PyTorchKR Papers

최신 논문

총 486편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2501.06642

Common Sense Is All You Need

Artificial intelligence (AI) has made significant strides in recent years, yet it continues to struggle with a fundamental aspect of cognition present in all animals: common sense. Current AI systems, including those designed for complex tasks like autonomous driving, problem-solving challenges such as the Abstraction and Reasoning Corpus (ARC), and conversational benchmarks like the Turing Test, often lack the ability to adapt to new situations without extensive prior knowledge. This manuscript argues that integrating common sense into AI systems is essential for achieving true autonomy and unlocking the full societal and commercial value of AI. We propose a shift in the order of knowledge acquisition emphasizing the importance of developing AI systems that start from minimal prior knowledge and are capable of contextual learning, adaptive reasoning, and embodiment -- even within abstract domains. Additionally, we highlight the need to rethink the AI software stack to address this foundational challenge. Without common sense, AI systems may never reach true autonomy, instead exhibiting asymptotic performance that approaches theoretical ideals like AIXI but remains unattainable in practice due to infinite resource and computation requirements. While scaling AI models and passing benchmarks like the Turing Test have brought significant advancements in applications that do not require autonomy, these approaches alone are insufficient to achieve autonomous AI with common sense. By redefining existing benchmarks and challenges to enforce constraints that require genuine common sense, and by broadening our understanding of embodiment to include both physical and abstract domains, we can encourage the development of AI systems better equipped to handle the complexities of real-world and abstract environments.

arXiv:2501.07458

Understanding and Benchmarking Artificial Intelligence: OpenAI's o3 Is Not AGI

OpenAI's o3 achieves a high score of 87.5 % on ARC-AGI, a benchmark proposed to measure intelligence. This raises the question whether systems based on Large Language Models (LLMs), particularly o3, demonstrate intelligence and progress towards artificial general intelligence (AGI). Building on the distinction between skills and intelligence made by Fran\c{c}ois Chollet, the creator of ARC-AGI, a new understanding of intelligence is introduced: an agent is the more intelligent, the more efficiently it can achieve the more diverse goals in the more diverse worlds with the less knowledge. An analysis of the ARC-AGI benchmark shows that its tasks represent a very specific type of problem that can be solved by massive trialling of combinations of predefined operations. This method is also applied by o3, achieving its high score through the extensive use of computing power. However, for most problems in the physical world and in the human domain, solutions cannot be tested in advance and predefined operations are not available. Consequently, massive trialling of predefined operations, as o3 does, cannot be a basis for AGI - instead, new approaches are required that can reliably solve a wide variety of problems without existing skills. To support this development, a new benchmark for intelligence is outlined that covers a much higher diversity of unknown tasks to be solved, thus enabling a comprehensive assessment of intelligence and of progress towards AGI.

arXiv:2501.05752

Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models

Recent advancements in large language models (LLMs) have shown remarkable potential in various complex tasks requiring multi-step reasoning methods like tree search to explore diverse reasoning paths. However, existing methods often suffer from computational inefficiency and redundancy. First, they overlook the diversity of task difficulties, leading to unnecessarily extensive searches even for easy tasks. Second, they neglect the semantics of reasoning paths, resulting in redundant exploration of semantically identical paths. To address these limitations, we propose Semantic Exploration with Adaptive Gating (SEAG), a computationally efficient method. SEAG employs an adaptive gating mechanism that dynamically decides whether to conduct a tree search, based on the confidence level of answers from a preceding simple reasoning method. Furthermore, its tree-based exploration consolidates semantically identical reasoning steps, reducing redundant explorations while maintaining or even improving accuracy. Our extensive experiments demonstrate that SEAG significantly improves accuracy by 4.3% on average while requiring only 31% of computational costs compared to existing tree search-based methods on complex reasoning benchmarks including GSM8K and ARC with diverse language models such as Llama2, Llama3, and Mistral.

arXiv:2501.04281

Cluster & Disperse: a general air conflict resolution heuristic using unsupervised learning

