paper-with-me

홈 › Papers

Align, Generate, Learn: A Novel Closed-Loop Framework for Cross-Lingual In-Context Learning

2024-12-12 · Mateo Alejandro Rojas, Rafael Carranza

Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on external retrievers or task-specific fine-tuning, limiting their scalability and generalizability. In this paper, we propose a novel self-supervised framework that harnesses the generative capabilities of LLMs to internally select and utilize task-relevant examples. Our method introduces two key objectives: a retrieval-generation alignment loss to optimize the quality of selected examples and a semantic coherence loss to ensure cross-lingual consistency. Through extensive experiments on multilingual benchmarks, our approach achieves state-of-the-art performance, significantly outperforming existing baselines. Further analysis highlights its robustness across diverse language families and its ability to generalize to unseen tasks. Human evaluations confirm the superior fluency, relevance, and semantic correctness of outputs generated by our method. This work provides a scalable, effective, and generalizable solution for cross-lingual in-context learning.

📄 PDF Abstract BibTeX arXiv:2412.08955

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context Learning

Similar Papers 제목 키워드 기반

Align2Act: Instruction-Tuned Models for Human-Aligned Autonomous Driving

2025-10-12 · Kanishkha Jaisankar, Sunidhi Tandel arxiv

Motion planning in complex scenarios is a core challenge in autonomous driving. Conventional methods apply predefined rules or learn from driving data to generate trajectories, while recent approaches leverage large lang…

Autonomous DrivingMotion Planning

Learning Dynamics of RNNs in Closed-Loop Environments

2025-05-19 · Yoav Ger, Omri Barak

Recurrent neural networks (RNNs) trained on neuroscience-inspired tasks offer powerful models of brain computation. However, typical training paradigms rely on open-loop, supervised settings, whereas real-world learning …

TakeAD: Preference-based Post-optimization for End-to-end Autonomous Driving with Expert Takeover Data

2025-12-19 · Deqing Liu, Yinfeng Gao, Deheng Qian, Qichao Zhang 외 arxiv

Existing end-to-end autonomous driving methods typically rely on imitation learning (IL) but face a key challenge: the misalignment between open-loop training and closed-loop deployment. This misalignment often triggers …

Autonomous Driving

CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies

2026-05-06 · Keyu Chen, Nanfei Ye, Yida Wang, Wenchao Sun 외 arxiv

Open-loop imitation learning has advanced modern autonomous driving policy architectures, but closed-loop deployment remains vulnerable to policy-induced distribution shift. Existing post-training paradigms exhibit funda…

Autonomous Driving

From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving

2026-06-12 · Yuewen Mei, Tong Nie, Jie Sun, Haotian Shi 외 arxiv

Closed-loop adversarial training improves autonomous driving safety by exposing policies to rare safety-critical scenarios. Standard pipelines first generate adversarial scenarios and then sample them for policy optimiza…

Autonomous Driving