PyTorchKR Papers

최신 논문

총 486편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2410.04838공식 코드 · Papers with Code

Rationale-Aware Answer Verification by Pairwise Self-Evaluation

Answer verification identifies correct solutions among candidates generated by large language models (LLMs). Current approaches typically train verifier models by labeling solutions as correct or incorrect based solely on whether the final answer matches the gold answer. However, this approach neglects any flawed rationale in the solution yielding the correct answer, undermining the verifier's ability to distinguish between sound and flawed rationales. We empirically show that in StrategyQA, only 19% of LLM-generated solutions with correct answers have valid rationales, thus leading to an unreliable verifier. Furthermore, we demonstrate that training a verifier on valid rationales significantly improves its ability to distinguish valid and flawed rationale. To make a better verifier without extra human supervision, we introduce REPS (Rationale Enhancement through Pairwise Selection), a method for selecting valid rationales from candidates by iteratively applying pairwise self-evaluation using the same LLM that generates the solutions. Verifiers trained on solutions selected by REPS outperform those trained using conventional training methods on three reasoning benchmarks (ARC-Challenge, DROP, and StrategyQA). Our results suggest that training reliable verifiers requires ensuring the validity of rationales in addition to the correctness of the final answers, which would be critical for models assisting humans in solving complex reasoning tasks.

논문 ID: document/1068551

DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks

In the realm of computer vision (CV), balancing speed and accuracy remains a significant challenge. Recent efforts have focused on developing lightweight networks that optimize computational efficiency and feature extraction. However, in remote sensing (RS) imagery, where small and multiscale object detection is critical, these networks often fall short in performance. To address these challenges, DecoupleNet is proposed, an innovative lightweight backbone network specifically designed for RS visual tasks in resource-constrained environments. DecoupleNet incorporates two key modules: the feature integration downsampling (FID) module and the multibranch feature decoupling (MBFD) module. The FID module preserves small object features during downsampling, while the MBFD module enhances small and multiscale object feature representation through a novel decoupling approach. Comprehensive evaluations on three RS visual tasks demonstrate DecoupleNet’s superior balance of accuracy and computational efficiency compared to existing lightweight networks. On the NWPU-RESISC45 classification dataset, DecoupleNet achieves a top-1 accuracy of 95.30%, surpassing FasterNet by 2%, with fewer parameters and lower computational overhead. In object detection tasks using the DOTA 1.0 test set, DecoupleNet records an accuracy of 78.04%, outperforming ARC-R50 by 0.69%. For semantic segmentation on the LoveDA test set, DecoupleNet achieves 53.1% accuracy, surpassing UnetFormer by 0.70%. These findings open new avenues for advancing RS image analysis on resource-constrained devices, addressing a pivotal gap in the field. The code and pretrained models are publicly available at https://github.com/lwCVer/DecoupleNet.

arXiv:2410.02651공식 코드 · Papers with Code

CAX: Cellular Automata Accelerated in JAX

Cellular automata have become a cornerstone for investigating emergence and self-organization across diverse scientific disciplines, spanning neuroscience, artificial life, and theoretical physics. However, the absence of a hardware-accelerated cellular automata library limits the exploration of new research directions, hinders collaboration, and impedes reproducibility. In this work, we introduce CAX (Cellular Automata Accelerated in JAX), a high-performance and flexible open-source library designed to accelerate cellular automata research. CAX offers cutting-edge performance and a modular design through a user-friendly interface, and can support both discrete and continuous cellular automata with any number of dimensions. We demonstrate CAX's performance and flexibility through a wide range of benchmarks and applications. From classic models like elementary cellular automata and Conway's Game of Life to advanced applications such as growing neural cellular automata and self-classifying MNIST digits, CAX speeds up simulations up to 2,000 times faster. Furthermore, we demonstrate CAX's potential to accelerate research by presenting a collection of three novel cellular automata experiments, each implemented in just a few lines of code thanks to the library's modular architecture. Notably, we show that a simple one-dimensional cellular automaton can outperform GPT-4 on the 1D-ARC challenge.

