Align, Generate, Learn: A Novel Closed-Loop Framework for Cross-Lingual In-Context Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
In-Context LearningSimilar Papers 제목 키워드 기반
Align2Act: Instruction-Tuned Models for Human-Aligned Autonomous Driving
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 PlanningLearning Dynamics of RNNs in Closed-Loop Environments
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
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 DrivingCRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
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 DrivingFrom Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving
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