paper-with-me

Papers

Abstract Reasoning via Logic-guided Generation

2021-07-22 · Sihyun Yu, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin

Abstract reasoning, i.e., inferring complicated patterns from given observations, is a central building block of artificial general intelligence. While humans find the answer by either eliminating wrong candidates or first constructing the answer, prior deep neural network (DNN)-based methods focus on the former discriminative approach. This paper aims to design a framework for the latter approach and bridge the gap between artificial and human intelligence. To this end, we propose logic-guided generation (LoGe), a novel generative DNN framework that reduces abstract reasoning as an optimization problem in propositional logic. LoGe is composed of three steps: extract propositional variables from images, reason the answer variables with a logic layer, and reconstruct the answer image from the variables. We demonstrate that LoGe outperforms the black box DNN frameworks for generative abstract reasoning under the RAVEN benchmark, i.e., reconstructing answers based on capturing correct rules of various attributes from observations.

📄 PDF Abstract BibTeX arXiv:2107.10493

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models

2026-01-29 · Rizky Ramadhana Putra, Raihan Sultan Pasha Basuki, Yutong Cheng, Peng Gao arxiv

Automated reasoning is critical in domains such as law and governance, where verifying claims against facts in documents requires both accuracy and interpretability. Recent work adopts structured reasoning pipelines that…

Code Generation

ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models

2025-02-13 · R. Kenny Jones, Paul Guerrero, Niloy J. Mitra, Daniel Ritchie

We present ShapeLib, the first method that leverages the priors of LLMs to design libraries of programmatic 3D shape abstractions. Our system accepts two forms of design intent: text descriptions of functions to include …

Synthetic Data Generation

Semantic-Aware Logical Reasoning via a Semiotic Framework

2025-09-29 · Yunyao Zhang, Xinglang Zhang, Junxi Sheng, Wenbing Li 외 arxiv

Logical reasoning is a fundamental capability of large language models. However, existing studies often overlook the interaction between logical complexity and semantic complexity, leading to systems that struggle with a…

Logical Reasoning

HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG

2026-02-24 · Yuqi Huang, Ning Liao, Kai Yang, Anning Hu 외 arxiv

Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmented Generation (RAG) mitigates these issue…

DELTA: Deliberative Multi-Agent Reasoning with Reinforcement Learning for Multimodal Psychological Counseling

2026-02-04 · Jiangnan Yang, Junjie Chen, Fei Wang, Yiqi Nie 외 arxiv

Psychological counseling is a fundamentally multimodal cognitive process in which clinicians integrate verbal content with visual and vocal cues to infer clients' mental states and respond empathically. However, most exi…

Reinforcement LearningMultimodal ReasoningResponse Generation