Related papers: Link, Synthesize, Retrieve: Universal Document Lin…
Entity linking (mapping ambiguous mentions in text to entities in a knowledge base) is a foundational step in tasks such as knowledge graph construction, question-answering, and information extraction. Our method, LELA, is a modular…
This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point…
Large language models (LLMs) enable zero-shot approaches in open-domain question answering (ODQA), yet with limited advancements as the reader is compared to the retriever. This study aims at the feasibility of a zero-shot reader that…
Because of the increasing number of electronic data, designing efficient tools to retrieve and exploit documents is a major challenge. Current search engines suffer from two main drawbacks: there is limited interaction with the list of…
Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and…
Safety critical software assessment requires robust assessment against complex regulatory frameworks, a process traditionally limited by manual evaluation. This paper presents Document Retrieval-Augmented Fine-Tuning (DRAFT), a novel…
A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting. However, while highly coveted and being the most general,…
Universal Information Extraction~(Universal IE) aims to solve different extraction tasks in a uniform text-to-structure generation manner. Such a generation procedure tends to struggle when there exist complex information structures to be…
Cross-Domain Sequential Recommendation (CDSR) aims to mine and transfer users' sequential preferences across different domains to alleviate the long-standing cold-start issue. Traditional CDSR models capture collaborative information…
Zero-shot learning aims to recognize unseen objects using their semantic representations. Most existing works use visual attributes labeled by humans, not suitable for large-scale applications. In this paper, we revisit the use of documents…
Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer…
Given a query consisting of a reference image and a relative caption, Composed Image Retrieval (CIR) aims to retrieve target images visually similar to the reference one while incorporating the changes specified in the relative caption. The…
Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are only feasible for re-ranking a handful of candidate documents…
This work introduces a companion reproducible paper with the aim of allowing the exact replication of the methods, experiments, and results discussed in a previous work [5]. In that parent paper, we proposed many and varied techniques for…
Natural language inference (NLI) is formulated as a unified framework for solving various NLP problems such as relation extraction, question answering, summarization, etc. It has been studied intensively in the past few years thanks to the…
Structured documents analysis and recognition are essential for modern online on-boarding processes, and document localization is a crucial step to achieve reliable key information extraction. While deep-learning has become the standard…
The advent of Large Language Models (LLMs) heralds a pivotal shift in online user interactions with information. Traditional Information Retrieval (IR) systems primarily relied on query-document matching, whereas LLMs excel in comprehending…
We present {\em generative clustering} (GC) for clustering a set of documents, $\mathrm{X}$, by using texts $\mathrm{Y}$ generated by large language models (LLMs) instead of by clustering the original documents $\mathrm{X}$. Because LLMs…
Recent advancements in the area of Computer Vision with state-of-art Neural Networks has given a boost to Optical Character Recognition (OCR) accuracies. However, extracting characters/text alone is often insufficient for relevant…
Traditionally in the domain of legal research, the retrieval of pertinent citations from intricate case descriptions has demanded manual effort and keyword-based search applications that mandate expertise in understanding legal jargon.…