5 segmentation dataset for sparse and dense tasks. The results demonstrate that the visual tokens obtained by HOOK correspond to individual objects, which demonstrates homogeneity. HOOK outperformed Patch Embed by 6\% and 10\% in the two tasks and achieved state-of-the-art performance compared to the baselines used for comparison. Compared to Patch Embed, which requires more than one hundred tokens for one image, HOOK requires only 6 and 8 tokens for sparse and dense tasks, respectively, resulting in efficiency improvements of 1.5 to 2.8 times. The code is available at https://github.com/GeoX-Lab/Hook.

arXiv:2403.17834공식 코드 · Papers with Code

Developing Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography

While computer vision has achieved tremendous success with multimodal encoding and direct textual interaction with images via chat-based large language models, similar advancements in medical imaging AI, particularly in 3D imaging, have been limited due to the scarcity of comprehensive datasets. To address this critical gap, we introduce CT-RATE, the first dataset that pairs 3D medical images with corresponding textual reports. CT-RATE comprises 25,692 non-contrast 3D chest CT scans from 21,304 unique patients. Through various reconstructions, these scans are expanded to 50,188 volumes, totaling over 14.3 million 2D slices. Each scan is accompanied by its corresponding radiology report. Leveraging CT-RATE, we develop CT-CLIP, a CT-focused contrastive language-image pretraining framework designed for broad applications without the need for task-specific training. We demonstrate how CT-CLIP can be used in two tasks: multi-abnormality detection and case retrieval. Remarkably, in multi-abnormality detection, CT-CLIP outperforms state-of-the-art fully supervised models across all key metrics, effectively eliminating the need for manual annotation. In case retrieval, it efficiently retrieves relevant cases using either image or textual queries, thereby enhancing knowledge dissemination. By combining CT-CLIP's vision encoder with a pretrained large language model, we create CT-CHAT, a vision-language foundational chat model for 3D chest CT volumes. Finetuned on over 2.7 million question-answer pairs derived from the CT-RATE dataset, CT-CHAT surpasses other multimodal AI assistants, underscoring the necessity for specialized methods in 3D medical imaging. Collectively, the open-source release of CT-RATE, CT-CLIP, and CT-CHAT not only addresses critical challenges in 3D medical imaging but also lays the groundwork for future innovations in medical AI and improved patient care.

arXiv:2403.17319공식 코드 · Papers with Code

JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset

Dialogue datasets are crucial for deep learning-based task-oriented dialogue system research. While numerous English language multi-domain task-oriented dialogue datasets have been developed and contributed to significant advancements in task-oriented dialogue systems, such a dataset does not exist in Japanese, and research in this area is limited compared to that in English. In this study, towards the advancement of research and development of task-oriented dialogue systems in Japanese, we constructed JMultiWOZ, the first Japanese language large-scale multi-domain task-oriented dialogue dataset. Using JMultiWOZ, we evaluated the dialogue state tracking and response generation capabilities of the state-of-the-art methods on the existing major English benchmark dataset MultiWOZ2.2 and the latest large language model (LLM)-based methods. Our evaluation results demonstrated that JMultiWOZ provides a benchmark that is on par with MultiWOZ2.2. In addition, through evaluation experiments of interactive dialogues with the models and human participants, we identified limitations in the task completion capabilities of LLMs in Japanese.

arXiv:2403.17209공식 코드 · Papers with Code

Generation of Asset Administration Shell with Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0

This research introduces a novel approach for achieving semantic interoperability in digital twins and assisting the creation of Asset Administration Shell (AAS) as digital twin model within the context of Industry 4.0. The foundational idea of our research is that the communication based on semantics and the generation of meaningful textual data are directly linked, and we posit that these processes are equivalent if the exchanged information can be serialized in text form. Based on this, we construct a "semantic node" data structure in our research to capture the semantic essence of textual data. Then, a system powered by large language models is designed and implemented to process the "semantic node" and generate standardized digital twin models from raw textual data collected from datasheets describing technical assets. Our evaluation demonstrates an effective generation rate of 62-79%, indicating a substantial proportion of the information from the source text can be translated error-free to the target digital twin instance model with the generative capability of large language models. This result has a direct application in the context of Industry 4.0, and the designed system is implemented as a data model generation tool for reducing the manual effort in creating AAS model. In our evaluation, a comparative analysis of different LLMs and an in-depth ablation study of Retrieval-Augmented Generation (RAG) mechanisms provide insights into the effectiveness of LLM systems for interpreting technical concepts and translating data. Our findings emphasize LLMs' capability to automate AAS instance creation and contribute to the broader field of semantic interoperability for digital twins in industrial applications. The prototype implementation and evaluation results are presented on our GitHub Repository: https://github.com/YuchenXia/AASbyLLM.

