DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENs

• URL: http://arxiv.org/abs/2604.17584v1
• Date: Sun, 19 Apr 2026 19:15:32 GMT
• Title: DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENs
• Abstract summary: We propose the Dual-Inference Rule-Contrastive Reasoning (DIRCR) model.<n>Its core component, the Dual-Inference Reasoning Module, combines a local path for row-wise analogical reasoning and a global path for holistic inference.<n> Experimental results on three RAVEN datasets demonstrate that DIRCR significantly enhances robustness and generalization.
• Score: 53.41360935117212
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Abstract visual reasoning remains challenging as existing methods often prioritize either global context or local row-wise relations, failing to integrate both, and lack intermediate feature constraints, leading to incomplete rule capture and entangled representations. To address these issues, we propose the Dual-Inference Rule-Contrastive Reasoning (DIRCR) model. Its core component, the Dual-Inference Reasoning Module, combines a local path for row-wise analogical reasoning and a global path for holistic inference, integrated via a gated attention mechanism. Additionally, a Rule-Contrastive Learning Module introduces pseudo-labels to construct positive and negative rule samples, applying contrastive learning to enhance feature separability and promote abstract, transferable rule learning. Experimental results on three RAVEN datasets demonstrate that DIRCR significantly enhances reasoning robustness and generalization. Codes are available at https://github.com/csZack-Zhang/DIRCR.

Related papers

• R-C2: Cycle-Consistent Reinforcement Learning Improves Multimodal Reasoning [20.899863841051662]
  Cross-modal inconsistency provides a rich and natural signal for learning.<n>We introduce RC2, a reinforcement learning framework that resolves internal conflicts by enforcing cross-modal cycle consistency.<n>Our results suggest that advanced reasoning emerges not only from scaling data, but also from enforcing a structurally consistent understanding of the world.
  arXiv  Detail & Related papers  (2026-03-26T17:58:04Z)
• Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping [51.33479921152361]
  Large language models (LLMs) often exhibit flawed reasoning ability that undermines reliability.<n>Existing approaches to improving reasoning typically treat it as a general and monolithic skill, applying broad training which is inefficient and unable to target specific reasoning errors.<n>We introduce Reasoning Editing, a paradigm for selectively modifying specific reasoning patterns in LLMs while preserving other reasoning pathways.
  arXiv  Detail & Related papers  (2026-03-06T22:51:39Z)
• Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning [96.01617809845396]
  Ground-R1 is a reinforcement learning framework that enables grounded visual reasoning without requiring explicit evidence or rationale annotations.<n>Ground-R1 achieves superior performance and exhibits emergent cognitive behaviors such as uncertainty awareness, spatial perception, and iterative refinement.
  arXiv  Detail & Related papers  (2025-05-26T17:51:47Z)
• Reinforced Latent Reasoning for LLM-based Recommendation [92.56166822197919]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks.<n>Existing methods typically rely on fine-tuning with explicit chain-of-thought (CoT) data.<n>In this work, we explore an alternative approach that shifts from explicit CoT reasoning to compact, information-dense latent reasoning.
  arXiv  Detail & Related papers  (2025-05-25T11:03:45Z)
• Deep Regression Representation Learning with Topology [57.203857643599875]
  We study how the effectiveness of a regression representation is influenced by its topology. We introduce PH-Reg, a regularizer that matches the intrinsic dimension and topology of the feature space with the target space. Experiments on synthetic and real-world regression tasks demonstrate the benefits of PH-Reg.
  arXiv  Detail & Related papers  (2024-04-22T06:28:41Z)
• Vision-and-Language Navigation via Causal Learning [13.221880074458227]
  Cross-modal causal transformer (GOAT) is a pioneering solution rooted in the paradigm of causal inference. BACL and FACL modules promote unbiased learning by comprehensively mitigating potential spurious correlations. To capture global confounder features, we propose a cross-modal feature pooling module supervised by contrastive learning.
  arXiv  Detail & Related papers  (2024-04-16T02:40:35Z)
• Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems [54.26307134687171]
  Raven's Progressive Matrix (RPM) is a classic test to realize such ability in machine intelligence by selecting from candidates. Recent studies suggest that solving RPM in an answer-generation way boosts a more in-depth understanding of rules. We propose a deep latent variable model for Concept-changing Rule ABstraction (CRAB) by learning interpretable concepts and parsing concept-changing rules in the latent space.
  arXiv  Detail & Related papers  (2023-07-15T07:16:38Z)
• Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning [8.344644072431898]
  We propose a graph convolutional network (GCN)-based approach for interpretable inductive reasoning with relational path contrast. RPC-IR firstly extracts relational paths between two entities and learns representations of them, and then innovatively introduces a contrastive strategy.
  arXiv  Detail & Related papers  (2021-10-17T12:39:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.