paper-with-me

Papers

Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models

2019-10-16 · Tianxing He, Jun Liu, Kyunghyun Cho, Myle Ott, Bing Liu, James Glass, Fuchun Peng

In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response generation task. Our major finding is that after standard finetuning, the model forgets some of the important language generation skills acquired during large-scale pretraining. We demonstrate the forgetting phenomenon through a set of detailed behavior analysis from the perspectives of knowledge transfer, context sensitivity, and function space projection. As a preliminary attempt to alleviate the forgetting problem, we propose an intuitive finetuning strategy named "mix-review". We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent. Finally, we discuss interesting behavior of the resulting dialogue model and its implications.

📄 PDF Abstract BibTeX arXiv:1910.07117

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderResponse GenerationText GenerationTransfer Learning

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

Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models

2021-04-01 · EACL 2021 2 · Tianxing He, Jun Liu, Kyunghyun Cho, Myle Ott 외

In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for the open-domain dia…

DecoderResponse GenerationText GenerationTransfer Learning

Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning

2026-05-04 · Prakhar Gupta, Garv Shah, Satyam Goyal, Anirudh Kanchi arxiv

Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting. Sparse Memory Finetuning (SMF) tries to avoid this by adding key-value m…

Pay Attention to Small Weights

2025-06-26 · Chao Zhou, Tom Jacobs, Advait Gadhikar, Rebekka Burkholz

Finetuning large pretrained neural networks is known to be resource-intensive, both in terms of memory and computational cost. To mitigate this, a common approach is to restrict training to a subset of the model paramete…

Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less

2026-05-07 · Yuxing Liu, Jianyu Wang, Tong Zhang arxiv

Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetuning with the same optimizer as in pretrain…

Which Pretrain Samples to Rehearse when Finetuning Pretrained Models?

2024-02-12 · Andrew Bai, Chih-Kuan Yeh, Cho-Jui Hsieh, Ankur Taly

Fine-tuning pretrained foundational models on specific tasks is now the de facto approach for text and vision tasks. A known pitfall of this approach is the forgetting of pretraining knowledge that happens during finetun…