Related papers: Doc2Query--: When Less is More

Proactive search in conversations (PSC) aims to reduce user effort in formulating explicit queries by proactively retrieving useful relevant information given conversational context. Previous work in PSC either directly uses this context as…

Large language models (LLMs) demonstrate exceptional capabilities, yet still face the hallucination issue. Typical text generation approaches adopt an auto-regressive generation without deliberate reasoning, which often results in…

Large language models (LLMs) demonstrate strong capabilities in natural language processing but remain prone to hallucinations, generating factually incorrect or fabricated content. This issue undermines their reliability, particularly in…

Reducing hallucinations in Large Language Models (LLMs) is essential for improving the accuracy of data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual…

Inverted file structure is a common technique for accelerating dense retrieval. It clusters documents based on their embeddings; during searching, it probes nearby clusters w.r.t. an input query and only evaluates documents within them by…

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…

Conversational search aims to satisfy users' complex information needs via multiple-turn interactions. The key challenge lies in revealing real users' search intent from the context-dependent queries. Previous studies achieve conversational…

Interactive search sessions often contain multiple queries, where the user submits a reformulated version of the previous query in response to the original results. We aim to enhance the query recommendation experience for a commercial…

The goal of screening prioritisation in systematic reviews is to identify relevant documents with high recall and rank them in early positions for review. This saves reviewing effort if paired with a stopping criterion, and speeds up review…

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…

The hallucinations of large language models (LLMs) are increasingly mitigated by allowing LLMs to search for information and to ground their answers in real sources. Unfortunately, LLMs often struggle with posing the right search queries,…

The query suggestion or auto-completion mechanisms help users to type less while interacting with a search engine. A basic approach that ranks suggestions according to their frequency in the query logs is suboptimal. Firstly, many candidate…

Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions. However,…

Large pretrained generative models like GPT-3 often suffer from hallucinating non-existent or incorrect content, which undermines their potential merits in real applications. Existing work usually attempts to detect these hallucinations…

Query expansion aims to mitigate the mismatch between the language used in a query and in a document. However, query expansion methods can suffer from introducing non-relevant information when expanding the query. To bridge this gap,…

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…

Labeled datasets are essential for modern search engines, which increasingly rely on supervised learning methods like Learning to Rank and massive amounts of data to power deep learning models. However, creating these datasets is both…

Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not…

Many early neural Information Retrieval (NeurIR) methods are re-rankers that rely on a traditional first-stage retriever due to expensive query time computations. Recently, representation-based retrievers have gained much attention, which…

Retrieval-Augmented Generation (RAG) has become a widely adopted approach to enhance Large Language Models (LLMs) by incorporating external knowledge and reducing hallucinations. However, noisy or irrelevant documents are often introduced…