arXiv:2410.02533

A Schema-aware Logic Reformulation for Graph Reachability

Graph reachability is the task of understanding whether two distinct points in a graph are interconnected by arcs to which in general a semantic is attached. Reachability has plenty of applications, ranging from motion planning to routing. Improving reachability requires structural knowledge of relations so as to avoid the complexity of traditional depth-first and breadth-first strategies, implemented in logic languages. In some contexts, graphs are enriched with their schema definitions establishing domain and range for every arc. The introduction of a schema-aware formalization for guiding the search may result in a sensitive improvement by cutting out unuseful paths and prioritising those that, in principle, reach the target earlier. In this work, we propose a strategy to automatically exclude and sort certain graph paths by exploiting the higher-level conceptualization of instances. The aim is to obtain a new first-order logic reformulation of the graph reachability scenario, capable of improving the traditional algorithms in terms of time, space requirements, and number of backtracks. The experiments exhibit the expected advantages of the approach in reducing the number of backtracks during the search strategy, resulting in saving time and space as well.

arXiv:2409.19765

Parameter Estimation in Optimal Tolling for Traffic Networks Under the Markovian Traffic Equilibrium

Tolling, or congestion pricing, has emerged as an effective tool for preventing gridlock in traffic systems. However, tolls are currently mostly designed on route-based traffic assignment models (TAM), which may be unrealistic and computationally expensive. Existing approaches also impractically assume that the central tolling authority can access latency function parameters that characterize the time required to traverse each network arc (edge), as well as the entropy parameter $\beta$ that characterizes commuters' stochastic arc-selection decisions on the network. To address these issues, this work formulates an online learning algorithm that simultaneously refines estimates of linear arc latency functions and entropy parameters in an arc-based TAM, while implementing tolls on each arc to induce equilibrium flows that minimize overall congestion on the network. We prove that our algorithm incurs regret upper bounded by $O(\sqrt{T} \ln(T) |\arcsMod| \max\{|\nodesMod| \ln(|\arcsMod|/|\nodesMod|), B \})$, where $T$ denotes the total iteration count, $|\arcsMod|$ and $|\nodesMod|$ denote the total number of arcs and nodes in the network, respectively, and $B$ describes the number of arcs required to construct an estimate of $\beta$ (usually $\ll |I|$). Finally, we present numerical results on simulated traffic networks that validate our theoretical contributions.

arXiv:2409.13514

LM-assisted keyword biasing with Aho-Corasick algorithm for Transducer-based ASR

Despite the recent success of end-to-end models for automatic speech recognition, recognizing special rare and out-of-vocabulary words, as well as fast domain adaptation with text, are still challenging. It often happens that biasing to the special entities leads to a degradation in the overall performance. We propose a light on-the-fly method to improve automatic speech recognition performance by combining a bias list of named entities with a word-level n-gram language model with the shallow fusion approach based on the Aho-Corasick string matching algorithm. The Aho-Corasick algorithm has proved to be more efficient than other methods and allows fast context adaptation. An n-gram language model is introduced as a graph with fail and output arcs, where the arc weights are adapted from the n-gram probabilities. The language model is used as an additional support to keyword biasing when the language model is combined with bias entities in a single context graph to take care of the overall performance. We demonstrate our findings on 4 languages, 2 public and 1 private datasets including performance on named entities and out-of-vocabulary entities. We achieve up to 21.6% relative improvement in the general word error rate with no practical difference in the inverse real-time factor.

