conftrace_

cross-task generalization

21 papers

Explore in graph

Co-occurring keywords

transfer learning (5449) zero-shot learning (3650) language model (4599) instruction tuning (838) few-shot learning (3398) instruction following (396) parameter-efficient fine-tuning (736) multi-task learning (2575) large language model (13587) low-rank adaptation (560)

Papers

CATAL: Causally Disentangled Task Representation Learning for Offline Meta-Reinforcement Learning AAAI 2026
Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning NAACL 2025
Toward Zero-Shot Instruction Following EACL 2024
Self-Specialization: Uncovering Latent Expertise within Large Language Models ACL 2024
From Instance Training to Instruction Learning: Task Adapters Generation from Instructions NIPS 2024
Cross-Task Generalization Abilities of Large Language Models NAACL 2024
Instance-Level Dynamic LoRAs Composition for Cross-Task Generalization EMNLP 2024
MedINST: Meta Dataset of Biomedical Instructions EMNLP 2024
HyperLoRA: Efficient Cross-task Generalization via Constrained Low-Rank Adapters Generation EMNLP 2024
Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations ACL 2023
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation EMNLP 2023
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks EMNLP 2023
Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning? ACL 2023
Multi-Head Adapter Routing for Cross-Task Generalization NIPS 2023
Differentiable Instruction Optimization for Cross-Task Generalization ACL 2023
Cross-Task Generalization via Natural Language Crowdsourcing Instructions ACL 2022
Unsupervised Cross-Task Generalization via Retrieval Augmentation NIPS 2022
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks EMNLP 2022
Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization EMNLP 2022
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP EMNLP 2021
Maximal Multiverse Learning for Promoting Cross-Task Generalization of Fine-Tuned Language Models EACL 2021