Copertina

Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	He, Qianxi, He, Qianyu, Liang, Jiaqing, Xiao, Yanghua, Zhou, Weikang, Sun, Zeye, Yu, Fei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following
di: Zeng, Jie, et al.
Pubblicazione: (2025)

Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models
di: Ren, Qingyu, et al.
Pubblicazione: (2025)

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
di: Ren, Qingyu, et al.
Pubblicazione: (2025)

Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following
di: Ren, Qingyu, et al.
Pubblicazione: (2025)

From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models
di: He, Qianyu, et al.
Pubblicazione: (2024)

Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks
di: Huang, Yuncheng, et al.
Pubblicazione: (2024)

Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
di: Han, Jinyi, et al.
Pubblicazione: (2025)

Small Language Model Can Self-correct
di: Han, Haixia, et al.
Pubblicazione: (2024)

Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception
di: Huang, Yuncheng, et al.
Pubblicazione: (2023)

Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
di: Li, Yanda, et al.
Pubblicazione: (2024)

A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
di: Han, Jinyi, et al.
Pubblicazione: (2025)

SEIF: Self-Evolving Reinforcement Learning for Instruction Following
di: Ren, Qingyu, et al.
Pubblicazione: (2026)

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
di: Xia, Sirui, et al.
Pubblicazione: (2024)

What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty
di: Zhang, Bowei, et al.
Pubblicazione: (2025)

Skeletons Matter: Dynamic Data Augmentation for Text-to-Query
di: Ji, Yuchen, et al.
Pubblicazione: (2025)

QUILL: Quotation Generation Enhancement of Large Language Models
di: Xiao, Jin, et al.
Pubblicazione: (2024)

Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases
di: Huang, Wenhao, et al.
Pubblicazione: (2024)

ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context
di: Li, Victoria R., et al.
Pubblicazione: (2024)

ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base
di: Yuan, Siyu, et al.
Pubblicazione: (2023)

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
di: Dang, Quy-Anh, et al.
Pubblicazione: (2025)

Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)
di: Yu, Zony, et al.
Pubblicazione: (2025)

Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space
di: Verma, Gaurav, et al.
Pubblicazione: (2024)

Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't
di: Taguchi, Chihiro, et al.
Pubblicazione: (2024)

Can Large Language Models Understand Real-World Complex Instructions?
di: He, Qianyu, et al.
Pubblicazione: (2023)

Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge Graphs
di: Zhang, Yifei, et al.
Pubblicazione: (2024)

Premise Order Matters in Reasoning with Large Language Models
di: Chen, Xinyun, et al.
Pubblicazione: (2024)

LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models
di: Ren, Qingyu, et al.
Pubblicazione: (2026)

Bayesian Elicitation with LLMs: Model Size Helps, Extra "Reasoning" Doesn't Always
di: Hobor, Luka, et al.
Pubblicazione: (2026)

Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
di: Jiang, Zishang, et al.
Pubblicazione: (2025)

IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language
di: Chance, Christina, et al.
Pubblicazione: (2026)

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
di: Zhang, Haoxiang, et al.
Pubblicazione: (2026)

Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models
di: Zhang, Yikai, et al.
Pubblicazione: (2024)

Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models
di: Xie, Zikai
Pubblicazione: (2024)

Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
di: Liu, Ming
Pubblicazione: (2026)

One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
di: He, Di, et al.
Pubblicazione: (2026)

Do Large Language Models Truly Understand Cross-cultural Differences?
di: Guo, Shiwei, et al.
Pubblicazione: (2025)

Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
di: Du, Chengyu, et al.
Pubblicazione: (2024)

SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
di: Lin, Jiacheng, et al.
Pubblicazione: (2025)

Can Pre-trained Language Models Understand Chinese Humor?
di: Chen, Yuyan, et al.
Pubblicazione: (2024)

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
di: Wang, Ziqiao, et al.
Pubblicazione: (2025)