Related papers: SPIRE: Structure-Preserving Interpretable Retrieva…

Model cards describe model behavior through a mixture of textual descriptions and structured artifacts, including performance, configuration, and dataset tables. Existing model search systems rely predominantly on semantic similarity over…

Real-world document question answering is challenging. Analysts must synthesize evidence across multiple documents and different parts of each document. However, any fixed LLM context window can be exceeded as document collections grow. A…

Academic literature retrieval is concerned with the selection of papers that are most likely to match a user's information needs. Most of the retrieval systems are limited to list-output models, in which the retrieval results are isolated…

We propose a structured approach to the problem of retrieval of images by content and present a description logic that has been devised for the semantic indexing and retrieval of images containing complex objects. As other approaches do, we…

Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new documents requires updating model parameters to encode new…

Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in locating the correct document and evidence fragmentation in…

Large-scale digitization initiatives have unlocked massive collections of historical newspapers, yet effective computational access remains hindered by OCR corruption, multilingual orthographic variation, and temporal language drift. We…

Code summarization aims to generate concise natural language descriptions of source code, which can help improve program comprehension and maintenance. Recent studies show that syntactic and structural information extracted from abstract…

Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context window receives substantially less attention than content at the boundaries, a phenomenon…

Column matching is a central task in reconciling schemas for data integration. Column names and descriptions are valuable for this task. LLMs can leverage such natural-language schema metadata. However, in many datasets, correct matching…

We introduce WordScape, a novel pipeline for the creation of cross-disciplinary, multilingual corpora comprising millions of pages with annotations for document layout detection. Relating visual and textual items on document pages has…

Heterogeneous information networks (HIN) have gained increasing popularity in recent years for capturing complex relations between diverse types of nodes. Meta-structures are proposed as a useful tool to identify the important patterns in…

Designing an embedding retrieval system requires navigating a complex design space of conflicting trade-offs between efficiency and effectiveness. This work structures these decisions as a vertical traversal of the system design stack. We…

The increasing volume and complexity of scientific literature demand robust methods for organizing and understanding research documents. In this study, we investigate whether structured knowledge, specifically, subject-predicate-object…

The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-modal semantic…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are…

Retrieval systems often fail when user queries differ stylistically or semantically from the language used in domain documents. Query rewriting has been proposed to bridge this gap, improving retrieval by reformulating user queries into…

This paper challenges a cross-genre document retrieval task, where the queries are in formal writing and the target documents are in conversational writing. In this task, a query, is a sentence extracted from either a summary or a plot of…

Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth. This task is challenging due to the need to accurately capture diverse facets of input…