PyTorchKR Papers

최신 논문

총 13,087편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2407.10930

Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together

Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may involve a distinct Language Model (LM) and an associated prompt template. These compound systems often lack intermediate labels or gradient flow to optimize each module, making their end-to-end optimization challenging. Here we seek strategies to optimize both the module-level LM weights and the associated prompt templates of such systems to maximize a downstream task metric. We propose for the first time combining the weight and prompt optimization strategies to optimize a modular LM pipeline by alternating between the two to get the same LM to teach itself. In experiments with multi-hop QA, mathematical reasoning, and feature-based classification using mistral-7b, llama-2-7b, and llama-3-8b, these BetterTogether strategies optimizing the weights and prompts of a pipeline together outperform directly optimizing weights alone and prompts alone by up to 60% and 6%, respectively, on average across LMs and tasks. BetterTogether optimizer is released in DSPy at http://dspy.ai

arXiv:2407.10853공식 코드 · Papers with Code

An Actionable Framework for Assessing Bias and Fairness in Large Language Model Use Cases

Large language models (LLMs) can exhibit bias in a variety of ways. Such biases can create or exacerbate unfair outcomes for certain groups within a protected attribute, including, but not limited to sex, race, sexual orientation, or age. This paper aims to provide a technical guide for practitioners to assess bias and fairness risks in LLM use cases. The main contribution of this work is a decision framework that allows practitioners to determine which metrics to use for a specific LLM use case. To achieve this, this study categorizes LLM bias and fairness risks, maps those risks to a taxonomy of LLM use cases, and then formally defines various metrics to assess each type of risk. As part of this work, several new bias and fairness metrics are introduced, including innovative counterfactual metrics as well as metrics based on stereotype classifiers. Instead of focusing solely on the model itself, the sensitivity of both prompt-risk and model-risk are taken into account by defining evaluations at the level of an LLM use case, characterized by a model and a population of prompts. Furthermore, because all of the evaluation metrics are calculated solely using the LLM output, the proposed framework is highly practical and easily actionable for practitioners.

arXiv:2407.10829

BiasScanner: Automatic Detection and Classification of News Bias to Strengthen Democracy

The increasing consumption of news online in the 21st century coincided with increased publication of disinformation, biased reporting, hate speech and other unwanted Web content. We describe BiasScanner, an application that aims to strengthen democracy by supporting news consumers with scrutinizing news articles they are reading online. BiasScanner contains a server-side pre-trained large language model to identify biased sentences of news articles and a front-end Web browser plug-in. At the time of writing, BiasScanner can identify and classify more than two dozen types of media bias at the sentence level, making it the most fine-grained model and only deployed application (automatic system in use) of its kind. It was implemented in a light-weight and privacy-respecting manner, and in addition to highlighting likely biased sentence it also provides explanations for each classification decision as well as a summary analysis for each news article. While prior research has addressed news bias detection, we are not aware of any work that resulted in a deployed browser plug-in (c.f. also biasscanner.org for a Web demo).

arXiv:2407.10805공식 코드 · Papers with Code

Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation

Retrieval-augmented generation (RAG) has improved large language models (LLMs) by using knowledge retrieval to overcome knowledge deficiencies. However, current RAG methods often fall short of ensuring the depth and completeness of retrieved information, which is necessary for complex reasoning tasks. In this work, we introduce Think-on-Graph 2.0 (ToG-2), a hybrid RAG framework that iteratively retrieves information from both unstructured and structured knowledge sources in a tight-coupling manner. Specifically, ToG-2 leverages knowledge graphs (KGs) to link documents via entities, facilitating deep and knowledge-guided context retrieval. Simultaneously, it utilizes documents as entity contexts to achieve precise and efficient graph retrieval. ToG-2 alternates between graph retrieval and context retrieval to search for in-depth clues relevant to the question, enabling LLMs to generate answers. We conduct a series of well-designed experiments to highlight the following advantages of ToG-2: 1) ToG-2 tightly couples the processes of context retrieval and graph retrieval, deepening context retrieval via the KG while enabling reliable graph retrieval based on contexts; 2) it achieves deep and faithful reasoning in LLMs through an iterative knowledge retrieval process of collaboration between contexts and the KG; and 3) ToG-2 is training-free and plug-and-play compatible with various LLMs. Extensive experiments demonstrate that ToG-2 achieves overall state-of-the-art (SOTA) performance on 6 out of 7 knowledge-intensive datasets with GPT-3.5, and can elevate the performance of smaller models (e.g., LLAMA-2-13B) to the level of GPT-3.5's direct reasoning. The source code is available on https://github.com/IDEA-FinAI/ToG-2.

