PyTorchKR Papers

최신 논문

총 420편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2406.04516공식 코드 · Papers with Code

Online Joint Fine-tuning of Multi-Agent Flows

A Flow is a collection of component models ("Agents") which constructs the solution to a complex problem via iterative communication. Flows have emerged as state of the art architectures for code generation, and are the raison d'etre for frameworks like Autogen. However, flows are currently constructed via a combination of manual prompt engineering and stagewise supervised learning techniques; the latter is limited to acyclic flows with granular node supervision. In this writeup I describe a procedure for online joint fine-tuning of an entire flow inspired by the Learning to Search framework. The approach leverages simulator access to reduce preferences over entire episodes to preferences over individual node outputs; when the components are language models the latter is a well-studied problem. The approach is applicable to reward-free settings (e.g., text feedback) if an episode evaluator model is available. I apply to the multi-hop QA dataset Musique achieving a state-of-the-art result.

arXiv:2406.04331공식 코드 · Papers with Code

PaCE: Parsimonious Concept Engineering for Large Language Models

Large Language Models (LLMs) are being used for a wide variety of tasks. While they are capable of generating human-like responses, they can also produce undesirable output including potentially harmful information, racist or sexist language, and hallucinations. Alignment methods are designed to reduce such undesirable outputs via techniques such as fine-tuning, prompt engineering, and representation engineering. However, existing methods face several challenges: some require costly fine-tuning for every alignment task; some do not adequately remove undesirable concepts, failing alignment; some remove benign concepts, lowering the linguistic capabilities of LLMs. To address these issues, we propose Parsimonious Concept Engineering (PaCE), a novel activation engineering framework for alignment. First, to sufficiently model the concepts, we construct a large-scale concept dictionary in the activation space, in which each atom corresponds to a semantic concept. Given any alignment task, we instruct a concept partitioner to efficiently annotate the concepts as benign or undesirable. Then, at inference time, we decompose the LLM activations along the concept dictionary via sparse coding, to accurately represent the activations as linear combinations of benign and undesirable components. By removing the latter ones from the activations, we reorient the behavior of the LLM towards the alignment goal. We conduct experiments on tasks such as response detoxification, faithfulness enhancement, and sentiment revising, and show that PaCE achieves state-of-the-art alignment performance while maintaining linguistic capabilities.

arXiv:2406.00027공식 코드 · Papers with Code

Adapting PromptORE for Modern History: Information Extraction from Hispanic Monarchy Documents of the XVIth Century

Semantic relations among entities are a widely accepted method for relation extraction. PromptORE (Prompt-based Open Relation Extraction) was designed to improve relation extraction with Large Language Models on generalistic documents. However, it is less effective when applied to historical documents, in languages other than English. In this study, we introduce an adaptation of PromptORE to extract relations from specialized documents, namely digital transcripts of trials from the Spanish Inquisition. Our approach involves fine-tuning transformer models with their pretraining objective on the data they will perform inference. We refer to this process as "biasing". Our Biased PromptORE addresses complex entity placements and genderism that occur in Spanish texts. We solve these issues by prompt engineering. We evaluate our method using Encoder-like models, corroborating our findings with experts' assessments. Additionally, we evaluate the performance using a binomial classification benchmark. Our results show a substantial improvement in accuracy -up to a 50% improvement with our Biased PromptORE models in comparison to the baseline models using standard PromptORE.

arXiv:2406.00426공식 코드 · Papers with Code

InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation

Tabular data are omnipresent in various sectors of industries. Neural networks for tabular data such as TabNet have been proposed to make predictions while leveraging the attention mechanism for interpretability. However, the inferred attention masks are often dense, making it challenging to come up with rationales about the predictive signal. To remedy this, we propose InterpreTabNet, a variant of the TabNet model that models the attention mechanism as a latent variable sampled from a Gumbel-Softmax distribution. This enables us to regularize the model to learn distinct concepts in the attention masks via a KL Divergence regularizer. It prevents overlapping feature selection by promoting sparsity which maximizes the model's efficacy and improves interpretability to determine the important features when predicting the outcome. To assist in the interpretation of feature interdependencies from our model, we employ a large language model (GPT-4) and use prompt engineering to map from the learned feature mask onto natural language text describing the learned signal. Through comprehensive experiments on real-world datasets, we demonstrate that InterpreTabNet outperforms previous methods for interpreting tabular data while attaining competitive accuracy.

