Related papers: Strong and Efficient Baselines for Open Domain Con…

The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. We present DoQA, a dataset with 2,437 dialogues and 10,917 QA pairs. The dialogues…

Recently, pre-trained contextual models, such as BERT, have shown to perform well in language related tasks. We revisit the design decisions that govern the applicability of these models for the passage re-ranking task in open-domain…

Recent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another reader model. Despite performing…

RAG-based question-answering (QA) in specialist domains faces a cold-start problem: lack of evaluative benchmarks and absence of labeled data for post-training. We present DoRA (Domain-oriented RAG Assessment), a novel benchmark…

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…

In open-domain question answering (QA), retrieve-and-read mechanism has the inherent benefit of interpretability and the easiness of adding, removing, or editing knowledge compared to the parametric approaches of closed-book QA models.…

Open Domain Multi-Hop Question Answering (ODMHQA) plays a crucial role in Natural Language Processing (NLP) by aiming to answer complex questions through multi-step reasoning over retrieved information from external knowledge sources.…

Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input into two pre-trained models, and the vectors generated by…

Current dense retrievers (DRs) are limited in their ability to effectively process misspelled queries, which constitute a significant portion of query traffic in commercial search engines. The main issue is that the pre-trained language…

In this paper we are interested in the problem of learning an over-complete basis and a methodology such that the reconstruction or inverse problem does not need optimization. We analyze the optimality of the presented approaches, their…

We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific annotated data or…

Large Language Models (LLMs) have shown impressive capabilities in complex reasoning tasks. However, current approaches employ uniform language density for both intermediate reasoning and final answers, leading to computational…

State-of-the-art deep reading comprehension models are dominated by recurrent neural nets. Their sequential nature is a natural fit for language, but it also precludes parallelization within an instances and often becomes the bottleneck for…

Evaluating large language models (LLMs) on question answering often relies on static benchmarks that reward memorization and understate the role of retrieval, failing to capture the dynamic nature of world knowledge. We present…

Despite significant advances in long-context reasoning by large language models (LLMs), primarily through Online Reinforcement Learning (RL) methods, these approaches incur substantial computational costs and complexity. In contrast,…

Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks. However, their performance…

Question answering is a task that answers factoid questions using a large collection of documents. It aims to provide precise answers in response to the user's questions in natural language. Question answering relies on efficient passage…

Recently, open-domain question answering (QA) has been combined with machine comprehension models to find answers in a large knowledge source. As open-domain QA requires retrieving relevant documents from text corpora to answer questions,…

Conversational Question Answering (ConvQA) involves multiple subtasks, i) to understand incomplete questions in their context, ii) to retrieve relevant information, and iii) to generate answers. This work presents PRAISE, a pipeline-based…

Information retrieval systems have progressed notably from lexical techniques such as BM25 and TF-IDF to modern semantic retrievers. This survey provides a brief overview of the BM25 baseline, then discusses the architecture of modern…