arXiv:2407.10793

GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework

Methods to evaluate Large Language Model (LLM) responses and detect inconsistencies, also known as hallucinations, with respect to the provided knowledge, are becoming increasingly important for LLM applications. Current metrics fall short in their ability to provide explainable decisions, systematically check all pieces of information in the response, and are often too computationally expensive to be used in practice. We present GraphEval: a hallucination evaluation framework based on representing information in Knowledge Graph (KG) structures. Our method identifies the specific triples in the KG that are prone to hallucinations and hence provides more insight into where in the response a hallucination has occurred, if at all, than previous methods. Furthermore, using our approach in conjunction with state-of-the-art natural language inference (NLI) models leads to an improvement in balanced accuracy on various hallucination benchmarks, compared to using the raw NLI models. Lastly, we explore the use of GraphEval for hallucination correction by leveraging the structure of the KG, a method we name GraphCorrect, and demonstrate that the majority of hallucinations can indeed be rectified.

arXiv:2407.09447공식 코드 · Papers with Code

ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Low-Perplexity Toxic Prompts

Conventional approaches for the automated red-teaming of large language models (LLMs) aim to identify prompts that elicit toxic outputs from a frozen language model (the defender). This often results in the prompting model (the adversary) producing text that is unlikely to arise during autoregression. In response, we propose a reinforcement learning formulation of LLM red-teaming designed to discover prompts that both (1) elicit toxic outputs from a defender and (2) have low perplexity as scored by that defender. These prompts are the most pertinent in a red-teaming setting because the defender generates them with high probability. We solve this formulation with an online and weakly supervised form of Identity Preference Optimization (IPO), attacking models ranging from 137M to 7.8B parameters. Our policy performs competitively, producing prompts that induce defender toxicity at a rate of 2-23 times higher than baseline across model scales. Importantly, these prompts have lower perplexity than both automatically generated and human-written attacks. Furthermore, our method creates black-box attacks with 5.4-14 times increased toxicity. To assess the downstream utility of our method, we use rollouts from our policy as negative examples for downstream toxicity tuning and demonstrate improved safety.

arXiv:2407.09241

The Sociolinguistic Foundations of Language Modeling

In this paper, we introduce a sociolinguistic perspective on language modeling. We claim that large language models are inherently models of varieties of language, and we consider how this insight can inform the development and deployment of large language models. We begin by presenting a technical definition of the concept of a variety of language as developed in sociolinguistics. We then discuss how this perspective can help address five basic challenges in language modeling: social bias, domain adaptation, alignment, language change, and scale. Ultimately, we argue that it is crucial to carefully define and compile training corpora that accurately represent the specific varieties of language being modeled to maximize the performance and societal value of large language models.

arXiv:2407.09184

Does Incomplete Syntax Influence Korean Language Model? Focusing on Word Order and Case Markers

Syntactic elements, such as word order and case markers, are fundamental in natural language processing. Recent studies show that syntactic information boosts language model performance and offers clues for people to understand their learning mechanisms. Unlike languages with a fixed word order such as English, Korean allows for varied word sequences, despite its canonical structure, due to case markers that indicate the functions of sentence components. This study explores whether Korean language models can accurately capture this flexibility. We note that incomplete word orders and omitted case markers frequently appear in ordinary Korean communication. To investigate this further, we introduce the Syntactically Incomplete Korean (SIKO) dataset. Through SIKO, we assessed Korean language models' flexibility with incomplete syntax and confirmed the dataset's training value. Results indicate these models reflect Korean's inherent flexibility, accurately handling incomplete inputs. Moreover, fine-tuning with SIKO enhances the ability to handle common incomplete Korean syntactic forms. The dataset's simple construction process, coupled with significant performance enhancements, solidifies its standing as an effective data augmentation technique.

