However, Large langugae models (LLM) have acquired superior reading when dealing with complex multi-document question answering comprehension and reasoning capabilities by pretraining on (MDQA) tasks, accurately understanding the question's extensive natural langugae data [1, 2]. They have demonstrated constraints and covering all supporting evidence remains an remarkable performance on a variety of tasks and benchmarks, open challenge [10, 11]. This difficulty arises because previous particularly in the realm of question answering (QA) [3, 4]. Researchers research has treated the relationship between each text chunk are expanding the parameter scale of these models to and the target question in isolation. The retrieval models have enable them to retain more knowledge [5]. However, due to the concentrated solely on whether the main topic of each chunk absence of efficient methods to evaluate or edit their internalized aligns with the question [12]. Imperfect preprocessing can lead knowledge [6], knowledge-intensive tasks remain a major to the incorrect truncation of continuous chunks.

Large language models (LLMs) have demonstrated strong reasoning capabilities. Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks. Retrieval-augmented reasoning represents a promising approach. However, significant challenges still persist, including inaccurate and insufficient retrieval for complex questions, as well as difficulty in integrating multi-source knowledge. To address this, we propose Beam Aggregation Reasoning, BeamAggR, a reasoning framework for knowledge-intensive multi-hop QA. BeamAggR explores and prioritizes promising answers at each hop of question. Concretely, we parse the complex questions into trees, which include atom and composite questions, followed by bottom-up reasoning. For atomic questions, the LLM conducts reasoning on multi-source knowledge to get answer candidates. For composite questions, the LLM combines beam candidates, explores multiple reasoning paths through probabilistic aggregation, and prioritizes the most promising trajectory. Extensive experiments on four open-domain multi-hop reasoning datasets show that our method significantly outperforms SOTA methods by 8.5%. Furthermore, our analysis reveals that BeamAggR elicits better knowledge collaboration and answer aggregation.

Retrieval-Augmented Large Language Models (LLMs), which incorporate the non-parametric knowledge from external knowledge bases into LLMs, have emerged as a promising approach to enhancing response accuracy in several tasks, such as Question-Answering (QA). However, even though there are various approaches dealing with queries of different complexities, they either handle simple queries with unnecessary computational overhead or fail to adequately address complex multi-step queries; yet, not all user requests fall into only one of the simple or complex categories. In this work, we propose a novel adaptive QA framework, that can dynamically select the most suitable strategy for (retrieval-augmented) LLMs from the simplest to the most sophisticated ones based on the query complexity. Also, this selection process is operationalized with a classifier, which is a smaller LM trained to predict the complexity level of incoming queries with automatically collected labels, obtained from actual predicted outcomes of models and inherent inductive biases in datasets. This approach offers a balanced strategy, seamlessly adapting between the iterative and single-step retrieval-augmented LLMs, as well as the no-retrieval methods, in response to a range of query complexities. We validate our model on a set of open-domain QA datasets, covering multiple query complexities, and show that ours enhances the overall efficiency and accuracy of QA systems, compared to relevant baselines including the adaptive retrieval approaches. Code is available at: https://github.com/starsuzi/Adaptive-RAG.

Abstract: Multi-hop Machine reading comprehension is a challenging task with aim of answering a question based on disjoint pieces of information across the different passages. The evaluation metrics and datasets are a vital part of multi-hop MRC because it is not possible to train and evaluate models without them, also, the proposed challenges by datasets often are an important motivation for improving the existing models. Due to increasing attention to this field, it is necessary and worth reviewing them in detail. This study aims to present a comprehensive survey on recent advances in multi-hop MRC evaluation metrics and datasets. In this regard, first, the multi-hop MRC problem definition will be presented, then the evaluation metrics based on their multi-hop aspect will be investigated. Also, 15 multi-hop datasets have been reviewed in detail from 2017 to 2022, and a comprehensive analysis has been prepared at the end. Finally, open issues in this field have been discussed. Keywords: Multi-hop Machine Reading Comprehension, Multi-hop Machine Reading Comprehension Dataset, Natural Language Processing, 1-INTRODUCTION Machine reading comprehension (MRC) is one of the most important and long-standing topics in Natural Language Processing (NLP). MRC provides a way to evaluate an NLP system's capability for natural language understanding. An MRC task, in brief, refers to the ability of a computer to read and understand natural language context and then find the answer to questions about that context. The emergence of large-scale single-document MRC datasets, such as SQuAD (Rajpurkar et al., 2016), CNN/Daily mail (Hermann et al., 2015), has led to increased attention to this topic and different models have been proposed to address the MRC problem, such as (D. However, for many of these datasets, it has been found that models don't need to comprehend and reason to answer a question. For example, Khashabi et al (Khashabi et al., 2016) proved that adversarial perturbation in candidate answers has a negative effect on the performance of the QA systems. Similarly, (Jia & Liang, 2017) showed that adding an adversarial sentence to the SQuAD (Rajpurkar et al., 2016) context will drop the result of many existing models.