paper-with-me

Papers

DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules

2023-05-22 · Yanchen Liu, William Held, Diyi Yang

Existing large language models (LLMs) that mainly focus on Standard American English (SAE) often lead to significantly worse performance when being applied to other English dialects. While existing mitigations tackle discrepancies for individual target dialects, they assume access to high-accuracy dialect identification systems. The boundaries between dialects are inherently flexible, making it difficult to categorize language into discrete predefined categories. In this paper, we propose DADA (Dialect Adaptation via Dynamic Aggregation), a modular approach to imbue SAE-trained models with multi-dialectal robustness by composing adapters which handle specific linguistic features. The compositional architecture of DADA allows for both targeted adaptation to specific dialect variants and simultaneous adaptation to various dialects. We show that DADA is effective for both single task and instruction finetuned language models, offering an extensible and interpretable framework for adapting existing LLMs to different English dialects.

📄 PDF Abstract BibTeX arXiv:2305.13406

Code (1)

salt-nlp/dada 공식 구현 jax

Tasks

Dialect Identification

Methods 이 논문이 사용한 방법론

American 설명 없음

Similar Papers 제목 키워드 기반

DADA: Dual Averaging with Distance Adaptation

2025-01-17 · Mohammad Moshtaghifar, Anton Rodomanov, Daniil Vankov, Sebastian Stich

We present a novel universal gradient method for solving convex optimization problems. Our algorithm -- Dual Averaging with Distance Adaptation (DADA) -- is based on the classical scheme of dual averaging and dynamically…

MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning

2024-05-05 · Wenqi Shi, ran Xu, Yuchen Zhuang, Yue Yu 외

Despite their improved capabilities in generation and reasoning, adapting large language models (LLMs) to the biomedical domain remains challenging due to their immense size and corporate privacy. In this work, we propos…

Privacy PreservingTest-time Adaptation

Optimizing Retrieval-Augmented Generation (RAG) for Colloquial Cantonese: A LoRA-Based Systematic Review

2025-08-12 · David Santandreu Calonge, Linda Smail arxiv

This review examines recent advances in Parameter-Efficient Fine-Tuning (PEFT), with a focus on Low-Rank Adaptation (LoRA), to optimize Retrieval-Augmented Generation (RAG) systems like Qwen3, DeepSeek, and Kimi. These s…

parameter-efficient fine-tuningSynthetic Data GenerationComputational EfficiencyDomain Adaptation

Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning

2026-02-24 · Zhangjie Xia, Yu Yang, Pan Xu arxiv

Off-dynamics offline reinforcement learning (RL) aims to learn a policy for a target domain using limited target data and abundant source data collected under different transition dynamics. Existing methods typically add…

Reinforcement LearningDomain AdaptationOffline RL

Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

2022-05-07 · CVPR 2022 1 · Xiaoqian Xu, Pengxu Wei, Weikai Chen, Mingzhi Mao 외

Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super-resolution (SR) models trained on image…

Domain AdaptationImage Super-ResolutionSuper-ResolutionUnsupervised Domain Adaptation