arXiv:2405.19425공식 코드 · Papers with Code

Adaptive In-conversation Team Building for Language Model Agents

Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks, while the effective design of multiple agents for a particular application remains an art. It is thus intriguing to answer a critical question: Given a task, how can we build a team of LLM agents to solve it effectively? Our new adaptive team-building paradigm offers a flexible solution, realized through a novel agent design named Captain Agent. It dynamically forms and manages teams for each step of a task-solving process, utilizing nested group conversations and reflection to ensure diverse expertise and prevent stereotypical outputs, allowing for a flexible yet structured approach to problem-solving. A comprehensive evaluation across six real-world scenarios demonstrates that Captain Agent significantly outperforms existing multi-agent methods with 21.94% improvement in average accuracy, providing outstanding performance without requiring task-specific prompt engineering. Our exploration of different backbone LLM and cost analysis further shows that Captain Agent can improve the conversation quality of weak LLM and achieve competitive performance with extremely low cost, which illuminates the application of multi-agent systems.

arXiv:2405.19616공식 코드 · Papers with Code

Easy Problems That LLMs Get Wrong

We introduce a comprehensive Linguistic Benchmark designed to evaluate the limitations of Large Language Models (LLMs) in domains such as logical reasoning, spatial intelligence, and linguistic understanding, among others. Through a series of straightforward questions, it uncovers the significant limitations of well-regarded models to perform tasks that humans manage with ease. It also highlights the potential of prompt engineering to mitigate some errors and underscores the necessity for better training methodologies. Our findings stress the importance of grounding LLMs with human reasoning and common sense, emphasising the need for human-in-the-loop for enterprise applications. We hope this work paves the way for future research to enhance the usefulness and reliability of new models.

arXiv:2405.19119공식 코드 · Papers with Code

Can Graph Learning Improve Planning in LLM-based Agents?

Task planning in language agents is emerging as an important research topic alongside the development of large language models (LLMs). It aims to break down complex user requests in natural language into solvable sub-tasks, thereby fulfilling the original requests. In this context, the sub-tasks can be naturally viewed as a graph, where the nodes represent the sub-tasks, and the edges denote the dependencies among them. Consequently, task planning is a decision-making problem that involves selecting a connected path or subgraph within the corresponding graph and invoking it. In this paper, we explore graph learning-based methods for task planning, a direction that is orthogonal to the prevalent focus on prompt design. Our interest in graph learning stems from a theoretical discovery: the biases of attention and auto-regressive loss impede LLMs' ability to effectively navigate decision-making on graphs, which is adeptly addressed by graph neural networks (GNNs). This theoretical insight led us to integrate GNNs with LLMs to enhance overall performance. Extensive experiments demonstrate that GNN-based methods surpass existing solutions even without training, and minimal training can further enhance their performance. The performance gain increases with a larger task graph size.

arXiv:2405.17743공식 코드 · Papers with Code

ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling

Optimization modeling plays a critical role in the application of Operations Research (OR) tools to address real-world problems, yet they pose challenges and require extensive expertise from OR experts. With the advent of large language models (LLMs), new opportunities have emerged to streamline and automate such task. However, current research predominantly relies on closed-source LLMs such as GPT-4, along with extensive prompt engineering techniques. This reliance stems from the scarcity of high-quality training datasets for optimization modeling, resulting in elevated costs, prolonged processing times, and privacy concerns. To address these challenges, our work is the first to propose a viable path for training open-source LLMs that are capable of optimization modeling and developing solver codes, eventually leading to a superior ability for automating optimization modeling and solving. Particularly, we design the {\sc OR-Instruct}, a semi-automated data synthesis framework for optimization modeling that enables customizable enhancements for specific scenarios or model types. This work also introduces IndustryOR, the first industrial benchmark for evaluating LLMs in solving practical OR problems. We train several 7B-scale open-source LLMs using synthesized data (dubbed ORLMs{https://github.com/Cardinal-Operations/ORLM}), which exhibit significantly enhanced optimization modeling capabilities, achieving competitive performance across the NL4OPT, MAMO, and IndustryOR benchmarks. Additionally, our experiments highlight the potential of scaling law and reinforcement learning to further enhance the performance of ORLMs. The workflows and human-machine interaction paradigms of ORLMs in practical industrial applications are also discussed in the paper.

