Buchumschlag

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Yang, Yuancheng, Yang, Lin, Wang, Xu, Tong, Chao, Yang, Haihua
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

MedMT-Bench: Can LLMs Memorize and Understand Long Multi-Turn Conversations in Medical Scenarios?
von: Yang, Lin, et al.
Veröffentlicht: (2026)

Stronger Models are NOT Stronger Teachers for Instruction Tuning
von: Xu, Zhangchen, et al.
Veröffentlicht: (2024)

Better Instruction-Following Through Minimum Bayes Risk
von: Wu, Ian, et al.
Veröffentlicht: (2024)

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training
von: Huang, Hui, et al.
Veröffentlicht: (2025)

Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models
von: Liu, Yuliang, et al.
Veröffentlicht: (2026)

Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants
von: Yang, Jiuding, et al.
Veröffentlicht: (2024)

Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Scaling Law for Language Models
von: Wang, Xinyi, et al.
Veröffentlicht: (2025)

Benchmarking Complex Instruction-Following with Multiple Constraints Composition
von: Wen, Bosi, et al.
Veröffentlicht: (2024)

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
von: Wang, Chenyang, et al.
Veröffentlicht: (2025)

Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information
von: Zhang, Zeyu, et al.
Veröffentlicht: (2025)

Constraint Back-translation Improves Complex Instruction Following of Large Language Models
von: Qi, Yunjia, et al.
Veröffentlicht: (2024)

Automatic Layout Planning for Visually-Rich Documents with Instruction-Following Models
von: Zhu, Wanrong, et al.
Veröffentlicht: (2024)

Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
von: Yang, Cehao, et al.
Veröffentlicht: (2025)

SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning
von: Zhao, Chenyang, et al.
Veröffentlicht: (2024)

LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
von: Kolasani, Sai, et al.
Veröffentlicht: (2025)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
von: Wen, Xumeng, et al.
Veröffentlicht: (2025)

Ada-Instruct: Adapting Instruction Generators for Complex Reasoning
von: Cui, Wanyun, et al.
Veröffentlicht: (2023)

Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
von: Ning, Xuefei, et al.
Veröffentlicht: (2024)

Reasoning Models Better Express Their Confidence
von: Yoon, Dongkeun, et al.
Veröffentlicht: (2025)

CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation
von: Li, Renhao, et al.
Veröffentlicht: (2024)

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
von: Fu, Tingchen, et al.
Veröffentlicht: (2025)

On the Multi-turn Instruction Following for Conversational Web Agents
von: Deng, Yang, et al.
Veröffentlicht: (2024)

System-2 Mathematical Reasoning via Enriched Instruction Tuning
von: Cai, Huanqia, et al.
Veröffentlicht: (2024)

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
von: Li, Ming, et al.
Veröffentlicht: (2025)

LIFEBench: Evaluating Length Instruction Following in Large Language Models
von: Zhang, Wei, et al.
Veröffentlicht: (2025)

Reverse Thinking Makes LLMs Stronger Reasoners
von: Chen, Justin Chih-Yao, et al.
Veröffentlicht: (2024)

Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models
von: Sun, Haoran, et al.
Veröffentlicht: (2024)

HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models
von: Hossain, Jawad, et al.
Veröffentlicht: (2026)

Countering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model Merging
von: Lyu, Mengxian, et al.
Veröffentlicht: (2026)

Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification
von: Sanyal, Soumya, et al.
Veröffentlicht: (2024)

Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning
von: Zhang, Xinlu, et al.
Veröffentlicht: (2024)

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs
von: Alrashed, Sultan
Veröffentlicht: (2024)

Can Language Models Follow Multiple Turns of Entangled Instructions?
von: Han, Chi, et al.
Veröffentlicht: (2025)

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models
von: Ye, Junjie, et al.
Veröffentlicht: (2025)

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
von: Lou, Renze, et al.
Veröffentlicht: (2023)

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
von: Peng, Hao, et al.
Veröffentlicht: (2025)

Timo: Towards Better Temporal Reasoning for Language Models
von: Su, Zhaochen, et al.
Veröffentlicht: (2024)

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
von: Ding, Deming, et al.
Veröffentlicht: (2026)

Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
von: Ji, Jiaming, et al.
Veröffentlicht: (2024)

Implicit Reasoning in Large Language Models: A Comprehensive Survey
von: Li, Jindong, et al.
Veröffentlicht: (2025)