English
Related papers

Related papers: Typologically Informed Parameter Aggregation

200 papers

Extending Large Language Models (LLMs) to advanced applications requires reliable structured output generation. Existing methods which often rely on rigid JSON schemas, can lead to unreliable outputs, diminished reasoning capabilities, and…

Computation and Language · Computer Science 2024-10-25 Chandra Irugalbandara

Embedding models are crucial to modern NLP. However, the creation of the most effective models relies on carefully constructed supervised finetuning data. For high resource languages, such as English, such datasets are readily available.…

Computation and Language · Computer Science 2026-03-19 Merve Basoz , Andrew Horne , Mattia Opper

We introduce Adapters, an open-source library that unifies parameter-efficient and modular transfer learning in large language models. By integrating 10 diverse adapter methods into a unified interface, Adapters offers ease of use and…

Data selection is a key component of efficient instruction tuning for large language models, as recent work has shown that data quality often matters more than data quantity. Accordingly, prior studies have introduced various…

Machine Learning · Computer Science 2026-05-12 Jingze Song , Zihao Chen , Wenqing Chen , Zibin Zheng

Multimodal pretraining is effective for building general-purpose representations, but in many practical deployments, only one modality is heavily used during downstream fine-tuning. Standard pretraining strategies treat all modalities…

Machine Learning · Computer Science 2026-01-30 Atik Faysal , Mohammad Rostami , Reihaneh Gh. Roshan , Nikhil Muralidhar , Huaxia Wang

Cross-lingual adaptation with multilingual pre-trained language models (mPTLMs) mainly consists of two lines of works: zero-shot approach and translation-based approach, which have been studied extensively on the sequence-level tasks. We…

Computation and Language · Computer Science 2021-06-23 Xin Li , Lidong Bing , Wenxuan Zhang , Zheng Li , Wai Lam

The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 Cheng Cheng , Lin Song , Ruoyi Xue , Hang Wang , Hongbin Sun , Yixiao Ge , Ying Shan

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…

Computation and Language · Computer Science 2021-12-21 Wenxin Hou , Han Zhu , Yidong Wang , Jindong Wang , Tao Qin , Renjun Xu , Takahiro Shinozaki

In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm. We find that pre-trained speech models optimally encode…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-14 Travis M. Bartley , Fei Jia , Krishna C. Puvvada , Samuel Kriman , Boris Ginsburg

Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Jiazuo Yu , Yunzhi Zhuge , Lu Zhang , Ping Hu , Dong Wang , Huchuan Lu , You He

While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when target language…

Computation and Language · Computer Science 2021-09-10 Massimo Nicosia , Zhongdi Qu , Yasemin Altun

Data augmentation by mixing samples, such as Mixup, has widely been used typically for classification tasks. However, this strategy is not always effective due to the gap between augmented samples for training and original samples for…

Machine Learning · Computer Science 2019-06-21 Takuya Shimada , Shoichiro Yamaguchi , Kohei Hayashi , Sosuke Kobayashi

Model-agnostic interpretation techniques allow us to explain the behavior of any predictive model. Due to different notations and terminology, it is difficult to see how they are related. A unified view on these methods has been missing. We…

Machine Learning · Computer Science 2020-04-01 Christian A. Scholbeck , Christoph Molnar , Christian Heumann , Bernd Bischl , Giuseppe Casalicchio

Recent advancements in retrieval-augmented generation (RAG) have enhanced large language models in question answering by integrating external knowledge. However, challenges persist in achieving global understanding and aligning responses…

Computation and Language · Computer Science 2025-06-24 Quanwei Tang , Sophia Yat Mei Lee , Junshuang Wu , Dong Zhang , Shoushan Li , Erik Cambria , Guodong Zhou

For the speaker-controlled spoken language identification task proposed in the TidyLang Challenge 2026, this paper proposes a language identification method based on pre-trained models and margin-based losses. The proposed method adopts a…

Sound · Computer Science 2026-05-05 Zhihua Fang , Liang He , Weiwu Jiang

Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a…

Computation and Language · Computer Science 2021-06-08 Ruidan He , Linlin Liu , Hai Ye , Qingyu Tan , Bosheng Ding , Liying Cheng , Jia-Wei Low , Lidong Bing , Luo Si

Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously correlated (e.g., "grassy background" and "cows"). Existing…

We propose THELMA (Task Based Holistic Evaluation of Large Language Model Applications), a reference free framework for RAG (Retrieval Augmented generation) based question answering (QA) applications. THELMA consist of six interdependent…

To efficiently execute dynamically typed languages, many language implementations have adopted a two-tier architecture. The first tier aims for low-latency startup times and collects dynamic profiles, such as the dynamic types of variables.…

Programming Languages · Computer Science 2020-10-07 Olivier Flückiger , Andreas Wälchli , Sebastián Krynski , Jan Vitek

Large Language Models (LLMs) have shown promising results on NLP tasks, however, their performance on tabular data still needs research attention, because Table Question-Answering (TQA) requires precise cell retrieval and multi-step…

Information Retrieval · Computer Science 2026-05-21 Amritansh Maurya , Navjot Singh , Mohammed Javed , Omar Moured
‹ Prev 1 3 4 5 6 7 10 Next ›