arXiv:2409.15466공식 코드 · Papers with Code

Matérn Kernels for Tunable Implicit Surface Reconstruction

We propose to use the family of Mat\'ern kernels for tunable implicit surface reconstruction, building upon the recent success of kernel methods for 3D reconstruction of oriented point clouds. As we show, both, from a theoretical and practical perspective, Mat\'ern kernels have some appealing properties which make them particularly well suited for surface reconstruction -- outperforming state-of-the-art methods based on the arc-cosine kernel while being significantly easier to implement, faster to compute, and scaleable. Being stationary, we demonstrate that the Mat\'ern kernels' spectrum can be tuned in the same fashion as Fourier feature mappings help coordinate-based MLPs to overcome spectral bias. Moreover, we theoretically analyze Mat\'ern kernel's connection to SIREN networks as well as its relation to previously employed arc-cosine kernels. Finally, based on recently introduced Neural Kernel Fields, we present data-dependent Mat\'ern kernels and conclude that especially the Laplace kernel (being part of the Mat\'ern family) is extremely competitive, performing almost on par with state-of-the-art methods in the noise-free case while having a more than five times shorter training time.

arXiv:2409.15631공식 코드 · Papers with Code

Data Augmentation for Sparse Multidimensional Learning Performance Data Using Generative AI

Learning performance data describe correct and incorrect answers or problem-solving attempts in adaptive learning, such as in intelligent tutoring systems (ITSs). Learning performance data tend to be highly sparse (80\%\(\sim\)90\% missing observations) in most real-world applications due to adaptive item selection. This data sparsity presents challenges to using learner models to effectively predict future performance explore new hypotheses about learning. This article proposes a systematic framework for augmenting learner data to address data sparsity in learning performance data. First, learning performance is represented as a three-dimensional tensor of learners' questions, answers, and attempts, capturing longitudinal knowledge states during learning. Second, a tensor factorization method is used to impute missing values in sparse tensors of collected learner data, thereby grounding the imputation on knowledge tracing tasks that predict missing performance values based on real observations. Third, a module for generating patterns of learning is used. This study contrasts two forms of generative Artificial Intelligence (AI), including Generative Adversarial Networks (GANs) and Generate Pre-Trained Transformers (GPT) to generate data associated with different clusters of learner data. We tested this approach on an adult literacy dataset from AutoTutor lessons developed for Adult Reading Comprehension (ARC). We found that: (1) tensor factorization improved the performance in tracing and predicting knowledge mastery compared with other knowledge tracing techniques without data augmentation, showing higher relative fidelity for this imputation method, and (2) the GAN-based simulation showed greater overall stability and less statistical bias based on a divergence evaluation with varying simulation sample sizes compared to GPT.

arXiv:2409.14026

Uncovering Latent Chain of Thought Vectors in Language Models

As language models grow more influential and trusted in our society, our ability to reliably steer them toward favorable behaviors becomes increasingly paramount. For this, we investigate the technique of steering vectors: biasing the forward pass of language models using a "steering vector" derived from a specific task. We apply them to steer language models toward performing Chain of Thought (CoT) Reasoning without the need to prompt through natural language. We demonstrate this approach on Llama3 8b and Mistral 7b v0.2, and obtain competitive results compared to CoT-prompted performances on a series of reasoning benchmarks (GSM8k, MMLU, AGI Eval, ARC AI2) and qualitative examples. We find this approach yields consistent steering towards CoT responses and takes less compute than traditional methods of fine-tuning models towards CoT.

