Copertina

LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ruan, Zhiwen, Li, Yixia, Zhu, He, Wang, Longyue, Luo, Weihua, Zhang, Kaifu, Chen, Yun, Chen, Guanhua
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
di: Ruan, Zhiwen, et al.
Pubblicazione: (2025)

G2: Guided Generation for Enhanced Output Diversity in LLMs
di: Ruan, Zhiwen, et al.
Pubblicazione: (2025)

Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models
di: Zhu, Chenyu, et al.
Pubblicazione: (2025)

New Trends for Modern Machine Translation with Large Reasoning Models
di: Liu, Sinuo, et al.
Pubblicazione: (2025)

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
di: Ruan, Zhiwen, et al.
Pubblicazione: (2026)

SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
di: Li, Yixia, et al.
Pubblicazione: (2024)

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks
di: Ruan, Zhiwen, et al.
Pubblicazione: (2025)

Challenging Multilingual LLMs: A New Taxonomy and Benchmark for Unraveling Hallucination in Translation
di: Wu, Xinwei, et al.
Pubblicazione: (2025)

A State-Transition Framework for Efficient LLM Reasoning
di: Zhang, Liang, et al.
Pubblicazione: (2026)

The Affective Bridge: Preserving Speech Representations while Enhancing Deepfake Detection vian emotional Constraints
di: Li, Yupei, et al.
Pubblicazione: (2025)

TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation
di: Zhu, He, et al.
Pubblicazione: (2025)

CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision
di: Wang, Pengcheng, et al.
Pubblicazione: (2026)

MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
di: Wang, Hanqing, et al.
Pubblicazione: (2024)

PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning
di: Xue, Tianci, et al.
Pubblicazione: (2023)

ComfyUI-R1: Exploring Reasoning Models for Workflow Generation
di: Xu, Zhenran, et al.
Pubblicazione: (2025)

The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks
di: Wu, Minghao, et al.
Pubblicazione: (2025)

Ovis: Structural Embedding Alignment for Multimodal Large Language Model
di: Lu, Shiyin, et al.
Pubblicazione: (2024)

Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
di: Wang, Xintong, et al.
Pubblicazione: (2025)

Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions
di: Hou, Yutao, et al.
Pubblicazione: (2024)

Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
di: Zhao, Yu, et al.
Pubblicazione: (2024)

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
di: Wang, Tianyi, et al.
Pubblicazione: (2026)

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment
di: Bu, Mengyu, et al.
Pubblicazione: (2025)

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
di: Li, Yuanyang, et al.
Pubblicazione: (2026)

(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts
di: Wu, Minghao, et al.
Pubblicazione: (2024)

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models
di: Zeng, Bo, et al.
Pubblicazione: (2025)

Marco-ASR: A Principled and Metric-Driven Framework for Fine-Tuning Large-Scale ASR Models for Domain Adaptation
di: Ni, Xuanfan, et al.
Pubblicazione: (2025)

HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Application
di: Yang, Yiqian, et al.
Pubblicazione: (2025)

CM-Align: Consistency-based Multilingual Alignment for Large Language Models
di: Zhang, Xue, et al.
Pubblicazione: (2025)

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
di: Fu, Minghao, et al.
Pubblicazione: (2025)

ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs
di: Yang, Yan, et al.
Pubblicazione: (2025)

DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking
di: Lan, Tian, et al.
Pubblicazione: (2025)

Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization
di: Wang, Yibo, et al.
Pubblicazione: (2026)

Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms
di: Xiao, Zeguan, et al.
Pubblicazione: (2025)

SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models
di: Wang, Yibo, et al.
Pubblicazione: (2025)

Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning
di: Zhao, Chunxu, et al.
Pubblicazione: (2026)

MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
di: She, Shuaijie, et al.
Pubblicazione: (2024)

FactAlign: Long-form Factuality Alignment of Large Language Models
di: Huang, Chao-Wei, et al.
Pubblicazione: (2024)

Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification
di: Wang, Tianyi, et al.
Pubblicazione: (2026)

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
di: Sun, Shuqiao, et al.
Pubblicazione: (2024)

MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models
di: Wang, Xinming, et al.
Pubblicazione: (2025)