arXiv:2403.17134공식 코드 · Papers with Code

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair

Automated program repair has emerged as a powerful technique to mitigate the impact of software bugs on system reliability and user experience. This paper introduces RepairAgent, the first work to address the program repair challenge through an autonomous agent based on a large language model (LLM). Unlike existing deep learning-based approaches, which prompt a model with a fixed prompt or in a fixed feedback loop, our work treats the LLM as an agent capable of autonomously planning and executing actions to fix bugs by invoking suitable tools. RepairAgent freely interleaves gathering information about the bug, gathering repair ingredients, and validating fixes, while deciding which tools to invoke based on the gathered information and feedback from previous fix attempts. Key contributions that enable RepairAgent include a set of tools that are useful for program repair, a dynamically updated prompt format that allows the LLM to interact with these tools, and a finite state machine that guides the agent in invoking the tools. Our evaluation on the popular Defects4J dataset demonstrates RepairAgent's effectiveness in autonomously repairing 164 bugs, including 39 bugs not fixed by prior techniques. Interacting with the LLM imposes an average cost of 270,000 tokens per bug, which, under the current pricing of OpenAI's GPT-3.5 model, translates to 14 cents of USD per bug. To the best of our knowledge, this work is the first to present an autonomous, LLM-based agent for program repair, paving the way for future agent-based techniques in software engineering.

arXiv:2403.17919공식 코드 · Papers with Code

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B model typically requires at least 60 GB of GPU memory with full parameter training, which presents challenges for researchers without access to high-resource environments. Parameter Efficient Fine-Tuning techniques such as Low-Rank Adaptation (LoRA) have been proposed to alleviate this problem. However, in most large-scale fine-tuning settings, their performance does not reach the level of full parameter training because they confine the parameter search to a low-rank subspace. Attempting to complement this deficiency, we investigate the layerwise properties of LoRA on fine-tuning tasks and observe an unexpected but consistent skewness of weight norms across different layers. Utilizing this key observation, a surprisingly simple training strategy is discovered, which outperforms both LoRA and full parameter training in a wide range of settings with memory costs as low as LoRA. We name it Layerwise Importance Sampled AdamW (LISA), a promising alternative for LoRA, which applies the idea of importance sampling to different layers in LLMs and randomly freezes most middle layers during optimization. Experimental results show that with similar or less GPU memory consumption, LISA surpasses LoRA or even full parameter tuning in downstream fine-tuning tasks, where LISA consistently outperforms LoRA by over 10%-35% in terms of MT-Bench score while achieving on-par or better performance in MMLU, AGIEval and WinoGrande. On large models, specifically LLaMA-2-70B, LISA surpasses LoRA on MT-Bench, GSM8K, and PubMedQA, demonstrating its effectiveness across different domains.

arXiv:2403.17710공식 코드 · Papers with Code

Optimization-based Prompt Injection Attack to LLM-as-a-Judge

LLM-as-a-Judge uses a large language model (LLM) to select the best response from a set of candidates for a given question. LLM-as-a-Judge has many applications such as LLM-powered search, reinforcement learning with AI feedback (RLAIF), and tool selection. In this work, we propose JudgeDeceiver, an optimization-based prompt injection attack to LLM-as-a-Judge. JudgeDeceiver injects a carefully crafted sequence into an attacker-controlled candidate response such that LLM-as-a-Judge selects the candidate response for an attacker-chosen question no matter what other candidate responses are. Specifically, we formulate finding such sequence as an optimization problem and propose a gradient based method to approximately solve it. Our extensive evaluation shows that JudgeDeceive is highly effective, and is much more effective than existing prompt injection attacks that manually craft the injected sequences and jailbreak attacks when extended to our problem. We also show the effectiveness of JudgeDeceiver in three case studies, i.e., LLM-powered search, RLAIF, and tool selection. Moreover, we consider defenses including known-answer detection, perplexity detection, and perplexity windowed detection. Our results show these defenses are insufficient, highlighting the urgent need for developing new defense strategies. Our implementation is available at this repository: https://github.com/ShiJiawenwen/JudgeDeceiver.