arXiv:2407.09147

AI-Powered Immersive Assistance for Interactive Task Execution in Industrial Environments

Many industrial sectors rely on well-trained employees that are able to operate complex machinery. In this work, we demonstrate an AI-powered immersive assistance system that supports users in performing complex tasks in industrial environments. Specifically, our system leverages a VR environment that resembles a juice mixer setup. This digital twin of a physical setup simulates complex industrial machinery used to mix preparations or liquids (e.g., similar to the pharmaceutical industry) and includes various containers, sensors, pumps, and flow controllers. This setup demonstrates our system's capabilities in a controlled environment while acting as a proof-of-concept for broader industrial applications. The core components of our multimodal AI assistant are a large language model and a speech-to-text model that process a video and audio recording of an expert performing the task in a VR environment. The video and speech input extracted from the expert's video enables it to provide step-by-step guidance to support users in executing complex tasks. This demonstration showcases the potential of our AI-powered assistant to reduce cognitive load, increase productivity, and enhance safety in industrial environments.

arXiv:2407.09024공식 코드 · Papers with Code

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes diffusion models for behavior modeling. However, unlike previous approaches, we represent diffusion policies as the derivative of a scalar neural network with respect to action inputs. This representation is critical because it enables direct density calculation for diffusion models, making them compatible with existing LLM alignment theories. During policy fine-tuning, we extend preference-based alignment methods like Direct Preference Optimization (DPO) to align diffusion behaviors with continuous Q-functions. Our evaluation on the D4RL benchmark shows that EDA exceeds all baseline methods in overall performance. Notably, EDA maintains about 95\% of performance and still outperforms several baselines given only 1\% of Q-labelled data during fine-tuning.

arXiv:2407.09007공식 코드 · Papers with Code

Benchmarking Language Model Creativity: A Case Study on Code Generation

As LLMs become increasingly prevalent, it is interesting to consider how ``creative'' these models can be. From cognitive science, creativity consists of at least two key characteristics: \emph{convergent} thinking (purposefulness to achieve a given goal) and \emph{divergent} thinking (adaptability to new environments or constraints) \citep{runco2003critical}. In this work, we introduce a framework for quantifying LLM creativity that incorporates the two characteristics. This is achieved by (1) Denial Prompting pushes LLMs to come up with more creative solutions to a given problem by incrementally imposing new constraints on the previous solution, compelling LLMs to adopt new strategies, and (2) defining and computing the NeoGauge metric which examines both convergent and divergent thinking in the generated creative responses by LLMs. We apply the proposed framework on Codeforces problems, a natural data source for collecting human coding solutions. We quantify NeoGauge for various proprietary and open-source models and find that even the most creative model, GPT-4, still falls short of demonstrating human-like creativity. We also experiment with advanced reasoning strategies (MCTS, self-correction, etc.) and observe no significant improvement in creativity. As a by-product of our analysis, we release NeoCoder dataset for reproducing our results on future models.

arXiv:2407.08959

Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification

Recently, various pre-trained language models (PLMs) have been proposed to prove their impressive performances on a wide range of few-shot tasks. However, limited by the unstructured prior knowledge in PLMs, it is difficult to maintain consistent performance on complex structured scenarios, such as hierarchical text classification (HTC), especially when the downstream data is extremely scarce. The main challenge is how to transfer the unstructured semantic space in PLMs to the downstream domain hierarchy. Unlike previous work on HTC which directly performs multi-label classification or uses graph neural network (GNN) to inject label hierarchy, in this work, we study the HTC problem under a few-shot setting to adapt knowledge in PLMs from an unstructured manner to the downstream hierarchy. Technically, we design a simple yet effective method named Hierarchical Iterative Conditional Random Field (HierICRF) to search the most domain-challenging directions and exquisitely crafts domain-hierarchy adaptation as a hierarchical iterative language modeling problem, and then it encourages the model to make hierarchical consistency self-correction during the inference, thereby achieving knowledge transfer with hierarchical consistency preservation. We perform HierICRF on various architectures, and extensive experiments on two popular HTC datasets demonstrate that prompt with HierICRF significantly boosts the few-shot HTC performance with an average Micro-F1 by 28.80% to 1.50% and Macro-F1 by 36.29% to 1.5% over the previous state-of-the-art (SOTA) baselines under few-shot settings, while remaining SOTA hierarchical consistency performance.

