Related papers: Science Checker Reloaded: A Bidirectional Paradigm…
Large language models (LLMs) typically enhance their performance through either the retrieval of semantically similar information or the improvement of their reasoning capabilities. However, a significant challenge remains in effectively…
Scientific paper retrieval, particularly framed as document-to-document retrieval, aims to identify relevant papers in response to a long-form query paper, rather than a short query string. Previous approaches to this task have focused…
Interdisciplinary studies often require researchers to explore literature in diverse branches of knowledge. Yet, navigating through the highly scattered knowledge from unfamiliar disciplines poses a significant challenge. In this paper, we…
The rapid growth of scientific literature has made it difficult for the researchers to quickly learn about the developments in their respective fields. Scientific document summarization addresses this challenge by providing summaries of the…
Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems from two fundamental challenges: 1) a low Signal-to-Noise…
Information Retriever (IR) aims to find the relevant documents (e.g. snippets, passages, and articles) to a given query at large scale. IR plays an important role in many tasks such as open domain question answering and dialogue systems,…
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…
Conversational interfaces that allow for intuitive and comprehensive access to digitally stored information remain an ambitious goal. In this thesis, we lay foundations for designing conversational search systems by analyzing the…
Publishing reproducible analyses is a long-standing and widespread challenge for the scientific community, funding bodies and publishers. Although a definitive solution is still elusive, the problem is recognized to affect all disciplines…
Because of the data deluge in scientific publication, finding relevant information is getting harder and harder for researchers and readers. Building an enhanced scientific search engine by taking semantic relations into account poses a…
Recent advances in large language models (LLMs) have led to new summarization strategies, offering an extensive toolkit for extracting important information. However, these approaches are frequently limited by their reliance on isolated…
Recently, automatically extracting information from visually rich documents (e.g., tickets and resumes) has become a hot and vital research topic due to its widespread commercial value. Most existing methods divide this task into two…
Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented generation (RAG) and agentic search. Unlike human users, LLMs are constrained by limited…
Sequence-to-sequence neural networks have been widely used in language-based applications as they have flexible capabilities to learn various language models. However, when seeking for the optimal language response through trained neural…
Two key assumptions shape the usual view of ranked retrieval: (1) that the searcher can choose words for their query that might appear in the documents that they wish to see, and (2) that ranking retrieved documents will suffice because the…
Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information…
Extracting hypotheses and their supporting statistical evidence from full-text scientific articles is central to the synthesis of empirical findings, but remains difficult due to document length and the distribution of scientific arguments…
Scientific research is highly structured and some of that structure is reflected in research reports. Traditional scientific research reports are yielding to interactive documents which expose their internal structure and are richly linked…
Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. However, in…
Information retrieval (IR) or knowledge retrieval, is a critical component for many down-stream tasks such as open-domain question answering (QA). It is also very challenging, as it requires succinctness, completeness, and correctness. In…