Papers with multi-attribute control
FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Controllable text generation (CTG) focuses on crafting texts adhering to specific attributes . studies show learning-based methods require extensive computational and data resources . |
| Approach: | They propose a learning-free approach that dynamically adjusts the weights of selected feedforward neural network vectors to steer the outputs of large language models. |
| Outcome: | The proposed approach outperforms learning-based and learning-free methods on multi-attribute control. |
Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review (2026.acl-long)
Copied to clipboard
| Challenge: | Existing ARG work lacks author inputs and controls and no evaluation measures response reflection of author signals and effectiveness in addressing reviewer concerns. |
| Approach: | They propose a novel author-in-the-loop framework that integrates domain expertise and author-only information into author response generation (ARG) they also propose re3Align, a large-scale dataset of aligned review–response–revision triplets, where revisions proxy author signals and REspGen, an author- in-the loop ARG framework supporting flexible author input, multi-attribute control, and evaluation-guided refinement. |
| Outcome: | Experiments with SOTA LLMs show that author input and evaluation-guided refinement improves author response quality and controllability–quality trade-offs. |
Controlled Text Generation with Hidden Representation Transformations (2023.findings-acl)
Copied to clipboard
| Challenge: | Using a con-trolled language model, we gain attribute control by modifying the hidden representation of thebase model through learning transformations. |
| Approach: | They propose a con-trolled language generation framework that gains attribute control bymodifying the hidden representation of thebase model through learned transformations. |
| Outcome: | The proposed framework outperforms all thebaselines in detoxification, positivesentiment steering, and text simplification while minimizing the loss in linguistic qualities. |