Copertina

Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Qin, Tian, Chen, Yuhan, Wang, Zhiwei, Xu, Zhi-Qin John
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
di: Wang, Zhiwei, et al.
Pubblicazione: (2024)

Identity Bridge: Enabling Implicit Reasoning via Shared Latent Memory
di: Lin, Pengxiao, et al.
Pubblicazione: (2025)

Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation
di: Liu, Yuhan, et al.
Pubblicazione: (2025)

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
di: Yang, Tong, et al.
Pubblicazione: (2025)

M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought
di: Chen, Qiguang, et al.
Pubblicazione: (2024)

Neuro-Symbolic Rule Lists
di: Xu, Sascha, et al.
Pubblicazione: (2024)

Structuring Reasoning for Complex Rules Beyond Flat Representations
di: Yang, Zhihao, et al.
Pubblicazione: (2025)

Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge
di: Feng, Yiyang, et al.
Pubblicazione: (2026)

Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL
di: Liu, Che, et al.
Pubblicazione: (2025)

New Rules for Causal Identification with Background Knowledge
di: Wang, Tian-Zuo, et al.
Pubblicazione: (2024)

SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection
di: Chen, Qin, et al.
Pubblicazione: (2025)

To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning
di: Lazić, Nevena, et al.
Pubblicazione: (2026)

MPPFND: A Dataset and Analysis of Detecting Fake News with Multi-Platform Propagation
di: Zhao, Congyuan, et al.
Pubblicazione: (2025)

DialogueReason: Rule-Based RL Sparks Dialogue Reasoning in LLMs
di: Shu, Yubo, et al.
Pubblicazione: (2025)

Optimal Pattern Detection Tree for Symbolic Rule-Based Classification
di: Hong, Young-Chae, et al.
Pubblicazione: (2026)

Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning
di: Wang, Chaojie, et al.
Pubblicazione: (2024)

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules
di: Wu, Di, et al.
Pubblicazione: (2026)

NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
di: Qin, Xiaohan, et al.
Pubblicazione: (2025)

Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks
di: Deng, Wentao, et al.
Pubblicazione: (2025)

RuleSafe-VL: Evaluating Rule-Conditioned Decision Reasoning in Vision-Language Content Moderation
di: Lu, Zhifeng, et al.
Pubblicazione: (2026)

Neuro-Symbolic Data Generation for Math Reasoning
di: Li, Zenan, et al.
Pubblicazione: (2024)

Entropy-based Exploration Conduction for Multi-step Reasoning
di: Zhang, Jinghan, et al.
Pubblicazione: (2025)

ReasoningV: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning Model
di: Qin, Haiyan, et al.
Pubblicazione: (2025)

Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions
di: Daniele, Alessandro, et al.
Pubblicazione: (2022)

MuAP: Multi-step Adaptive Prompt Learning for Vision-Language Model with Missing Modality
di: Dai, Ruiting, et al.
Pubblicazione: (2024)

Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs
di: Chen, Jack, et al.
Pubblicazione: (2025)

LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition
di: Kheirandish, Alireza, et al.
Pubblicazione: (2024)

MMSR: Symbolic Regression is a Multi-Modal Information Fusion Task
di: Li, Yanjie, et al.
Pubblicazione: (2024)

Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection
di: Hu, Wen-Chao, et al.
Pubblicazione: (2024)

Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning
di: Zhang, Zheng
Pubblicazione: (2025)

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
di: Mirzadeh, Iman, et al.
Pubblicazione: (2024)

Modeling Endogenous Logic: Causal Neuro-Symbolic Reasoning Model for Explainable Multi-Behavior Recommendation
di: Chen, Yuzhe, et al.
Pubblicazione: (2026)

Brainstorming Brings Power to Large Language Models of Knowledge Reasoning
di: Qin, Zining, et al.
Pubblicazione: (2024)

Research on Flight Accidents Prediction based Back Propagation Neural Network
di: Liu, Haoxing, et al.
Pubblicazione: (2024)

Symbolic Rule Extraction from Attention-Guided Sparse Representations in Vision Transformers
di: Padalkar, Parth, et al.
Pubblicazione: (2025)

GraphReAct: Reasoning and Acting for Multi-step Graph Inference
di: Yu, Xingtong, et al.
Pubblicazione: (2026)

Debiasing Kernel-Based Generative Models
di: Qin, Tian, et al.
Pubblicazione: (2025)

Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

DABstep: Data Agent Benchmark for Multi-step Reasoning
di: Egg, Alex, et al.
Pubblicazione: (2025)