Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
This addresses the problem of limited adaptability in task embeddings for researchers and practitioners using multiple models, though it is incremental as it builds on existing meta-learning techniques.
The paper tackles the challenge of creating task embeddings that work across diverse models, including prompt-based large language models, by proposing a unified framework (FUTE) that harmonizes embeddings from various models into a single vector space, enabling comparison and analysis while maintaining performance comparable to architecture-specific methods.
Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence of prompt-guided Large Language Models (LLMs) operating in a gradient-free manner. Existing task embedding methods rely on fine-tuned, task-specific language models, which hinders the adaptability of task embeddings across diverse models, especially prompt-based LLMs. To hardness the potential of task embeddings in the era of LLMs, we propose a framework for unified task embeddings (FUTE), harmonizing task embeddings from various models, including smaller language models and LLMs with varied prompts, within a single vector space. Such uniformity enables comparison and analysis of similarities amongst different models, broadening the scope and utility of existing task embedding methods in multi-model scenarios, while maintaining their performance comparable to architecture-specific methods.