arXiv:2405.15729공식 코드 · Papers with Code

Optimizing Large Language Models for OpenAPI Code Completion

Recent advancements in Large Language Models (LLMs) and their utilization in code generation tasks have significantly reshaped the field of software development. Despite the remarkable efficacy of code completion solutions in mainstream programming languages, their performance lags when applied to less ubiquitous formats such as OpenAPI definitions. This study evaluates the OpenAPI completion performance of GitHub Copilot, a prevalent commercial code completion tool, and proposes a set of task-specific optimizations leveraging Meta's open-source model Code Llama. A semantics-aware OpenAPI completion benchmark proposed in this research is used to perform a series of experiments through which the impact of various prompt-engineering and fine-tuning techniques on the Code Llama model's performance is analyzed. The fine-tuned Code Llama model reaches a peak correctness improvement of 55.2% over GitHub Copilot despite utilizing 25 times fewer parameters than the commercial solution's underlying Codex model. Additionally, this research proposes an enhancement to a widely used code infilling training technique, addressing the issue of underperformance when the model is prompted with context sizes smaller than those used during training. The dataset, the benchmark, and the model fine-tuning code are made publicly available.

arXiv:2405.14977공식 코드 · Papers with Code

A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models

In deep learning, maintaining model robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time, with a particular emphasis on CLIP and its variants. The study systematically examines prompt-based techniques and existing test-time adaptation methods, aiming to improve the robustness under distribution shift in diverse real-world scenarios. Specifically, the investigation covers various prompt engineering strategies, including handcrafted prompts, prompt ensembles, and prompt learning techniques. Additionally, we introduce a vision-text-space ensemble that substantially enhances average performance compared to text-space-only ensembles. Since online test-time adaptation has shown to be effective to mitigate performance drops under distribution shift, the study extends its scope to evaluate the effectiveness of existing test-time adaptation methods that were originally designed for vision-only classification models. Through extensive experimental evaluations conducted across multiple datasets and diverse model architectures, the research demonstrates the effectiveness of these adaptation strategies. Code is available at: https://github.com/mariodoebler/test-time-adaptation

arXiv:2405.06706공식 코드 · Papers with Code

Exploring the Capabilities of Large Multimodal Models on Dense Text

While large multi-modal models (LMM) have shown notable progress in multi-modal tasks, their capabilities in tasks involving dense textual content remains to be fully explored. Dense text, which carries important information, is often found in documents, tables, and product descriptions. Understanding dense text enables us to obtain more accurate information, assisting in making better decisions. To further explore the capabilities of LMM in complex text tasks, we propose the DT-VQA dataset, with 170k question-answer pairs. In this paper, we conduct a comprehensive evaluation of GPT4V, Gemini, and various open-source LMMs on our dataset, revealing their strengths and weaknesses. Furthermore, we evaluate the effectiveness of two strategies for LMM: prompt engineering and downstream fine-tuning. We find that even with automatically labeled training datasets, significant improvements in model performance can be achieved. We hope that this research will promote the study of LMM in dense text tasks. Code will be released at https://github.com/Yuliang-Liu/MultimodalOCR.

arXiv:2405.06454공식 코드 · Papers with Code

E2TP: Element to Tuple Prompting Improves Aspect Sentiment Tuple Prediction

Generative approaches have significantly influenced Aspect-Based Sentiment Analysis (ABSA), garnering considerable attention. However, existing studies often predict target text components monolithically, neglecting the benefits of utilizing single elements for tuple prediction. In this paper, we introduce Element to Tuple Prompting (E2TP), employing a two-step architecture. The former step focuses on predicting single elements, while the latter step completes the process by mapping these predicted elements to their corresponding tuples. E2TP is inspired by human problem-solving, breaking down tasks into manageable parts, using the first step's output as a guide in the second step. Within this strategy, three types of paradigms, namely E2TP($diet$), E2TP($f_1$), and E2TP($f_2$), are designed to facilitate the training process. Beyond dataset-specific experiments, our paper addresses cross-domain scenarios, demonstrating the effectiveness and generalizability of the approach. By conducting a comprehensive analysis on various benchmarks, we show that E2TP achieves new state-of-the-art results in nearly all cases.

arXiv:2405.05600공식 코드 · Papers with Code

Can We Use Large Language Models to Fill Relevance Judgment Holes?