arXiv:2407.08842

Evaluating Nuanced Bias in Large Language Model Free Response Answers

Pre-trained large language models (LLMs) can now be easily adapted for specific business purposes using custom prompts or fine tuning. These customizations are often iteratively re-engineered to improve some aspect of performance, but after each change businesses want to ensure that there has been no negative impact on the system's behavior around such critical issues as bias. Prior methods of benchmarking bias use techniques such as word masking and multiple choice questions to assess bias at scale, but these do not capture all of the nuanced types of bias that can occur in free response answers, the types of answers typically generated by LLM systems. In this paper, we identify several kinds of nuanced bias in free text that cannot be similarly identified by multiple choice tests. We describe these as: confidence bias, implied bias, inclusion bias and erasure bias. We present a semi-automated pipeline for detecting these types of bias by first eliminating answers that can be automatically classified as unbiased and then co-evaluating name reversed pairs using crowd workers. We believe that the nuanced classifications our method generates can be used to give better feedback to LLMs, especially as LLM reasoning capabilities become more advanced.

arXiv:2407.08819

Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladin

This paper explores the impact of different back-translation approaches on machine translation for Ladin, specifically the Val Badia variant. Given the limited amount of parallel data available for this language (only 18k Ladin-Italian sentence pairs), we investigate the performance of a multilingual neural machine translation model fine-tuned for Ladin-Italian. In addition to the available authentic data, we synthesise further translations by using three different models: a fine-tuned neural model, a rule-based system developed specifically for this language pair, and a large language model. Our experiments show that all approaches achieve comparable translation quality in this low-resource scenario, yet round-trip translations highlight differences in model performance.

arXiv:2407.09103공식 코드 · Papers with Code

DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents

Information extraction from handwritten documents involves traditionally three distinct steps: Document Layout Analysis, Handwritten Text Recognition, and Named Entity Recognition. Recent approaches have attempted to integrate these steps into a single process using fully end-to-end architectures. Despite this, these integrated approaches have not yet matched the performance of language models, when applied to information extraction in plain text. In this paper, we introduce DANIEL (Document Attention Network for Information Extraction and Labelling), a fully end-to-end architecture integrating a language model and designed for comprehensive handwritten document understanding. DANIEL performs layout recognition, handwriting recognition, and named entity recognition on full-page documents. Moreover, it can simultaneously learn across multiple languages, layouts, and tasks. For named entity recognition, the ontology to be applied can be specified via the input prompt. The architecture employs a convolutional encoder capable of processing images of any size without resizing, paired with an autoregressive decoder based on a transformer-based language model. DANIEL achieves competitive results on four datasets, including a new state-of-the-art performance on RIMES 2009 and M-POPP for Handwriting Text Recognition, and IAM NER for Named Entity Recognition. Furthermore, DANIEL is much faster than existing approaches. We provide the source code and the weights of the trained models at \url{https://github.com/Shulk97/daniel}.

arXiv:2407.09043공식 코드 · Papers with Code

Vision Language Model is NOT All You Need: Augmentation Strategies for Molecule Language Models

