C-Pack: Packaged Resources To Advance General Chinese Embedding

By Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff. arXiv.org, 2023

931 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/2ff694e20f492a7acf7fd0646c5e1576f0b3c901

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval (2024, methodology): “Re-sults show that our encoder outperforms the same-sized previous state-of-the-art XLM-R (Conneau et al., 2020) et al., 2023), French (Ciancone et al., 2024) and Polish (Po ´ swiata et al., 2024).”
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference (2024, unknown): “Surprisingly, these pipelines currently rely on older models, and quite often on the original BERT itself as their backbone (Wang et al., 2022; Xiao et al., 2023), without leveraging improvements developed in recent years.”
Nomic Embed: Training a Reproducible Long Context Text Embedder (2024, methodology): “The majority of the top open-source models on the MTEB benchmark (Muennighoff et al., 2023) are limited to context lengths of 512, such as E5 Wang et al. (2022), GTE Li et al. (2023), and BGE Xiao et al. (2023).”
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation (2024, unknown): “Particularly, the unsupervised data is curated by extracting the rich-semantic structures, e.g., title-body, title-abstract, instruction-output, etc., within a wide variety of multi-lingual corpora, including Wikipedia, S2ORC (Lo et al., 2020), xP3 (Muennighoff et al., 2023), mC4 (Raffel et al., 202”
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (2024, methodology): “Additionally, we also include a Reranker module to examine the retrieval performance, using bge-reranker-large (Xiao et al., 2023).”
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression (2023, methodology): “Conversely, dense retrieval methods assess the relevance between queries and documents in latent space using embedding model (Reimers and Gurevych, 2019; Xiao et al., 2023; Günther et al., 2023) and reranker model (Xiao et al., 2023).”
Improving Text Embeddings with Large Language Models (2023, methodology): “To address this challenge, methods like Contriever [17], OpenAI Embeddings [29], E5 [44], and BGE [46] adopt a multi-stage training paradigm.”
Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024, unknown): “6, they separately encode the input, the retrieved code, and the corresponding summary, then combine the middle representations or probabilities in the decoder.”
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders (2024, background): “The advantages of small bidirectional encoders come at the cost of complex and computationally intensive training regimes (Li et al., 2023a; Xiao et al., 2023; Li et al., 2023a).”
Nomic Embed Vision: Expanding the Latent Space (2024, methodology): “Since then, models such as E5 (Wang et al., 2024), GTE (Li et al., 2023), BGE (Xiao et al., 2024), InstructOR (Su et al., 2023), Jina (G¨unther et al., 2024), and Nomic (Nussbaum et al., 2024) train dual encoders in multiple stages.”
SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation (2026, unknown): “While MTEB primarily targets English, it catalyzed the development of language-specific benchmarks providing comparable depth: C-MTEB (Xiao et al., 2023) for Chinese (35 datasets), PL-MTEB (Po´swiata et al., 2024) for Polish (28 datasets), the Scandinavian Embed-ding Benchmark (Enevoldsen et al.,…”
The TellTail of Embeddings: Fingerprinting Retrievers in Black-Box Systems (2026, unknown): “5 [44]; gtr-t5-base [45]; minilm-l6 and minilm-l12 [46]; mpnet [47]; snowflake-v2 [48]; gemma-300m [49]; bge-base [50]; and the closed-weights model text-embedding-3-small (OpenAI) [51].”
Effects of Model Choice, Corpus Context, and Post Hoc Correction on Layer-Level Embedding Degradation in Clinical Document Retrieval: Experimental Study (2026, unknown): “…embedding geometry, with pairwise cosine similarities exceeding 0.90, whereas general-purpose models (Beijing Academy of Artificial Intelligence General Embedding [BGE]-base [6], General Text Embeddings [GTE]-base [7], Nomic-embed-text [8]) achieved higher MRR@10 and more dispersed geometry.”
ARTLAS: Mapping Art-Technology Institutions via Conceptual Axes, Text Embeddings, and Unsupervised Clustering (2026, unknown): “More recent models – including the BGE family [17,33] and the GTE family [18] – achieve state-of-the-art performance on the Massive Text Embedding Benchmark (MTEB) and are particularly suited for domain-specific retrieval and clustering tasks.”
EmbeddingRWKV: State-Centric Retrieval with Reusable States (2026, unknown): “…(Devlin et al., 2019; Hou et al., 2024a) to large language model backbones, with recent systems such as NV-Emb (Lee et al., 2024), E5-Mistral (Wang et al., 2024c), and GTE (Zhang et al., 2024) achieving strong performance on benchmarks like MTEB (Muennighoff et al., 2023a; Xiao et al., 2023).”