Large language models for information retrieval: A survey
As a primary means of information acquisition, information retrieval (IR) systems, such as
search engines, have integrated themselves into our daily lives. These systems also serve …
search engines, have integrated themselves into our daily lives. These systems also serve …
Retrieval-augmented generation for ai-generated content: A survey
The development of Artificial Intelligence Generated Content (AIGC) has been facilitated by
advancements in model algorithms, scalable foundation model architectures, and the …
advancements in model algorithms, scalable foundation model architectures, and the …
A survey on knowledge distillation of large language models
This survey presents an in-depth exploration of knowledge distillation (KD) techniques
within the realm of Large Language Models (LLMs), spotlighting the pivotal role of KD in …
within the realm of Large Language Models (LLMs), spotlighting the pivotal role of KD in …
JaColBERTv2. 5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources
B Clavié - arXiv preprint arXiv:2407.20750, 2024 - arxiv.org
Neural Information Retrieval has advanced rapidly in high-resource languages, but progress
in lower-resource ones such as Japanese has been hindered by data scarcity, among other …
in lower-resource ones such as Japanese has been hindered by data scarcity, among other …
Benchmarking and building long-context retrieval models with loco and m2-bert
Retrieval pipelines-an integral component of many machine learning systems-perform
poorly in domains where documents are long (eg, 10K tokens or more) and where …
poorly in domains where documents are long (eg, 10K tokens or more) and where …
Active in-context learning for cross-domain entity resolution
Entity resolution (ER) is the task of determining the equivalence between two entity
descriptions. In traditional settings, the testing data and training data come from the same …
descriptions. In traditional settings, the testing data and training data come from the same …
PRADA: Pre-train Ranking Models with Diverse Relevance Signals Mined from Search Logs
Existing studies have proven that pre-trained ranking models outperform pre-trained
language models when it comes to ranking tasks. To pre-train such models, researchers …
language models when it comes to ranking tasks. To pre-train such models, researchers …
LargePiG: Your Large Language Model is Secretly a Pointer Generator
Recent research on query generation has focused on using Large Language Models
(LLMs), which despite bringing state-of-the-art performance, also introduce issues with …
(LLMs), which despite bringing state-of-the-art performance, also introduce issues with …
Improving dense retrieval models with LLM augmented data for dataset search
Data augmentation for training supervised models has achieved great results in different
areas. With the popularity of Large Language Models (LLMs), a research area has emerged …
areas. With the popularity of Large Language Models (LLMs), a research area has emerged …
KVPruner: Structural Pruning for Faster and Memory-Efficient Large Language Models
B Lv, Q Zhou, X Ding, Y Wang, Z Ma - arXiv preprint arXiv:2409.11057, 2024 - arxiv.org
The bottleneck associated with the key-value (KV) cache presents a significant challenge
during the inference processes of large language models. While depth pruning accelerates …
during the inference processes of large language models. While depth pruning accelerates …