paper-with-me

Papers

Controlled Text Generation with Hidden Representation Transformations

2023-05-30 · Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi, Amita Misra, Ankit Chadha, Emilio Ferrara

We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity). CHRT gains attribute control by modifying the hidden representation of the base model through learned transformations. We employ a contrastive-learning framework to learn these transformations that can be combined to gain multi-attribute control. The effectiveness of CHRT is experimentally shown by comparing it with seven baselines over three attributes. CHRT outperforms all the baselines in the task of detoxification, positive sentiment steering, and text simplification while minimizing the loss in linguistic qualities. Further, our approach has the lowest inference latency of only 0.01 seconds more than the base model, making it the most suitable for high-performance production environments. We open-source our code and release two novel datasets to further propel controlled language generation research.

📄 PDF Abstract BibTeX arXiv:2305.19230

Code (1)

amazon-science/wqa-controlled-text-generation 공식 구현 pytorch

Tasks

AttributeContrastive LearningText GenerationText Simplification

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model

2026-07-22 · Markus J. Buehler arxiv

Large language models can answer scientific questions, yet a correct output does not reveal whether the model represents or uses the governing physics. Here we show that materials science mechanism information in the ope…

When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures

2026-07-03 · Mojtaba Faramarzi, Alex Lamb, Irina Rish arxiv

Diffusion architectures now encompass convolutional UNets as well as transformer-based designs such as Diffusion Transformers (DiTs), inspired by Vision Transformers (ViTs), yet the effects of structured geometric pertur…

From Deep to Shallow: Transformations of Deep Rectifier Networks

2017-03-30 · Senjian An, Farid Boussaid, Mohammed Bennamoun, Jiankun Hu

In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be…

Jump to Conclusions: Short-Cutting Transformers With Linear Transformations

2023-03-16 · Alexander Yom Din, Taelin Karidi, Leshem Choshen, Mor Geva

Transformer-based language models create hidden representations of their inputs at every layer, but only use final-layer representations for prediction. This obscures the internal decision-making process of the model and…

Decision MakingLanguage ModelingLanguage Modelling

How Retrieved Context Shapes Internal Representations in RAG

2026-02-23 · Samuel Yeh, Sharon Li arxiv

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by conditioning generation on retrieved external documents, but the effect of retrieved context is often non-trivial. In realistic retrieval sett…