LLMs are Also Effective Embedding Models: An In-depth Overview
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913959447101440 |
|---|---|
| author | Tao, Chongyang Shen, Tao Gao, Shen Zhang, Junshuo Li, Zhen Hua, Kai Hu, Wenpeng Tao, Zhengwei Ma, Shuai |
| author_facet | Tao, Chongyang Shen, Tao Gao, Shen Zhang, Junshuo Li, Zhen Hua, Kai Hu, Wenpeng Tao, Zhengwei Ma, Shuai |
| contents | Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs such as GPT, LLaMA, and Mistral. This survey provides an in-depth overview of this transition, beginning with foundational techniques before the LLM era, followed by LLM-based embedding models through two main strategies to derive embeddings from LLMs. 1) Direct prompting: We mainly discuss the prompt designs and the underlying rationale for deriving competitive embeddings. 2) Data-centric tuning: We cover extensive aspects that affect tuning an embedding model, including model architecture, training objectives, data constructions, etc. Upon the above, we also cover advanced methods for producing embeddings from longer texts, multilingual, code, cross-modal data, as well as reasoning-aware and other domain-specific scenarios. Furthermore, we discuss factors affecting choices of embedding models, such as performance/efficiency comparisons, dense vs sparse embeddings, pooling strategies, and scaling law. Lastly, the survey highlights the limitations and challenges in adapting LLMs for embeddings, including cross-task embedding quality, trade-offs between efficiency and accuracy, low-resource, long-context, data bias, robustness, etc. This survey serves as a valuable resource for researchers and practitioners by synthesizing current advancements, highlighting key challenges, and offering a comprehensive framework for future work aimed at enhancing the effectiveness and efficiency of LLMs as embedding models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12591 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLMs are Also Effective Embedding Models: An In-depth Overview Tao, Chongyang Shen, Tao Gao, Shen Zhang, Junshuo Li, Zhen Hua, Kai Hu, Wenpeng Tao, Zhengwei Ma, Shuai Computation and Language Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs such as GPT, LLaMA, and Mistral. This survey provides an in-depth overview of this transition, beginning with foundational techniques before the LLM era, followed by LLM-based embedding models through two main strategies to derive embeddings from LLMs. 1) Direct prompting: We mainly discuss the prompt designs and the underlying rationale for deriving competitive embeddings. 2) Data-centric tuning: We cover extensive aspects that affect tuning an embedding model, including model architecture, training objectives, data constructions, etc. Upon the above, we also cover advanced methods for producing embeddings from longer texts, multilingual, code, cross-modal data, as well as reasoning-aware and other domain-specific scenarios. Furthermore, we discuss factors affecting choices of embedding models, such as performance/efficiency comparisons, dense vs sparse embeddings, pooling strategies, and scaling law. Lastly, the survey highlights the limitations and challenges in adapting LLMs for embeddings, including cross-task embedding quality, trade-offs between efficiency and accuracy, low-resource, long-context, data bias, robustness, etc. This survey serves as a valuable resource for researchers and practitioners by synthesizing current advancements, highlighting key challenges, and offering a comprehensive framework for future work aimed at enhancing the effectiveness and efficiency of LLMs as embedding models. |
| title | LLMs are Also Effective Embedding Models: An In-depth Overview |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.12591 |