Incomplete relevance judgments limit the re-usability of test collections. When new systems are compared against previous systems used to build the pool of judged documents, they often do so at a disadvantage due to the ``holes'' in test collection (i.e., pockets of un-assessed documents returned by the new system). In this paper, we take initial steps towards extending existing test collections by employing Large Language Models (LLM) to fill the holes by leveraging and grounding the method using existing human judgments. We explore this problem in the context of Conversational Search using TREC iKAT, where information needs are highly dynamic and the responses (and, the results retrieved) are much more varied (leaving bigger holes). While previous work has shown that automatic judgments from LLMs result in highly correlated rankings, we find substantially lower correlates when human plus automatic judgments are used (regardless of LLM, one/two/few shot, or fine-tuned). We further find that, depending on the LLM employed, new runs will be highly favored (or penalized), and this effect is magnified proportionally to the size of the holes. Instead, one should generate the LLM annotations on the whole document pool to achieve more consistent rankings with human-generated labels. Future work is required to prompt engineering and fine-tuning LLMs to reflect and represent the human annotations, in order to ground and align the models, such that they are more fit for purpose.

arXiv:2405.03677공식 코드 · Papers with Code

Towards A Human-in-the-Loop LLM Approach to Collaborative Discourse Analysis

LLMs have demonstrated proficiency in contextualizing their outputs using human input, often matching or beating human-level performance on a variety of tasks. However, LLMs have not yet been used to characterize synergistic learning in students' collaborative discourse. In this exploratory work, we take a first step towards adopting a human-in-the-loop prompt engineering approach with GPT-4-Turbo to summarize and categorize students' synergistic learning during collaborative discourse. Our preliminary findings suggest GPT-4-Turbo may be able to characterize students' synergistic learning in a manner comparable to humans and that our approach warrants further investigation.

arXiv:2405.03194공식 코드 · Papers with Code

CityLLaVA: Efficient Fine-Tuning for VLMs in City Scenario

In the vast and dynamic landscape of urban settings, Traffic Safety Description and Analysis plays a pivotal role in applications ranging from insurance inspection to accident prevention. This paper introduces CityLLaVA, a novel fine-tuning framework for Visual Language Models (VLMs) designed for urban scenarios. CityLLaVA enhances model comprehension and prediction accuracy through (1) employing bounding boxes for optimal visual data preprocessing, including video best-view selection and visual prompt engineering during both training and testing phases; (2) constructing concise Question-Answer sequences and designing textual prompts to refine instruction comprehension; (3) implementing block expansion to fine-tune large VLMs efficiently; and (4) advancing prediction accuracy via a unique sequential questioning-based prediction augmentation. Demonstrating top-tier performance, our method achieved a benchmark score of 33.4308, securing the leading position on the leaderboard. The code can be found: https://github.com/alibaba/AICITY2024_Track2_AliOpenTrek_CityLLaVA

arXiv:2405.02345공식 코드 · Papers with Code

Exploring the Capabilities of Large Language Models for Generating Diverse Design Solutions

Access to large amounts of diverse design solutions can support designers during the early stage of the design process. In this paper, we explore the efficacy of large language models (LLM) in producing diverse design solutions, investigating the level of impact that parameter tuning and various prompt engineering techniques can have on the diversity of LLM-generated design solutions. Specifically, LLMs are used to generate a total of 4,000 design solutions across five distinct design topics, eight combinations of parameters, and eight different types of prompt engineering techniques, comparing each combination of parameter and prompt engineering method across four different diversity metrics. LLM-generated solutions are compared against 100 human-crowdsourced solutions in each design topic using the same set of diversity metrics. Results indicate that human-generated solutions consistently have greater diversity scores across all design topics. Using a post hoc logistic regression analysis we investigate whether these differences primarily exist at the semantic level. Results show that there is a divide in some design topics between humans and LLM-generated solutions, while others have no clear divide. Taken together, these results contribute to the understanding of LLMs' capabilities in generating a large volume of diverse design solutions and offer insights for future research that leverages LLMs to generate diverse design solutions for a broad range of design tasks (e.g., inspirational stimuli).

arXiv:2405.00828공식 코드 · Papers with Code

WIBA: What Is Being Argued? A Comprehensive Approach to Argument Mining

We propose WIBA, a novel framework and suite of methods that enable the comprehensive understanding of "What Is Being Argued" across contexts. Our approach develops a comprehensive framework that detects: (a) the existence, (b) the topic, and (c) the stance of an argument, correctly accounting for the logical dependence among the three tasks. Our algorithm leverages the fine-tuning and prompt-engineering of Large Language Models. We evaluate our approach and show that it performs well in all the three capabilities. First, we develop and release an Argument Detection model that can classify a piece of text as an argument with an F1 score between 79% and 86% on three different benchmark datasets. Second, we release a language model that can identify the topic being argued in a sentence, be it implicit or explicit, with an average similarity score of 71%, outperforming current naive methods by nearly 40%. Finally, we develop a method for Argument Stance Classification, and evaluate the capability of our approach, showing it achieves a classification F1 score between 71% and 78% across three diverse benchmark datasets. Our evaluation demonstrates that WIBA allows the comprehensive understanding of What Is Being Argued in large corpora across diverse contexts, which is of core interest to many applications in linguistics, communication, and social and computer science. To facilitate accessibility to the advancements outlined in this work, we release WIBA as a free open access platform (wiba.dev).

