Today's large language models (LLMs) typically train on short text segments (eg,< 4K
tokens) due to the quadratic complexity of their Transformer architectures. As a result, their …

Retrieval-augmented generation (RAG) is a key means to effectively enhance large
language models (LLMs) in many knowledge-based tasks. However, existing RAG methods …

Building a human-like system that continuously interacts with complex environments--
whether simulated digital worlds or human society--presents several key challenges. Central …

Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-
intensive tasks via interactions with tools and data retrievers have garnered significant …

We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented
Generation (RAG) that utilizes Signal-to-Noise Ratio (SNR)-based span uncertainty to …

The efficient processing of long context poses a serious challenge for large language
models (LLMs). Recently, retrieval-augmented generation (RAG) has emerged as a …

Retrieval-augmented generation (RAG) is a promising approach to address the limitations of
fixed knowledge in large language models (LLMs). However, current benchmarks for …

Document retrieval techniques form the foundation for the development of large-scale
information systems. The prevailing methodology is to construct a bi-encoder and compute …

Embeddings have become a cornerstone in the functionality of large language models
(LLMs) due to their ability to transform text data into rich, dense numerical representations …

Retrieval-Augmented Generation (RAG) mitigates the issue of hallucination in Large
Language Models (LLMs) by integrating information retrieval techniques. However, in the …