# RepCali: High Efficient Fine-tuning Via Representation Calibration in Latent Space for Pre-trained Language Models

arXiv: https://arxiv.org/abs/2505.08463 · HTML: https://mlsanity.com/paper/2505.08463/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 51 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 30 of 42)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models](https://mlsanity.com/paper/2203.06904/) (2022)
- [BRIO: Bringing Order to Abstractive Summarization](https://mlsanity.com/paper/2203.16804/) (2022)
- [Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space](https://mlsanity.com/paper/2004.04092/) (2020)
- [MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.12005/) (2020)
- [Understanding and Improving Visual Prompting: A Label-Mapping Perspective](https://mlsanity.com/paper/2211.11635/) (2022)
- [Mixture Models for Diverse Machine Translation: Tricks of the Trade](https://mlsanity.com/paper/1902.07816/) (2019)
- [Towards Efficient Visual Adaption via Structural Re-parameterization](https://mlsanity.com/paper/2302.08106/) (2023)
- [Debiased Self-Training for Semi-Supervised Learning](https://mlsanity.com/paper/2202.07136/) (2022)
- [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2106.10502/) (2021)
- [Structured Fusion Networks for Dialog](https://mlsanity.com/paper/1907.10016/) (2019)

## Built on by (most cited first, 1 of 1)

- [GeoRecon: Graph-Level Representation Learning for 3D Molecules via Reconstruction-Based Pretraining](https://mlsanity.com/paper/2506.13174/) (2025)

## Abstract (arXiv)

Fine-tuning pre-trained language models (PLMs) has become a dominant paradigm in applying PLMs to downstream tasks. However, with limited fine-tuning, PLMs still struggle with the discrepancies between the representation obtained from the PLMs' encoder and the optimal input to the PLMs' decoder. This paper tackles this challenge by learning to calibrate the representation of PLMs in the latent space. In the proposed representation calibration method (RepCali), we integrate a specific calibration block to the latent space after the encoder and use the calibrated output as the decoder input. The merits of the proposed RepCali include its universality to all PLMs with encoder-decoder architectures, its plug-and-play nature, and ease of implementation. Extensive experiments on 25 PLM-based models across 8 tasks (including both English and Chinese datasets) demonstrate that the proposed RepCali offers desirable enhancements to PLMs (including LLMs) and significantly improves the performance of downstream tasks. Comparison experiments across 4 benchmark tasks indicate that RepCali is superior to the representative fine-tuning baselines.