arXiv:2409.13697

Prompt Baking

Two primary ways to change LLM behavior are prompting and weight updates (e.g., fine-tuning). Prompting LLMs is simple and effective, specifying the desired changes explicitly in natural language, whereas weight updates provide more expressive and permanent behavior changes, specified implicitly via training on large datasets. We present a technique for "baking" prompts into the weights of an LLM. Prompt Baking converts a prompt $u$ and initial weights $\theta$ to a new set of weights $\theta_u$ such that new "baked" LLM behaves like the original prompted LLM. Mathematically, we minimize the KL divergence between $P_\theta(\cdot | u)$ and $P_{\theta_u}(\cdot)$, where $P$ is the LLM's probability distribution over token sequences. Across all our experiments, we find prompts can be readily baked into weight updates. Baking chain-of-thought prompts improves zero-shot performance on GSM8K, ASDiv, MBPP, ARC-Easy, ARC-Challenge, and CommonsenseQA benchmarks. Baking news headlines directly updates an LLM's knowledge. And baking instructions & personas alleviates "prompt forgetting" over long sequences. Furthermore, stopping baking early creates "half-baked" models, continuously scaling prompt strength. Baked models retain their sensitivity to further prompting and baking, including re-prompting with the baked-in prompt. Surprisingly, the re-prompted models yield further performance gains in instruction following, as well as math reasoning and coding benchmarks. Taking re-prompting and re-baking to the limit yields a form of iterative self-improvement we call Prompt Pursuit, and preliminary results on instruction following exhibit dramatic performance gains. Finally, we discuss implications for AI safety, continuous model updating, enhancing real-time learning capabilities in LLM-based agents, and generating more stable AI personas.

arXiv:2409.08642

CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks

Post-training, particularly reinforcement learning (RL) using self-play-generated data, has become a new learning paradigm for large language models (LLMs). However, scaling RL to develop a general reasoner remains a research challenge, as existing methods focus on task-specific reasoning without adequately addressing generalization across a broader range of tasks. Moreover, unlike traditional RL with limited action space, LLMs operate in an infinite space, making it crucial to search for valuable and diverse strategies to solve problems effectively. To address this, we propose searching within the action space on high-level abstract plans to enhance model generalization and introduce Critical Plan Step Learning (CPL), comprising: 1) searching on plan, using Monte Carlo Tree Search (MCTS) to explore diverse plan steps in multi-step reasoning tasks, and 2) learning critical plan steps through Step-level Advantage Preference Optimization (Step-APO), which integrates advantage estimates for step preference obtained via MCTS into Direct Preference Optimization (DPO). This combination helps the model effectively learn critical plan steps, enhancing both reasoning capabilities and generalization. Experimental results demonstrate that our method, trained exclusively on GSM8K and MATH, not only significantly improves performance on GSM8K (+10.5%) and MATH (+6.5%), but also enhances out-of-domain reasoning benchmarks, such as HumanEval (+12.2%), GPQA (+8.6%), ARC-C (+4.0%), MMLU-STEM (+2.2%), and BBH (+1.8%).

arXiv:2409.01374

H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark

The Abstraction and Reasoning Corpus (ARC) is a visual program synthesis benchmark designed to test challenging out-of-distribution generalization in humans and machines. Since 2019, limited progress has been observed on the challenge using existing artificial intelligence methods. Comparing human and machine performance is important for the validity of the benchmark. While previous work explored how well humans can solve tasks from the ARC benchmark, they either did so using only a subset of tasks from the original dataset, or from variants of ARC, and therefore only provided a tentative estimate of human performance. In this work, we obtain a more robust estimate of human performance by evaluating 1729 humans on the full set of 400 training and 400 evaluation tasks from the original ARC problem set. We estimate that average human performance lies between 73.3% and 77.2% correct with a reported empirical average of 76.2% on the training set, and between 55.9% and 68.9% correct with a reported empirical average of 64.2% on the public evaluation set. However, we also find that 790 out of the 800 tasks were solvable by at least one person in three attempts, suggesting that the vast majority of the publicly available ARC tasks are in principle solvable by typical crowd-workers recruited over the internet. Notably, while these numbers are slightly lower than earlier estimates, human performance still greatly exceeds current state-of-the-art approaches for solving ARC. To facilitate research on ARC, we publicly release our dataset, called H-ARC (human-ARC), which includes all of the submissions and action traces from human participants.

arXiv:2408.14855

Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL

This paper demonstrates that model-based reinforcement learning (model-based RL) is a suitable approach for the task of analogical reasoning. We hypothesize that model-based RL can solve analogical reasoning tasks more efficiently through the creation of internal models. To test this, we compared DreamerV3, a model-based RL method, with Proximal Policy Optimization, a model-free RL method, on the Abstraction and Reasoning Corpus (ARC) tasks. Our results indicate that model-based RL not only outperforms model-free RL in learning and generalizing from single tasks but also shows significant advantages in reasoning across similar tasks.

