Cover Image

Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deng, Yunlong, Sun, Boyang, Li, Yan, Kong, Lingjing, Tang, Zeyu, Zhang, Kun, Chen, Guangyi
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Self-Refinement of Vision-Language Models with Triangular Consistency
by: Deng, Yunlong, et al.
Published: (2025)

Towards Understanding Extrapolation: a Causal Lens
by: Kong, Lingjing, et al.
Published: (2025)

Reflection-Window Decoding: Text Generation with Selective Refinement
by: Tang, Zeyu, et al.
Published: (2025)

Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards
by: Xie, Shaoan, et al.
Published: (2025)

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
by: Xie, Shaoan, et al.
Published: (2025)

Learning Discrete Concepts in Latent Hierarchical Models
by: Kong, Lingjing, et al.
Published: (2024)

Unsupervised Synthetic Image Attribution: Alignment and Disentanglement
by: Liu, Zongfang, et al.
Published: (2026)

Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models
by: Li, Loka, et al.
Published: (2024)

First Try Matters: Revisiting the Role of Reflection in Reasoning Models
by: Kang, Liwei, et al.
Published: (2025)

World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
by: Liu, Yuejiang, et al.
Published: (2026)

Continual Learning of Nonlinear Independent Representations
by: Sun, Boyang, et al.
Published: (2024)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
by: Song, Xiangchen, et al.
Published: (2025)

Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation
by: Li, Yuting, et al.
Published: (2025)

Adjusting Pretrained Backbones for Performativity
by: Demirel, Berker, et al.
Published: (2024)

LLM-Driven Self-Refinement for Embodied Drone Task Planning
by: Zhang, Deyu, et al.
Published: (2025)

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
by: Jiao, Difan, et al.
Published: (2026)

Federated Causal Discovery from Heterogeneous Data
by: Li, Loka, et al.
Published: (2024)

Haibu Mathematical-Medical Intelligent Agent:Enhancing Large Language Model Reliability in Medical Tasks via Verifiable Reasoning Chains
by: Zhang, Yilun, et al.
Published: (2025)

Revisiting Counterfactual Regression through the Lens of Gromov-Wasserstein Information Bottleneck
by: Yang, Hao, et al.
Published: (2024)

SSR: Socratic Self-Refine for Large Language Model Reasoning
by: Shi, Haizhou, et al.
Published: (2025)

Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications
by: Paul, Debdas, et al.
Published: (2026)

Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction
by: Zeng, Qinglin, et al.
Published: (2025)

Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
by: Pan, Zhiyu, et al.
Published: (2026)

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
by: Wang, Qibin, et al.
Published: (2025)

Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality
by: Kong, Lingjing, et al.
Published: (2025)

Causality for Large Language Models
by: Wu, Anpeng, et al.
Published: (2024)

Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained Reflection
by: Yang, Zongxian, et al.
Published: (2025)

MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning
by: Chen, Jinhao, et al.
Published: (2025)

Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective
by: Yan, Hanqi, et al.
Published: (2024)

HAIBU-ReMUD: Reasoning Multimodal Ultrasound Dataset and Model Bridging to General Specific Domains
by: Wang, Shijie, et al.
Published: (2025)

IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement
by: Shen, Yuanzhe, et al.
Published: (2025)

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
by: Xi, Zhiheng, et al.
Published: (2023)

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models
by: Liu, Kaiyuan, et al.
Published: (2025)

Fault-Tolerant Sandboxing for AI Coding Agents: A Transactional Approach to Safe Autonomous Execution
by: Yan, Boyang
Published: (2025)

Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning
by: Yu, Yahan, et al.
Published: (2026)

MMLU-Reason: Benchmarking Multi-Task Multi-modal Language Understanding and Reasoning
by: Tie, Guiyao, et al.
Published: (2025)

APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation
by: Chen, Kun, et al.
Published: (2026)

ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation
by: Zhou, Jingqi, et al.
Published: (2026)

SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
by: Liu, Liangxin, et al.
Published: (2024)

ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback
by: Yun, Taewon, et al.
Published: (2025)