Related papers: Multi-Step Reasoning Over Unstructured Text with B…
Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve relevant documents…
Knowledge retrieval and reasoning are two key stages in multi-hop question answering (QA) at web scale. Existing approaches suffer from low confidence when retrieving evidence facts to fill the knowledge gap and lack transparent reasoning…
Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented…
Recent advances in Large Language Models (LLMs) have significantly improved complex reasoning capabilities. Retrieval-Augmented Generation (RAG) has further extended these capabilities by grounding generation in dynamically retrieved…
Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is…
Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…
In this paper, we propose a comprehensive benchmark to investigate models' logical reasoning capabilities in complex real-life scenarios. Current explanation datasets often employ synthetic data with simple reasoning structures. Therefore,…
Large-scale text retrieval technology has been widely used in various practical business scenarios. This paper presents our systems for the TREC 2022 Deep Learning Track. We explain the hybrid text retrieval and multi-stage text ranking…
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,…
This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple (potentially long) documents. The system, called Visconde, uses a three-step pipeline to perform the task:…
Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured…
Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document…
Reasoning machine reading comprehension (R-MRC) aims to answer complex questions that require discrete reasoning based on text. To support discrete reasoning, evidence, typically the concise textual fragments that describe question-related…
Implicit sentiment analysis aims to uncover emotions that are subtly expressed, often obscured by ambiguity and figurative language. To accomplish this task, large language models and multi-step reasoning are needed to identify those…
Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…
This work deals with the challenge of learning and reasoning over multi-modal multi-hop question answering (QA). We propose a graph reasoning network based on the semantic structure of the sentences to learn multi-source reasoning paths and…
Retrieval-Augmented Generation (RAG) has become a pivotal paradigm for Large Language Models (LLMs), yet current approaches struggle with visually rich documents by treating text and images as isolated retrieval targets. Existing methods…
Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a "rationale'"). If…
Distilling large reasoning models is essential for making Long-CoT reasoning practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches select complete reasoning traces post-hoc, overlooking…
Deep LSTM is an ideal candidate for text recognition. However text recognition involves some initial image processing steps like segmentation of lines and words which can induce error to the recognition system. Without segmentation,…