Recently, there has been a growing interest among researchers in understanding molecules and their textual descriptions through molecule language models (MoLM). However, despite some early promising developments, the advancement of MoLM still trails significantly behind that of vision language models (VLM). This is because unique challenges exist apart from VLM in the field of MoLM due to 1) a limited amount of molecule-text paired data and 2) missing expertise that occurred due to the specialized areas of focus among the experts. To this end, we propose AMOLE, which 1) augments molecule-text pairs with structural similarity preserving loss, and 2) transfers the expertise between the molecules. Specifically, AMOLE enriches molecule-text pairs by sharing descriptions among structurally similar molecules with a novel structural similarity preserving loss. Moreover, we propose an expertise reconstruction loss to transfer knowledge from molecules that have extensive expertise to those with less expertise. Extensive experiments on various downstream tasks demonstrate the superiority of AMOLE in comprehending molecules and their descriptions, highlighting its potential for application in real-world drug discovery. The source code for AMOLE is available at https://github.com/Namkyeong/AMOLE.

arXiv:2407.09035

GPC: Generative and General Pathology Image Classifier

Deep learning has been increasingly incorporated into various computational pathology applications to improve its efficiency, accuracy, and robustness. Although successful, most previous approaches for image classification have crucial drawbacks. There exist numerous tasks in pathology, but one needs to build a model per task, i.e., a task-specific model, thereby increasing the number of models, training resources, and cost. Moreover, transferring arbitrary task-specific model to another task is still a challenging problem. Herein, we propose a task-agnostic generative and general pathology image classifier, so called GPC, that aims at learning from diverse kinds of pathology images and conducting numerous classification tasks in a unified model. GPC, equipped with a convolutional neural network and a Transformer-based language model, maps pathology images into a high-dimensional feature space and generates pertinent class labels as texts via the image-to-text classification mechanism. We evaluate GPC on six datasets for four different pathology image classification tasks. Experimental results show that GPC holds considerable potential for developing an effective and efficient universal model for pathology image analysis.

arXiv:2407.08942

A Neural Matrix Decomposition Recommender System Model based on the Multimodal Large Language Model

Recommendation systems have become an important solution to information search problems. This article proposes a neural matrix factorization recommendation system model based on the multimodal large language model called BoNMF. This model combines BoBERTa's powerful capabilities in natural language processing, ViT in computer in vision, and neural matrix decomposition technology. By capturing the potential characteristics of users and items, and after interacting with a low-dimensional matrix composed of user and item IDs, the neural network outputs the results. recommend. Cold start and ablation experimental results show that the BoNMF model exhibits excellent performance on large public data sets and significantly improves the accuracy of recommendations.

arXiv:2407.08836

Fault Diagnosis in Power Grids with Large Language Model

Power grid fault diagnosis is a critical task for ensuring the reliability and stability of electrical infrastructure. Traditional diagnostic systems often struggle with the complexity and variability of power grid data. This paper proposes a novel approach that leverages Large Language Models (LLMs), specifically ChatGPT and GPT-4, combined with advanced prompt engineering to enhance fault diagnosis accuracy and explainability. We designed comprehensive, context-aware prompts to guide the LLMs in interpreting complex data and providing detailed, actionable insights. Our method was evaluated against baseline techniques, including standard prompting, Chain-of-Thought (CoT), and Tree-of-Thought (ToT) methods, using a newly constructed dataset comprising real-time sensor data, historical fault records, and component descriptions. Experimental results demonstrate significant improvements in diagnostic accuracy, explainability quality, response coherence, and contextual understanding, underscoring the effectiveness of our approach. These findings suggest that prompt-engineered LLMs offer a promising solution for robust and reliable power grid fault diagnosis.

arXiv:2407.09136공식 코드 · Papers with Code

Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors

Large language models (LLMs) present an opportunity to scale high-quality personalized education to all. A promising approach towards this means is to build dialog tutoring models that scaffold students' problem-solving. However, even though existing LLMs perform well in solving reasoning questions, they struggle to precisely detect student's errors and tailor their feedback to these errors. Inspired by real-world teaching practice where teachers identify student errors and customize their response based on them, we focus on verifying student solutions and show how grounding to such verification improves the overall quality of tutor response generation. We collect a dataset of 1K stepwise math reasoning chains with the first error step annotated by teachers. We show empirically that finding the mistake in a student solution is challenging for current models. We propose and evaluate several verifiers for detecting these errors. Using both automatic and human evaluation we show that the student solution verifiers steer the generation model towards highly targeted responses to student errors which are more often correct with less hallucinations compared to existing baselines.