Related papers: RocketQA: An Optimized Training Approach to Dense …

The retrieval model is an indispensable component for real-world knowledge-intensive tasks, e.g., open-domain question answering (ODQA). As separate retrieval skills are annotated for different datasets, recent work focuses on customized…

In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance…

Long-tail question answering presents significant challenges for large language models (LLMs) due to their limited ability to acquire and accurately recall less common knowledge. Retrieval-augmented generation (RAG) systems have shown great…

Dense retrieval conducts text retrieval in the embedding space and has shown many advantages compared to sparse retrieval. Existing dense retrievers optimize representations of queries and documents with contrastive training and map them to…

Large language models have recently pushed open domain question answering (ODQA) to new frontiers. However, prevailing retriever-reader pipelines often depend on multiple rounds of prompt level instructions, leading to high computational…

Unlike the Open Domain Question Answering (ODQA) setting, the conversational (ODConvQA) domain has received limited attention when it comes to reevaluating baselines for both efficiency and effectiveness. In this paper, we study the…

We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. We model retrieval decisions as…

In dense retrieval, embedding long texts into dense vectors can result in information loss, leading to inaccurate query-text matching. Additionally, low-quality texts with excessive noise or sparse key information are unlikely to align well…

To better support information retrieval tasks such as web search and open-domain question answering, growing effort is made to develop retrieval-oriented language models, e.g., RetroMAE and many others. Most of the existing works focus on…

Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for…

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose…

Knowledge-intensive multi-hop question answering (QA) tasks, which require integrating evidence from multiple sources to address complex queries, often necessitate multiple rounds of retrieval and iterative generation by large language…

Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved promising performance on the task of open-domain question answering (QA). Their effectiveness can further reach new state-of-the-arts by…

One of the challenges in large-scale information retrieval (IR) is to develop fine-grained and domain-specific methods to answer natural language questions. Despite the availability of numerous sources and datasets for answer retrieval,…

Efficiently retrieving a concise set of candidates from a large document corpus remains a pivotal challenge in Information Retrieval (IR). Neural retrieval models, particularly dense retrieval models built with transformers and pretrained…

Reading Comprehension (RC) is a task of answering a question from a given passage or a set of passages. In the case of multiple passages, the task is to find the best possible answer to the question. Recent trials and experiments in the…

Most Outside-Knowledge Visual Question Answering (OK-VQA) systems employ a two-stage framework that first retrieves external knowledge given the visual question and then predicts the answer based on the retrieved content. However, the…

Conversational search supports multi-turn user-system interactions to solve complex information needs. Different from the traditional single-turn ad-hoc search, conversational search encounters a more challenging problem of…

Question-answering (QA) is an important application of Information Retrieval (IR) and language models, and the latest trend is toward pre-trained large neural networks with embedding parameters. Augmenting QA performances with these LLMs…

The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge. Although prior work has sought to increase the knowledge coverage by incorporating structured knowledge beyond…