We provide a general and malleable heuristic for the air conflict resolution problem. This heuristic is based on a new neighborhood structure for searching the solution space of trajectories and flight-levels. Using unsupervised learning, the core idea of our heuristic is to cluster the conflict points and disperse them in various flight levels. Our first algorithm is called Cluster & Disperse and in each iteration it assigns the most problematic flights in each cluster to another flight-level. In effect, we shuffle them between the flight-levels until we achieve a well-balanced configuration. The Cluster & Disperse algorithm then uses any horizontal plane conflict resolution algorithm as a subroutine to solve these well-balanced instances. Nevertheless, we develop a novel algorithm for the horizontal plane based on a similar idea. That is we cluster and disperse the conflict points spatially in the same flight level using the gradient descent and a social force. We use a novel maneuver making flights travel on an arc instead of a straight path which is based on the aviation routine of the Radius to Fix legs. Our algorithms can handle a high density of flights within a reasonable computation time. We put their performance in context with some notable algorithms from the literature. Being a general framework, a particular strength of the Cluster & Disperse is its malleability in allowing various constraints regarding the aircraft or the environment to be integrated with ease. This is in contrast to the models for instance based on mixed integer programming.

arXiv:2501.04424공식 코드 · Papers with Code

NSA: Neuro-symbolic ARC Challenge

The Abstraction and Reasoning Corpus (ARC) evaluates general reasoning capabilities that are difficult for both machine learning models and combinatorial search methods. We propose a neuro-symbolic approach that combines a transformer for proposal generation with combinatorial search using a domain-specific language. The transformer narrows the search space by proposing promising search directions, which allows the combinatorial search to find the actual solution in short time. We pre-train the trainsformer with synthetically generated data. During test-time we generate additional task-specific training tasks and fine-tune our model. Our results surpass comparable state of the art on the ARC evaluation set by 27% and compare favourably on the ARC train set. We make our code and dataset publicly available at https://github.com/Batorskq/NSA.

arXiv:2501.00852공식 코드 · Papers with Code

Hybridising Reinforcement Learning and Heuristics for Hierarchical Directed Arc Routing Problems

The Hierarchical Directed Capacitated Arc Routing Problem (HDCARP) is an extension of the Capacitated Arc Routing Problem (CARP), where the arcs of a graph are divided into classes based on their priority. The traversal of these classes is determined by either precedence constraints or a hierarchical objective, resulting in two distinct HDCARP variants. To the best of our knowledge, only one matheuristic has been proposed for these variants, but it performs relatively slowly, particularly for large-scale instances (Ha et al., 2024). In this paper, we propose a fast heuristic to efficiently address the computational challenges of HDCARP. Furthermore, we incorporate Reinforcement Learning (RL) into our heuristic to effectively guide the selection of local search operators, resulting in a hybrid algorithm. We name this hybrid algorithm as the Hybrid Reinforcement Learning and Heuristic Algorithm for Directed Arc Routing (HRDA). The hybrid algorithm adapts to changes in the problem dynamically, using real-time feedback to improve routing strategies and solution's quality by integrating heuristic methods. Extensive computational experiments on artificial instances demonstrate that this hybrid approach significantly improves the speed of the heuristic without deteriorating the solution quality. Our source code is publicly available at: https://github.com/HySonLab/ArcRoute

arXiv:2412.16181공식 코드 · Papers with Code

Minimum Weighted Feedback Arc Sets for Ranking from Pairwise Comparisons

The Minimum Weighted Feedback Arc Set (MWFAS) problem is fundamentally connected to the Ranking Problem -- the task of deriving global rankings from pairwise comparisons. Recent work [He et al. ICML2022] has advanced the state-of-the-art for the Ranking Problem using learning-based methods, improving upon multiple previous approaches. However, the connection to MWFAS remains underexplored. This paper investigates this relationship and presents efficient combinatorial algorithms for solving MWFAS, thus addressing the Ranking Problem. Our experimental results demonstrate that these simple, learning-free algorithms not only significantly outperform learning-based methods in terms of speed but also generally achieve superior ranking accuracy.

arXiv:2412.17758

In Case You Missed It: ARC 'Challenge' Is Not That Challenging

ARC Challenge appears more difficult than ARC Easy for modern LLMs primarily due to an evaluation setup that prevents direct comparison of answer choices rather than inherent complexity. Although some researchers have quietly shifted to a more appropriate scheme over the last year, the implications of this change have yet to be widely acknowledged. We highlight this overlooked shift, show how similar evaluation practices falsely imply reasoning deficits in other benchmarks, and demonstrate that fairer methods dramatically reduce performance gaps (e.g. on SIQA) and even yield superhuman results (OpenBookQA). In doing so, we reveal how evaluation shapes perceived difficulty and offer guidelines to ensure that multiple-choice evaluations accurately reflect actual model capabilities.

