Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models

arXiv:2404.03921v1 Announce Type: new
Abstract: Sentence Embedding stands as a fundamental task within the realm of Natural Language Processing, finding extensive application in search engines, expert systems, and question-and-answer platforms. With the continuous evolution of large language models such as LLaMA and Mistral, research on sentence embedding has recently achieved notable breakthroughs. However, these advancements mainly pertain to fine-tuning scenarios, leaving explorations into computationally efficient direct inference methods for sentence representation in a nascent stage. This paper endeavors to bridge …

abstract application arxiv continuous cs.cl embedding embeddings evolution expert generative language language models language processing large language large language models llama mistral natural natural language natural language processing platforms processing question realm research search simple systems type