Papers with transfer ability
Layer-wise Swapping for Generalizable Multilingual Safety (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing safety datasets are predominantly English-centric, limiting progress in multilingual safety alignment. |
| Approach: | They propose a safety-aware layer swapping method that transfers alignment from an English safety expert to low-resource language experts without additional training. |
| Outcome: | The proposed method preserves performance on general language understanding tasks while enhancing safety in the target languages. |
Efficient Hyper-parameter Search for Knowledge Graph Embedding (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning knowledge graphs do not search hyper-parameters efficiently. |
| Approach: | They propose an efficient two-stage search algorithm which explores HP configurations on small subgraph and transfers top-performed configurations for fine-tuning on large full graph. |
| Outcome: | The proposed method finds better HPs than baseline algorithms within the same time budget and achieves 9.1% relative improvement on large-scale knowledge graphs. |
Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets (2024.lrec-main)
Copied to clipboard
| Challenge: | Multilingual Language Models (MLLMs) exhibit robust cross-lingual transfer capabilities for downstream tasks such as Named Entity Recognition (NER) challenges persist in MLLM implementations that are not cross-linguistically robust. |
| Approach: | They evaluate two well-known MLLMs on 13 pairs of languages with a geographic, genetic, or borrowing relationship. |
| Outcome: | The proposed models show that they can leverage information acquired in a source language and apply it to a target language. |
HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks (2023.findings-acl)
Copied to clipboard
| Challenge: | Pretraining and fine-tuning are the dominant paradigms in natural language processing. |
| Approach: | They propose a parameter-efficient multitask learning framework that takes trainable hyper-embeddings and visual modality as input and outputs weights for different modules in a pretrained language model. |
| Outcome: | The proposed framework adds fewer trainable parameters in multi-task learning while achieving superior performances and transfer ability compared to state-of-the-art methods. |
Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Continual learning and zero-shot learning approaches have not been adopted to scale to novel-emerging types. |
| Approach: | They propose a method to recognize entities in novel types by their textual names or descriptions. |
| Outcome: | The proposed method outperforms the state-of-the-art methods on three challenging OVNER benchmarks by 9.7%, 9.5%, and 1.8% F1-score of novel types. |
UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent studies have shown that multi-task instruction tuning after pre-training greatly improves the model’s robustness and transfer ability, which is crucial for building a high-quality dialog system. |
| Approach: | They propose to use Task-aware Automatic Prompt generation (TAP) to automatically generate high-quality prompts from 15 dialog-related tasks. |
| Outcome: | The proposed model is robust to input prompts and capable of various dialog-related tasks. |