paper-with-me

Papers

Conditional Language Learning with Context

2024-06-04 · Xiao Zhang, Miao Li, Ji Wu

Language models can learn sophisticated language understanding skills from fitting raw text. They also unselectively learn useless corpus statistics and biases, especially during finetuning on domain-specific corpora. In this paper, we propose a simple modification to causal language modeling called conditional finetuning, which performs language modeling conditioned on a context. We show that a context can "explain away" certain corpus statistics and make the model avoid learning them. In this fashion, conditional finetuning achieves selective learning from a corpus, learning knowledge useful for downstream tasks while avoiding learning useless corpus statistics like topic biases. This selective learning effect leads to less forgetting and better stability-plasticity tradeoff in domain finetuning, potentially benefitting lifelong learning with language models.

📄 PDF Abstract BibTeX arXiv:2406.01976

Code (1)

xiaozeroone/conditional_finetune 공식 구현 pytorch

Tasks

Causal Language ModelingLanguage ModelingLanguage ModellingLifelong learning

Similar Papers 제목 키워드 기반

Conditional BERT Contextual Augmentation

2018-12-17 · Xing Wu, Shangwen Lv, Liangjun Zang, Jizhong Han 외

We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neu…

Data AugmentationLanguage ModelingLanguage ModellingText Classification

Static and Dynamic Vector Semantics for Lambda Calculus Models of Natural Language

2018-10-26 · Mehrnoosh Sadrzadeh, Reinhard Muskens

Vector models of language are based on the contextual aspects of language, the distributions of words and how they co-occur in text. Truth conditional models focus on the logical aspects of language, compositional proper…

Sentence

Modelling Source- and Target- Language Syntactic Information as Conditional Context in Interactive Neural Machine Translation

2020-11-01 · EAMT 2020 11 · Kamal Kumar Gupta, Rejwanul Haque, Asif Ekbal, Pushpak Bhattacharyya 외

In interactive machine translation (MT), human translators correct errors in automatic translations in collaboration with the MT systems, which is seen as an effective way to improve the productivity gain in translation.…

Machine TranslationNMTTranslation

Tractable Transformers for Flexible Conditional Generation

2025-02-11 · Anji Liu, Xuejie Liu, Dayuan Zhao, Mathias Niepert 외

Non-autoregressive (NAR) generative models are valuable because they can handle diverse conditional generation tasks in a more principled way than their autoregressive (AR) counterparts, which are constrained by sequenti…

Decoder

Conditional Prompt Learning for Vision-Language Models

2022-03-10 · CVPR 2022 1 · Kaiyang Zhou, Jingkang Yang, Chen Change Loy, Ziwei Liu

With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. A recently proposed method named Context Optimization (CoOp) …

Domain GeneralizationPrompt EngineeringPrompt Learning