Related papers: APE: Faster and Longer Context-Augmented Generatio…

Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to input features, have proven effective for explaining the…

The advancements in cloud-based Large Languages Models (LLMs) have revolutionized AI-assisted programming. However, their integration into certain local development environments like ones within the Apple software ecosystem (e.g., iOS apps,…

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable…

Retrieval-augmented generation (RAG) systems trained using reinforcement learning (RL) with reasoning are hampered by inefficient context management, where long, noisy retrieved documents increase costs and degrade performance. We introduce…

Reasoning LLMs produce longer outputs, requiring speculative decoding drafters trained on extended sequences. Parallel drafting - predicting multiple tokens per forward pass - offers latency benefits over sequential generation, but training…

Large vision-language models (LVLMs) employ multi-modal in-context learning (MM-ICL) to adapt to new tasks by leveraging demonstration examples. While increasing the number of demonstrations boosts performance, they incur significant…

This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency…

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.…

Retrieval-augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG for understanding of videos is appealing but there are two…

This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer. Conventional RAG methods usually perform a single retrieval step before…

Retrieval-Augmented Generation (RAG) systems combine dense retrievers and language models to ground LLM outputs in retrieved documents. However, the opacity of how these components interact creates challenges for deployment in high-stakes…

Large language models (LLMs) have transformed natural language processing (NLP), enabling diverse applications by integrating large-scale pre-trained knowledge. However, their static knowledge limits dynamic reasoning over external…

This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \textbf{S}mart \textbf{P}arallel \textbf{A}uto-\textbf{C}orrect d\textbf{E}coding (SPACE), an innovative approach…

Motivated by the imperative for real-time responsiveness and data privacy preservation, large language models (LLMs) are increasingly deployed on resource-constrained edge devices to enable localized inference. To improve output quality,…

Enterprise systems increasingly require natural language interfaces that can translate user requests into structured operations such as SQL queries and REST API calls. While large language models (LLMs) show promise for code generation…

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve…

The recently developed retrieval-augmented generation (RAG) technology has enabled the efficient construction of domain-specific applications. However, it also has limitations, including the gap between vector similarity and the relevance…

Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized…

Long contexts improve capabilities of large language models but pose serious hardware challenges: compute and memory footprints grow linearly with sequence length. Particularly, the decoding phase continuously accesses massive KV cache,…

Retrieval-Augmented Generation (RAG) has emerged as a crucial framework in natural language processing (NLP), improving factual consistency and reducing hallucinations by integrating external document retrieval with large language models…