Chain-of-note: Enhancing robustness in retrieval-augmented language models
Retrieval-augmented language models (RALMs) represent a substantial advancement in
the capabilities of large language models, notably in reducing factual hallucination by …
the capabilities of large language models, notably in reducing factual hallucination by …
Dense x retrieval: What retrieval granularity should we use?
Dense retrieval has become a prominent method to obtain relevant context or world
knowledge in open-domain NLP tasks. When we use a learned dense retriever on a …
knowledge in open-domain NLP tasks. When we use a learned dense retriever on a …
Sub-sentence encoder: Contrastive learning of propositional semantic representations
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model
for fine-grained semantic representation of text. In contrast to the standard practice with …
for fine-grained semantic representation of text. In contrast to the standard practice with …
Think and retrieval: A hypothesis knowledge graph enhanced medical large language models
X Jiang, R Zhang, Y Xu, R Qiu, Y Fang, Z Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
We explore how the rise of Large Language Models (LLMs) significantly impacts task
performance in the field of Natural Language Processing. We focus on two strategies …
performance in the field of Natural Language Processing. We focus on two strategies …
Pre-training multi-task contrastive learning models for scientific literature understanding
Scientific literature understanding tasks have gained significant attention due to their
potential to accelerate scientific discovery. Pre-trained language models (LMs) have shown …
potential to accelerate scientific discovery. Pre-trained language models (LMs) have shown …
IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues
Although the Retrieval-Augmented Generation (RAG) paradigms can use external
knowledge to enhance and ground the outputs of Large Language Models (LLMs) to …
knowledge to enhance and ground the outputs of Large Language Models (LLMs) to …
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
In traditional RAG framework, the basic retrieval units are normally short. The common
retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design …
retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design …
SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing
We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English
information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that …
information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that …
A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion
Entity Set Expansion, Taxonomy Expansion, and Seed-Guided Taxonomy Construction are
three representative tasks that can be used to automatically populate an existing taxonomy …
three representative tasks that can be used to automatically populate an existing taxonomy …
Question Answering with Texts and Tables through Deep Reinforcement Learning
This paper proposes a novel architecture to generate multi-hop answers to open domain
questions that require information from texts and tables, using the Open Table-and-Text …
questions that require information from texts and tables, using the Open Table-and-Text …