arXiv:2403.17007공식 코드 · Papers with Code

DreamLIP: Language-Image Pre-training with Long Captions

Language-image pre-training largely relies on how precisely and thoroughly a text describes its paired image. In practice, however, the contents of an image can be so rich that well describing them requires lengthy captions (e.g., with 10 sentences), which are usually missing in existing datasets. Consequently, there are currently no clear evidences on whether and how language-image pre-training could benefit from long captions. To figure this out, we first re-caption 30M images with detailed descriptions using a pre-trained Multi-modality Large Language Model (MLLM), and then study the usage of the resulting captions under a contrastive learning framework. We observe that, each sentence within a long caption is very likely to describe the image partially (e.g., an object). Motivated by this, we propose to dynamically sample sub-captions from the text label to construct multiple positive pairs, and introduce a grouping loss to match the embeddings of each sub-caption with its corresponding local image patches in a self-supervised manner. Experimental results on a wide rage of downstream tasks demonstrate the consistent superiority of our method, termed DreamLIP, over previous alternatives, highlighting its fine-grained representational capacity. It is noteworthy that, on the tasks of image-text retrieval and semantic segmentation, our model trained with 30M image-text pairs achieves on par or even better performance than CLIP trained with 400M pairs. Project page is available at https://zyf0619sjtu.github.io/dream-lip.

arXiv:2403.16820공식 코드 · Papers with Code

Cross-lingual Contextualized Phrase Retrieval

Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks by leveraging the fine-grained information that phrases offer. In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information. However, the lack of specific training data and models are the primary challenges to achieve our goal. As a result, we extract pairs of cross-lingual phrases using word alignment information automatically induced from parallel sentences. Subsequently, we train our Cross-lingual Contextualized Phrase Retriever (CCPR) using contrastive learning, which encourages the hidden representations of phrases with similar contexts and semantics to align closely. Comprehensive experiments on both the cross-lingual phrase retrieval task and a downstream task, i.e, machine translation, demonstrate the effectiveness of CCPR. On the phrase retrieval task, CCPR surpasses baselines by a significant margin, achieving a top-1 accuracy that is at least 13 points higher. When utilizing CCPR to augment the large-language-model-based translator, it achieves average gains of 0.7 and 1.5 in BERTScore for translations from X=>En and vice versa, respectively, on WMT16 dataset. Our code and data are available at \url{https://github.com/ghrua/ccpr_release}.

arXiv:2403.16971공식 코드 · Papers with Code

AIOS: LLM Agent Operating System

LLM-based intelligent agents face significant deployment challenges, particularly related to resource management. Allowing unrestricted access to LLM or tool resources can lead to inefficient or even potentially harmful resource allocation and utilization for agents. Furthermore, the absence of proper scheduling and resource management mechanisms in current agent designs hinders concurrent processing and limits overall system efficiency. As the diversity and complexity of agents continue to grow, addressing these resource management issues becomes increasingly critical to LLM-based agent systems. To address these challenges, this paper proposes the architecture of AIOS (LLM-based AI Agent Operating System) under the context of managing LLM-based agents. It introduces a novel architecture for serving LLM-based agents by isolating resources and LLM-specific services from agent applications into an AIOS kernel. This AIOS kernel provides fundamental services (e.g., scheduling, context management, memory management, storage management, access control) and efficient management of resources (e.g., LLM and external tools) for runtime agents. To enhance usability, AIOS also includes an AIOS-Agent SDK, a comprehensive suite of APIs designed for utilizing functionalities provided by the AIOS kernel. Experimental results demonstrate that using AIOS can achieve up to 2.1x faster execution for serving agents built by various agent frameworks. The source code is available at https://github.com/agiresearch/AIOS.

arXiv:2403.16950공식 코드 · Papers with Code

Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent evaluations that align with human assessments. In this work, we first conduct a systematic study of the misalignment between LLM evaluators and human evaluation, revealing that existing calibration methods aimed at mitigating biases of LLMs are insufficient for effectively aligning LLM evaluators. Inspired by the use of preference data in RLHF, we formulate the evaluation as a ranking problem and introduce Pairwise-preference Search (PAIRS), an uncertainty-guided search-based rank aggregation method that employs LLMs to conduct pairwise comparisons locally and efficiently ranks candidate texts globally. PAIRS achieves state-of-the-art performance on representative evaluation tasks in long-form generations and demonstrates significant improvements over direct scoring. Furthermore, we provide insights into the role of pairwise preference in quantifying the transitivity of LLMs and demonstrate how PAIRS benefits from calibration using debiased pairwise evaluations.