paper-with-me

홈 › Papers

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

2025-02-17 · Zhiwen Ruan, Yixia Li, He Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang, Yun Chen, Guanhua Chen

Despite being pretrained on multilingual corpora, large language models (LLMs) exhibit suboptimal performance on low-resource languages. Recent approaches have leveraged multilingual encoders alongside LLMs by introducing trainable parameters connecting the two models. However, these methods typically focus on the encoder's output, overlooking valuable information from other layers. We propose \aname (\mname), a framework that integrates representations from all encoder layers, coupled with the \attaname mechanism to enable layer-wise interaction between the LLM and the multilingual encoder. Extensive experiments on multilingual reasoning tasks, along with analyses of learned representations, show that our approach consistently outperforms existing baselines.

📄 PDF Abstract BibTeX arXiv:2502.11405

Code (1)

sustech-nlp/layalign 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

The Multilingual Mind : A Survey of Multilingual Reasoning in Language Models

2025-02-13 · Akash Ghosh, Debayan Datta, Sriparna Saha, Chirag Agarwal

While reasoning and multilingual capabilities in Language Models (LMs) have achieved remarkable progress in recent years, their integration into a unified paradigm, multilingual reasoning, is at a nascent stage. Multilin…

Logical ReasoningSurvey

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance

2026-05-21 · Yuchun Fan, Bei Li, Peiguang Li, Yilin Wang 외 arxiv

Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundam…

Reinforcement Learning

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment

2025-01-07 · Yuchun Fan, Yongyu Mu, Yilin Wang, Lei Huang 외

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-st…

Representation Learning

Cross-Lingual Consistency: A Novel Inference Framework for Advancing Reasoning in Large Language Models

2025-04-02 · Zhiwei Yu, Tuo Li, Changhong Wang, Hui Chen 외

Chain-of-thought (CoT) has emerged as a critical mechanism for enhancing reasoning capabilities in large language models (LLMs), with self-consistency demonstrating notable promise in boosting performance. However, inher…

Math

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Tasks

2024-12-17 · Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang 외

Large language models (LLMs) have demonstrated impressive multilingual understanding and reasoning capabilities, driven by extensive pre-training multilingual corpora and fine-tuning instruction data. However, a performa…

Math