Related papers: Hierarchical Memory Organization for Wikipedia Gen…
Corrective Retrieval Augmented Generation (CRAG) improves the robustness of RAG systems by evaluating retrieved document quality and triggering corrective actions. However, the original implementation relies on proprietary components…
High quality arguments are essential elements for human reasoning and decision-making processes. However, effective argument construction is a challenging task for both human and machines. In this work, we study a novel task on…
The development of a company often entails the emergence of autonomous data sources with different structural and technological organization. This can lead to the inability of data analysis at a high level and a violation of the integrity…
How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks are usually a great choice and a promising way. However,…
Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based…
Large Multimodal Models (LMMs) have achieved remarkable progress in generating photorealistic and prompt-aligned images, but they often produce outputs that contradict verifiable knowledge, especially when prompts involve fine-grained…
A selection of intellectual goods produced by online communities - e.g. open source software or knowledge bases like Wikipedia - are in daily use by a broad audience, and thus their quality impacts the public at large. Yet, it is still…
Written texts reflect an author's perspective, making the thorough analysis of literature a key research method in fields such as the humanities and social sciences. However, conventional text mining techniques like sentiment analysis and…
Multimodal Retrieval Augmented Generation (MMRAG) is a powerful approach to question-answering over multimodal documents. A key challenge with evaluating MMRAG is the paucity of high-quality datasets matching the question styles and…
An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph. In many cases citations are either outdated…
Current approaches to machine translation (MT) either translate sentences in isolation, disregarding the context they appear in, or model context at the level of the full document, without a notion of any internal structure the document may…
Knowledge bases are very good sources for knowledge extraction, the ability to create knowledge from structured and unstructured sources and use it to improve automatic processes as query expansion. However, extracting knowledge from…
Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal,…
Writers generally rely on plans or sketches to write long stories, but most current language models generate word by word from left to right. We explore coarse-to-fine models for creating narrative texts of several hundred words, and…
Hyperlinks constitute the backbone of the Web; they enable user navigation, information discovery, content ranking, and many other crucial services on the Internet. In particular, hyperlinks found within Wikipedia allow the readers to…
Wikipedia is a critical source of information for millions of users across the Web. It serves as a key resource for large language models, search engines, question-answering systems, and other Web-based applications. In Wikipedia, content…
Retrieval-augmented generation stores all content indiscriminately, degrading accuracy as noise accumulates. Parametric approaches compress knowledge into weights, precluding selective updates. Neither mirrors biological memory, which gates…
Recent advances in transformer-based text-to-motion generation have led to impressive progress in synthesizing high-quality human motion. Nevertheless, jointly achieving high fidelity, streaming capability, real-time responsiveness, and…
Although retrieval-augmented generation(RAG) significantly improves generation quality by retrieving external knowledge bases and integrating generated content, it faces computational efficiency bottlenecks, particularly in knowledge…
This Ontologies are widely used as a means for solving the information heterogeneity problems on the web because of their capability to provide explicit meaning to the information. They become an efficient tool for knowledge representation…