Related papers: Natural Logic-guided Autoregressive Multi-hop Docu…

The increased focus on misinformation has spurred development of data and systems for detecting the veracity of a claim as well as retrieving authoritative evidence. The Fact Extraction and VERification (FEVER) dataset provides such a…

Classic retrieval methods use simple bag-of-word representations for queries and documents. This representation fails to capture the full semantic richness of queries and documents. More recent retrieval models have tried to overcome this…

Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative…

Retrieve-and-rerank is a popular retrieval pipeline because of its ability to make slow but effective rerankers efficient enough at query time by reducing the number of comparisons. Recent works in neural rerankers take advantage of large…

The success of contextual word representations and advances in neural information retrieval have made dense vector-based retrieval a standard approach for passage and document ranking. While effective and efficient, dual-encoders are…

Speculative decoding (SD) has emerged as an effective technique to accelerate large language model (LLM) inference without compromising output quality. However, the achievable speedup largely depends on the effectiveness of the drafting…

Question generation (QG) attempts to solve the inverse of question answering (QA) problem by generating a natural language question given a document and an answer. While sequence to sequence neural models surpass rule-based systems for QG,…

Retrieval approaches that score documents based on learned dense vectors (i.e., dense retrieval) rather than lexical signals (i.e., conventional retrieval) are increasingly popular. Their ability to identify related documents that do not…

The classification of legal documents from an unstructured data corpus has several crucial applications in downstream tasks. Documents relevant to court filings are key in use cases such as drafting motions, memos, and outlines, as well as…

Evaluating the veracity of everyday claims is time consuming and in some cases requires domain expertise. We empirically demonstrate that the commonly used fact checking pipeline, known as the retriever-reader, suffers from performance…

Large Language Models (LLMs) have been increasingly employed for query expansion. However, their generative nature often undermines performance on complex multi-hop retrieval tasks by introducing irrelevant or noisy information. To address…

Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic…

Automated fact-checking aims to assess the truthfulness of textual claims based on relevant evidence. However, verifying complex claims that require multi-hop reasoning remains a significant challenge. We propose GraphCheck, a novel…

Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream…

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…

We present a new benchmark for evaluating Deep Search--a realistic and complex form of retrieval-augmented generation (RAG) that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. These include documents,…

Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document…

Neural networks with deep architectures have demonstrated significant performance improvements in computer vision, speech recognition, and natural language processing. The challenges in information retrieval (IR), however, are different…

Multi-Hop Question Answering (MHQA) tasks permeate real-world applications, posing challenges in orchestrating multi-step reasoning across diverse knowledge domains. While existing approaches have been improved with iterative retrieval,…

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…