Related papers: Parallel Context-of-Experts Decoding for Retrieval…
Context-augmented generation (CAG) techniques, including RAG and ICL, require the efficient combination of multiple contexts to generate responses to user queries. Directly inputting these contexts as a sequence introduces a considerable…
In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of…
When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge the gap between external knowledge and the LLMs' parametric knowledge. Recent research has been…
Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk…
Retrieval augmented generation mitigates limitations of large language models in factual consistency and knowledge updating by introducing external knowledge. However, practical applications still suffer from semantic misalignment between…
Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context. While standard autoregressive decoding is slow due to its sequential nature, the…
Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…
Large Language Models (LLMs) have achieved impressive performance across a wide range of applications. However, they often suffer from hallucinations in knowledge-intensive domains due to their reliance on static pretraining corpora. To…
As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a…
Large language models (LLMs) are susceptible to generating hallucinated information, despite the integration of retrieval-augmented generation (RAG). Parallel context extension (PCE) is a line of research attempting to effectively…
Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently…
Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from…
A common approach to question answering with retrieval-augmented generation (RAG) is to concatenate documents into a single context and pass it to a language model to generate an answer. While simple, this strategy can obscure the…
Generative approaches have been recently shown to be effective for both Entity Disambiguation and Entity Linking (i.e., joint mention detection and disambiguation). However, the previously proposed autoregressive formulation for EL suffers…
Document Visual Question Answering (Document VQA) must cope with documents that span dozens of pages, yet leading systems still concatenate every page or rely on very large vision-language models, both of which are memory-hungry.…
Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…
Retrieval-Augmented Generation (RAG) has become an essential approach for extending the reasoning and knowledge capacity of large language models (LLMs). While prior research has primarily focused on retrieval quality and prompting…
Retrieval-Augmented Generation (RAG) often relies on large vector databases and cross-encoders tuned for large-scale corpora, which can be excessive for small, domain-specific collections. We present MODE (Mixture of Document Experts), a…
Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context…
Recent advances in reasoning models have demonstrated significant improvements in accuracy by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and…