arXiv:2409.13203공식 코드 · Papers with Code

Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks

In this paper, we propose $\textbf{Ne}$ural-$\textbf{Sy}$mbolic $\textbf{C}$ollaborative $\textbf{D}$istillation ($\textbf{NesyCD}$), a novel knowledge distillation method for learning the complex reasoning abilities of Large Language Models (LLMs, e.g., \textgreater 13B). We argue that complex reasoning tasks are difficult for Small Language Models (SLMs, e.g., $\leq$ 7B), as these tasks demand not only general cognitive abilities but also specialized knowledge, which is often sparse and difficult for these neural-based SLMs to effectively capture. Therefore, NesyCD distills the general capabilities and specialized knowledge in LLMs using different manners. On the one hand, we distill only general abilities from teacher LLMs into the student SLMs of parameterized neural networks. On the other hand, for the specialized abilities and uncommon knowledge of a complex reasoning task, we employ a symbolic knowledge distillation approach to obtain and store the specialized knowledge within a symbolic knowledge base (KB). By decoupling general and specialized capabilities, the proposed NesyCD can achieve superior performance cost-effectively, utilizing smaller models and blending parameterized neural networks with symbolic KB. Moreover, the specialized KB generalizes well and is comprehended and manipulated by humans. Our experiments show that NesyCD significantly boosts SLMs' complex reasoning performance on in-domain (BBH, GSM8K) and out-of-domain (AGIEval, ARC) datasets. Notably, our approach enabled the LLaMA3-8B and Qwen2-7B to surpass GPT-3.5-turbo in performance and come close to matching LLaMA3-70B, despite the latter having nine times more parameters. Our code will be available at https://github.com/Xnhyacinth/NesyCD.

arXiv:2412.08347

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs

We present SmolTulu-1.7b-Instruct, referenced in this report as SmolTulu-DPO-1130, an instruction-tuned language model that adapts AllenAI's Tulu 3 post-training pipeline to enhance Huggingface's SmolLM2-1.7B base model. Through comprehensive empirical analysis using a 135M parameter model, we demonstrate that the relationship between learning rate and batch size significantly impacts model performance in a task-dependent manner. Our findings reveal a clear split: reasoning tasks like ARC and GSM8K benefit from higher learning rate to batch size ratios, while pattern recognition tasks such as HellaSwag and IFEval show optimal performance with lower ratios. These insights informed the development of SmolTulu, which achieves state-of-the-art performance among sub-2B parameter models on instruction following, scoring 67.7% on IFEval ($\Delta$11%), and mathematical reasoning with 51.6% on GSM8K ($\Delta$3.4%), with an alternate version achieving scoring 57.1% on ARC ($\Delta5.4%$). We release our model, training recipes, and ablation studies to facilitate further research in efficient model alignment, demonstrating that careful adaptation of optimization dynamics can help bridge the capability gap between small and large language models.

arXiv:2412.07322공식 코드 · Papers with Code

ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)

The Abstraction and Reasoning Corpus (ARC) poses a significant challenge to artificial intelligence, demanding broad generalization and few-shot learning capabilities that remain elusive for current deep learning methods, including large language models (LLMs). While LLMs excel in program synthesis, their direct application to ARC yields limited success. To address this, we introduce ConceptSearch, a novel function-search algorithm that leverages LLMs for program generation and employs a concept-based scoring method to guide the search efficiently. Unlike simplistic pixel-based metrics like Hamming distance, ConceptSearch evaluates programs on their ability to capture the underlying transformation concept reflected in the input-output examples. We explore three scoring functions: Hamming distance, a CNN-based scoring function, and an LLM-based natural language scoring function. Experimental results demonstrate the effectiveness of ConceptSearch, achieving a significant performance improvement over direct prompting with GPT-4. Moreover, our novel concept-based scoring exhibits up to 30% greater efficiency compared to Hamming distance, measured in terms of the number of iterations required to reach the correct solution. These findings highlight the potential of LLM-driven program search when integrated with concept-based guidance for tackling challenging generalization problems like ARC.

arXiv:2412.04604공식 코드 · Papers with Code

ARC Prize 2024: Technical Report

As of December 2024, the ARC-AGI benchmark is five years old and remains unbeaten. We believe it is currently the most important unsolved AI benchmark in the world because it seeks to measure generalization on novel tasks -- the essence of intelligence -- as opposed to skill at tasks that can be prepared for in advance. This year, we launched ARC Prize, a global competition to inspire new ideas and drive open progress towards AGI by reaching a target benchmark score of 85\%. As a result, the state-of-the-art score on the ARC-AGI private evaluation set increased from 33\% to 55.5\%, propelled by several frontier AGI reasoning techniques including deep learning-guided program synthesis and test-time training. In this paper, we survey top approaches, review new open-source implementations, discuss the limitations of the ARC-AGI-1 dataset, and share key insights gained from the competition.

