Summary of Llm2vec: Large Language Models Are Secretly Powerful Text Encoders, by Parishad Behnamghader et al.
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
by Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, Siva Reddy
First submitted to arxiv on: 9 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces LLM2Vec, an unsupervised approach to transform large decoder-only language models (LLMs) into strong text encoders. By enabling bidirectional attention, masked next token prediction, and contrastive learning, LLM2Vec can transform popular LLMs ranging from 1.3B to 8B parameters. The resulting models outperform encoder-only models on word-level tasks and reach state-of-the-art performance on the Massive Text Embeddings Benchmark (MTEB) using only publicly available data. When combined with supervised contrastive learning, LLM2Vec achieves new benchmarks on MTEB. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary LLMs are really smart computers that can understand language. Right now, they’re great at many tasks like answering questions or translating text. But sometimes we want them to learn more about the meaning of words and phrases. This paper shows how to make these LLMs even better by teaching them to understand the context of words. It’s like adding a special ingredient that makes their answers more accurate. |
Keywords
» Artificial intelligence » Attention » Decoder » Encoder » Supervised » Token » Unsupervised