arXiv:2408.12621

StringNET: Neural Network based Variational Method for Transition Pathways

Rare transition events in meta-stable systems under noisy fluctuations are crucial for many non-equilibrium physical and chemical processes. In these processes, the primary contributions to reactive flux are predominantly near the transition pathways that connect two meta-stable states. Efficient computation of these paths is essential in computational chemistry. In this work, we examine the temperature-dependent maximum flux path, the minimum energy path, and the minimum action path at zero temperature. We propose the StringNET method for training these paths using variational formulations and deep learning techniques. Unlike traditional chain-of-state methods, StringNET directly parametrizes the paths through neural network functions, utilizing the arc-length parameter as the main input. The tasks of gradient descent and re-parametrization in the string method are unified into a single framework using loss functions to train deep neural networks. More importantly, the loss function for the maximum flux path is interpreted as a softmax approximation to the numerically challenging minimax problem of the minimum energy path. To compute the minimum energy path efficiently and robustly, we developed a pre-training strategy that includes the maximum flux path loss in the early training stage, significantly accelerating the computation of minimum energy and action paths. We demonstrate the superior performance of this method through various analytical and chemical examples, as well as the two- and four-dimensional Ginzburg-Landau functional energy.

arXiv:2408.12638

AI-driven Transformer Model for Fault Prediction in Non-Linear Dynamic Automotive System

Fault detection in automotive engine systems is one of the most promising research areas. Several works have been done in the field of model-based fault diagnosis. Many researchers have discovered more advanced statistical methods and algorithms for better fault detection on any automotive dynamic engine system. The gas turbines/diesel engines produce highly complex and huge data which are highly non-linear. So, researchers should come up with an automated system that is more resilient and robust enough to handle this huge, complex data in highly non-linear dynamic automotive systems. Here, I present an AI-based fault classification and prediction model in the diesel engine that can be applied to any highly non-linear dynamic automotive system. The main contribution of this paper is the AI-based Transformer fault classification and prediction model in the diesel engine concerning the worldwide harmonic light vehicle test procedure (WLTP) driving cycle. This model used 27 input dimensions, 64 hidden dimensions with 2 layers, and 9 heads to create a classifier with 12 output heads (one for fault-free data and 11 different fault types). This model was trained on the UTSA Arc High-Performance Compute (HPC) cluster with 5 NVIDIA V100 GPUs, 40-core CPUs, and 384GB RAM and achieved 70.01 % accuracy on a held test set.

arXiv:2408.11984

Chemical Reaction Neural Networks for Fitting Accelerating Rate Calorimetry Data

As the demand for lithium-ion batteries rapidly increases there is a need to design these cells in a safe manner to mitigate thermal runaway. Thermal runaway in batteries leads to an uncontrollable temperature rise and potentially fires, which is a major safety concern. Typically, when modelling the chemical kinetics of thermal runaway calorimetry data ( e.g. Accelerating Rate Calorimetry (ARC)) is needed to determine the temperature-driven decomposition kinetics. Conventional methods of fitting Arrhenius Ordinary Differential Equation (ODE) thermal runaway models to Accelerated Rate Calorimetry (ARC) data make several assumptions that reduce the fidelity and generalizability of the obtained model. In this paper, Chemical Reaction Neural Networks (CRNNs) are trained to fit the kinetic parameters of N-equation Arrhenius ODEs to ARC data obtained from a Molicel 21700 P45B. The models are found to be better approximations of the experimental data. The flexibility of the method is demonstrated by experimenting with two-equation and four-equation models. Thermal runaway simulations are conducted in 3D using the obtained kinetic parameters, showing the applicability of the obtained thermal runaway models to large-scale simulations.