arXiv:2412.02928

Asymptotic enumeration of normal and hybridization networks via tree decoration

Phylogenetic networks provide a more general description of evolutionary relationships than rooted phylogenetic trees. One way to produce a phylogenetic network is to randomly place $k$ arcs between the edges of a rooted binary phylogenetic tree with $n$ leaves. The resulting directed graph may fail to be a phylogenetic network, and even when it is (and thereby a `tree-based' network), it may fail to be a tree-child or normal network. In this paper, we first show that if $k$ is fixed, the proportion of arc placements that result in a normal network tends to 1 as $n$ grows. From this result, the asymptotic enumeration of normal networks becomes straightforward and provides a transparent meaning to the combinatorial terms that arise. Moreover, the approach extends to allow $k$ to grow with $n$ (at the rate $o(n^\frac{1}{3})$), which was not handled in earlier work. We also investigate a subclass of normal networks of particular relevance in biology (hybridization networks) and establish that the same asymptotic results apply.

arXiv:2412.00948

Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages

Evaluations of Large Language Models (LLMs) on knowledge-intensive tasks and factual accuracy often focus on high-resource languages primarily because datasets for low-resource languages (LRLs) are scarce. In this paper, we present Uhura -- a new benchmark that focuses on two tasks in six typologically-diverse African languages, created via human translation of existing English benchmarks. The first dataset, Uhura-ARC-Easy, is composed of multiple-choice science questions. The second, Uhura-TruthfulQA, is a safety benchmark testing the truthfulness of models on topics including health, law, finance, and politics. We highlight the challenges creating benchmarks with highly technical content for LRLs and outline mitigation strategies. Our evaluation reveals a significant performance gap between proprietary models such as GPT-4o and o1-preview, and Claude models, and open-source models like Meta's LLaMA and Google's Gemma. Additionally, all models perform better in English than in African languages. These results indicate that LMs struggle with answering scientific questions and are more prone to generating false claims in low-resource African languages. Our findings underscore the necessity for continuous improvement of multilingual LM capabilities in LRL settings to ensure safe and reliable use in real-world contexts. We open-source the Uhura Benchmark and Uhura Platform to foster further research and development in NLP for LRLs.

arXiv:2412.02595

Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset

Recent English Common Crawl datasets like FineWeb-Edu and DCLM achieved significant benchmark gains via aggressive model-based filtering, but at the cost of removing 90% of data. This limits their suitability for long token horizon training, such as 15T tokens for Llama 3.1. In this paper, we show how to achieve better trade-offs between accuracy and data quantity by a combination of classifier ensembling, synthetic data rephrasing, and reduced reliance on heuristic filters. When training 8B parameter models for 1T tokens, using a high-quality subset of our data improves MMLU by 5.6 over DCLM, demonstrating the efficacy of our methods for boosting accuracies over a relatively short token horizon. Furthermore, our full 6.3T token dataset matches DCLM on MMLU, but contains four times more unique real tokens than DCLM. This unlocks state-of-the-art training over a long token horizon: an 8B parameter model trained for 15T tokens, of which 7.2T came from our dataset, is better than the Llama 3.1 8B model: +5 on MMLU, +3.1 on ARC-Challenge, and +0.5 on average across ten diverse tasks. The dataset is available at https://data.commoncrawl.org/contrib/Nemotron/Nemotron-CC/index.html

arXiv:2411.17708

Towards Efficient Neurally-Guided Program Induction for ARC-AGI

ARC-AGI is an open-world problem domain in which the ability to generalize out-of-distribution is a crucial quality. Under the program induction paradigm, we present a series of experiments that reveal the efficiency and generalization characteristics of various neurally-guided program induction approaches. The three paradigms we consider are Learning the grid space, Learning the program space, and Learning the transform space. We implement and experiment thoroughly on the first two, and retain the second one for ARC-AGI submission. After identifying the strengths and weaknesses of both of these approaches, we suggest the third as a potential solution, and run preliminary experiments.

