paper-with-me

Papers

Aligning the Pretraining and Finetuning Objectives of Language Models

2020-02-05 · Nuo Wang Pierse, Jingwen Lu

We demonstrate that explicitly aligning the pretraining objectives to the finetuning objectives in language model training significantly improves the finetuning task performance and reduces the minimum amount of finetuning examples required. The performance margin gained from objective alignment allows us to build language models with smaller sizes for tasks with less available training data. We provide empirical evidence of these claims by applying objective alignment to concept-of-interest tagging and acronym detection tasks. We found that, with objective alignment, our 768 by 3 and 512 by 3 transformer language models can reach accuracy of 83.9%/82.5% for concept-of-interest tagging and 73.8%/70.2% for acronym detection using only 200 finetuning examples per task, outperforming the 768 by 3 model pretrained without objective alignment by +4.8%/+3.4% and +9.9%/+6.3%. We name finetuning small language models in the presence of hundreds of training examples or less "Few Example learning". In practice, Few Example Learning enabled by objective alignment not only saves human labeling costs, but also makes it possible to leverage language models in more real-time applications.

📄 PDF Abstract BibTeX arXiv:2002.02000

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning

2024-07-22 · Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal 외

Reward-based finetuning is crucial for aligning language policies with intended behaviors (e.g., creativity and safety). A key challenge is to develop steerable language models that trade-off multiple (conflicting) objec…

CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning

2023-03-06 · ICCV 2023 1 · Hritik Bansal, Nishad Singhi, Yu Yang, Fan Yin 외

Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data. However, previous studies have revealed that such models are vulnerabl…

Backdoor AttackContrastive LearningData Poisoning

LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures

2025-09-11 · Hai Huang, Yann LeCun, Randall Balestriero arxiv

Large Language Model (LLM) pretraining, finetuning, and evaluation rely on input-space reconstruction and generative capabilities. Yet, it has been observed in vision that embedding-space training objectives, e.g., with …

Pretraining Language Models with Human Preferences

2023-02-16 · Tomasz Korbak, Kejian Shi, Angelica Chen, Rasika Bhalerao 외

Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-qualit…

Imitation LearningLanguage Modelling

What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?

2022-04-12 · Thomas Wang, Adam Roberts, Daniel Hesslow, Teven Le Scao 외

Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly trained on. However, the architectures and pre…

DecoderLanguage ModelingLanguage ModellingMasked Language Modeling+1