arXiv:2405.00972공식 코드 · Papers with Code

CACTUS: Chemistry Agent Connecting Tool-Usage to Science

Large language models (LLMs) have shown remarkable potential in various domains, but they often lack the ability to access and reason over domain-specific knowledge and tools. In this paper, we introduced CACTUS (Chemistry Agent Connecting Tool-Usage to Science), an LLM-based agent that integrates cheminformatics tools to enable advanced reasoning and problem-solving in chemistry and molecular discovery. We evaluate the performance of CACTUS using a diverse set of open-source LLMs, including Gemma-7b, Falcon-7b, MPT-7b, Llama2-7b, and Mistral-7b, on a benchmark of thousands of chemistry questions. Our results demonstrate that CACTUS significantly outperforms baseline LLMs, with the Gemma-7b and Mistral-7b models achieving the highest accuracy regardless of the prompting strategy used. Moreover, we explore the impact of domain-specific prompting and hardware configurations on model performance, highlighting the importance of prompt engineering and the potential for deploying smaller models on consumer-grade hardware without significant loss in accuracy. By combining the cognitive capabilities of open-source LLMs with domain-specific tools, CACTUS can assist researchers in tasks such as molecular property prediction, similarity searching, and drug-likeness assessment. Furthermore, CACTUS represents a significant milestone in the field of cheminformatics, offering an adaptable tool for researchers engaged in chemistry and molecular discovery. By integrating the strengths of open-source LLMs with domain-specific tools, CACTUS has the potential to accelerate scientific advancement and unlock new frontiers in the exploration of novel, effective, and safe therapeutic candidates, catalysts, and materials. Moreover, CACTUS's ability to integrate with automated experimentation platforms and make data-driven decisions in real time opens up new possibilities for autonomous discovery.

arXiv:2404.17749공식 코드 · Papers with Code

UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt -- A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis

This paper presents our team's participation in the MEDIQA-ClinicalNLP2024 shared task B. We present a novel approach to diagnosing clinical dermatology cases by integrating large multimodal models, specifically leveraging the capabilities of GPT-4V under a retriever and a re-ranker framework. Our investigation reveals that GPT-4V, when used as a retrieval agent, can accurately retrieve the correct skin condition 85% of the time using dermatological images and brief patient histories. Additionally, we empirically show that Naive Chain-of-Thought (CoT) works well for retrieval while Medical Guidelines Grounded CoT is required for accurate dermatological diagnosis. Further, we introduce a Multi-Agent Conversation (MAC) framework and show its superior performance and potential over the best CoT strategy. The experiments suggest that using naive CoT for retrieval and multi-agent conversation for critique-based diagnosis, GPT-4V can lead to an early and accurate diagnosis of dermatological conditions. The implications of this work extend to improving diagnostic workflows, supporting dermatological education, and enhancing patient care by providing a scalable, accessible, and accurate diagnostic tool.

arXiv:2404.16859공식 코드 · Papers with Code

Rumour Evaluation with Very Large Language Models

Conversational prompt-engineering-based large language models (LLMs) have enabled targeted control over the output creation, enhancing versatility, adaptability and adhoc retrieval. From another perspective, digital misinformation has reached alarming levels. The anonymity, availability and reach of social media offer fertile ground for rumours to propagate. This work proposes to leverage the advancement of prompting-dependent LLMs to combat misinformation by extending the research efforts of the RumourEval task on its Twitter dataset. To the end, we employ two prompting-based LLM variants (GPT-3.5-turbo and GPT-4) to extend the two RumourEval subtasks: (1) veracity prediction, and (2) stance classification. For veracity prediction, three classifications schemes are experimented per GPT variant. Each scheme is tested in zero-, one- and few-shot settings. Our best results outperform the precedent ones by a substantial margin. For stance classification, prompting-based-approaches show comparable performance to prior results, with no improvement over finetuning methods. Rumour stance subtask is also extended beyond the original setting to allow multiclass classification. All of the generated predictions for both subtasks are equipped with confidence scores determining their trustworthiness degree according to the LLM, and post-hoc justifications for explainability and interpretability purposes. Our primary aim is AI for social good.