arXiv:2411.18158

Abductive Symbolic Solver on Abstraction and Reasoning Corpus

This paper addresses the challenge of enhancing artificial intelligence reasoning capabilities, focusing on logicality within the Abstraction and Reasoning Corpus (ARC). Humans solve such visual reasoning tasks based on their observations and hypotheses, and they can explain their solutions with a proper reason. However, many previous approaches focused only on the grid transition and it is not enough for AI to provide reasonable and human-like solutions. By considering the human process of solving visual reasoning tasks, we have concluded that the thinking process is likely the abductive reasoning process. Thus, we propose a novel framework that symbolically represents the observed data into a knowledge graph and extracts core knowledge that can be used for solution generation. This information limits the solution search space and helps provide a reasonable mid-process. Our approach holds promise for improving AI performance on ARC tasks by effectively narrowing the solution space and providing logical solutions grounded in core knowledge extraction.

arXiv:2411.17270

An Attempt to Develop a Neural Parser based on Simplified Head-Driven Phrase Structure Grammar on Vietnamese

In this paper, we aimed to develop a neural parser for Vietnamese based on simplified Head-Driven Phrase Structure Grammar (HPSG). The existing corpora, VietTreebank and VnDT, had around 15% of constituency and dependency tree pairs that did not adhere to simplified HPSG rules. To attempt to address the issue of the corpora not adhering to simplified HPSG rules, we randomly permuted samples from the training and development sets to make them compliant with simplified HPSG. We then modified the first simplified HPSG Neural Parser for the Penn Treebank by replacing it with the PhoBERT or XLM-RoBERTa models, which can encode Vietnamese texts. We conducted experiments on our modified VietTreebank and VnDT corpora. Our extensive experiments showed that the simplified HPSG Neural Parser achieved a new state-of-the-art F-score of 82% for constituency parsing when using the same predicted part-of-speech (POS) tags as the self-attentive constituency parser. Additionally, it outperformed previous studies in dependency parsing with a higher Unlabeled Attachment Score (UAS). However, our parser obtained lower Labeled Attachment Score (LAS) scores likely due to our focus on arc permutation without changing the original labels, as we did not consult with a linguistic expert. Lastly, the research findings of this paper suggest that simplified HPSG should be given more attention to linguistic expert when developing treebanks for Vietnamese natural language processing.

arXiv:2411.14346

Lower Dimensional Spherical Representation of Medium Voltage Load Profiles for Visualization, Outlier Detection, and Generative Modelling

This paper presents the spherical lower dimensional representation for daily medium voltage load profiles, based on principal component analysis. The objective is to unify and simplify the tasks for (i) clustering visualisation, (ii) outlier detection and (iii) generative profile modelling under one concept. The lower dimensional projection of standardised load profiles unveils a latent distribution in a three-dimensional sphere. This spherical structure allows us to detect outliers by fitting probability distribution models in the spherical coordinate system, identifying measurements that deviate from the spherical shape. The same latent distribution exhibits an arc shape, suggesting an underlying order among load profiles. We develop a principal curve technique to uncover this order based on similarity, offering new advantages over conventional clustering techniques. This finding reveals that energy consumption in a wide region can be seen as a continuously changing process. Furthermore, we combined the principal curve with a von Mises-Fisher distribution to create a model capable of generating profiles with continuous mixtures between clusters. The presence of the spherical distribution is validated with data from four municipalities in the Netherlands. The uncovered spherical structure implies the possibility of employing new mathematical tools from directional statistics and differential geometry for load profile modelling.

arXiv:2411.11206공식 코드 · Papers with Code

Capturing Sparks of Abstraction for the ARC Challenge

Excellent progress has been made recently in solving ARC Challenge problems. However, it seems that new techniques may be required to push beyond 60% accuracy. Even commercial Large Language Models (LLMs) struggle to 'understand' many of the problems (when given the input and output grids), which makes discovering solutions by LLM-lead program search somewhat futile. In this work, LLM 'understanding' is attempted from a stronger starting position : An LLM is given complete solutions to tasks in code, and then asked to explain how the task is being solved at various levels of abstraction. Specifically, the LLM was given code solutions implemented in arc-dsl-llm (an LLM-legible version of Hodel's arc-dsl to obtain: (a) commented code; (b) code refactored into reusable functional chunks; (c) problem solution steps; and (d) high-level problem-solving tactics. We demonstrate that 'Sparks of Abstraction' can be extracted from the LLM output - in a form that could be used in downstream tasks with Local LLMs eligible to enter the ARC Prize. Both the arc-dsl-llm DSL framework (with the re-engineered solutions) and the Gemini LLM-generated data (along with the generation code) are made Open Source.