arXiv:2408.08869

PEDAL: Enhancing Greedy Decoding with Large Language Models using Diverse Exemplars

Self-ensembling techniques with diverse reasoning paths such as Self-Consistency have demonstrated remarkable performance gains in text generation with Large Language Models (LLMs). However, such techniques depend on the availability of an accurate answer extraction process to aggregate across multiple outputs. Moreover, they acquire higher inference cost, in comparison to Greedy Decoding, due to generation of relatively higher number of output tokens. Research has shown that the free form text outputs from Self-Consistency can be aggregated reliably using LLMs to produce the final output. Additionally, recent advancements in LLM inference have demonstrated that usage of diverse exemplars in prompts have the ability to induce diversity in the LLM outputs. Such proven techniques can be easily extended to self-ensembling based approaches to achieve enhanced results in text generation. In this paper, we introduce PEDAL (Prompts based on Exemplar Diversity Aggregated using LLMs), a hybrid self-ensembling approach, that combines the strengths of diverse exemplar based prompts and LLM based aggregation to achieve improvement in overall performance. On the publicly available SVAMP and ARC datasets, our experiments reveal that PEDAL can achieve better accuracy than Greedy Decoding based strategies with lower inference cost compared to Self Consistency based approaches.

arXiv:2408.08648

Understanding Enthymemes in Argument Maps: Bridging Argument Mining and Logic-based Argumentation

Argument mining is natural language processing technology aimed at identifying arguments in text. Furthermore, the approach is being developed to identify the premises and claims of those arguments, and to identify the relationships between arguments including support and attack relationships. In this paper, we assume that an argument map contains the premises and claims of arguments, and support and attack relationships between them, that have been identified by argument mining. So from a piece of text, we assume an argument map is obtained automatically by natural language processing. However, to understand and to automatically analyse that argument map, it would be desirable to instantiate that argument map with logical arguments. Once we have the logical representation of the arguments in an argument map, we can use automated reasoning to analyze the argumentation (e.g. check consistency of premises, check validity of claims, and check the labelling on each arc corresponds with thw logical arguments). We address this need by using classical logic for representing the explicit information in the text, and using default logic for representing the implicit information in the text. In order to investigate our proposal, we consider some specific options for instantiation.

arXiv:2408.07602

The Dial-a-Ride Problem with Limited Pickups per Trip

The Dial-a-Ride Problem (DARP) is an optimization problem that involves determining optimal routes and schedules for several vehicles to pick up and deliver items at minimum cost. Motivated by real-world carpooling and crowdshipping scenarios, we introduce an additional constraint imposing a maximum number on the number of pickups per trip. This results in the Dial-a-Ride Problem with Limited Pickups per Trip (DARP-LPT). We apply a fragment-based method for DARP-LPT, where a fragment is a partial path. Specifically, we extend two formulations from Rist & Forbes (2021): the Fragment Flow Formulation (FFF) and the Fragment Assignment Formulation (FAF). We establish FFF's superiority over FAF, both from a theoretical as well as from a computational perspective. Furthermore, our results show that FFF and FAF significantly outperform traditional arc-based formulations in terms of solution quality and time. Additionally, compared to the two existing fragment sets, one with longer partial paths and another with shorter ones, our newly generated fragment sets perform better in terms of solution quality and time when fed into FFF.

arXiv:2407.20806공식 코드 · Papers with Code

ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning

This paper introduces ARCLE, an environment designed to facilitate reinforcement learning research on the Abstraction and Reasoning Corpus (ARC). Addressing this inductive reasoning benchmark with reinforcement learning presents these challenges: a vast action space, a hard-to-reach goal, and a variety of tasks. We demonstrate that an agent with proximal policy optimization can learn individual tasks through ARCLE. The adoption of non-factorial policies and auxiliary losses led to performance enhancements, effectively mitigating issues associated with action spaces and goal attainment. Based on these insights, we propose several research directions and motivations for using ARCLE, including MAML, GFlowNets, and World Models.