MQPF: A MULTI-DIMENSIONAL QUALITY-AWARE PATH FUSION FRAMEWORK FOR QUESTION ANSWERING

In this paper, we detail our submission to the 7th year BioASQ competition. We present our approach for Task-7b, Phase B, Exact Answering Task. These Question Answering (QA) tasks include Factoid, Yes/No, List Type Question answering. Our system is based on a contextual word embedding model. We have used a Bidirectional Encoder Representations from Transformers (BERT) based system, fined tuned for biomedical question answering task using BioBERT. In the third test batch set, our system achieved the highest ‘MRR’ score for Factoid Question Answering task. Also, for List type question answering task our system achieved the highest recall score in the fourth test batch set. Along with our detailed approach, we present the results for our submissions, and also highlight identified downsides for our current approach and ways to improve them in our future experiments.

Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could introduce noise and degrade the performance, especially when handling multi-hop questions that require multiple steps of reasoning. To enhance the multi-hop reasoning ability of RAG models, we propose TRACE1. TRACE constructs knowledge-grounded reasoning chains, which are a series of logically connected knowledge triples, to identify and integrate supporting evidence from the retrieved documents for answering questions. Specifically, TRACE employs a KG Generator to create a knowledge graph (KG) from the retrieved documents, and then uses a novel Autoregressive Reasoning Chain Constructor to build reasoning chains. Experimental results on three multi-hop QA datasets show that TRACE achieves an average performance improvement of up to 14.03% compared to using all the retrieved documents. Moreover, the results indicate that using reasoning chains as context, rather than the entire documents, is often sufficient to correctly answer questions.

Knowledge graph question answering is an important research direction for question answering tasks. In recent years, there has been an increasing amount of research on knowledge graph question answering, but temporal knowledge graph question answering is still a relatively unexplored area. In question answering tasks, many natural language questions have explicit or implicit temporal constraints, and most existing research methods lack the temporal awareness to deal with complex temporal questions. To address these challenges, this paper proposes a question answering model based on temporal knowledge graph embedding (TKGETQA). The model uses TKG embeddings to root a question in the entities, relations and time horizons it references, and perceives temporal information from the question to improve the accuracy of answer prediction. Experiments on the dataset CronQuestions in this paper show that the TKGETQA model exhibits better results compared to existing temporal knowledge graph question answering approaches.

While conversing with chatbots, humans typically tend to ask many questions, a significant portion of which can be answered by referring to large-scale knowledge graphs (KG). While Question Answering (QA) and dialog systems have been studied independently, there is a need to study them closely to evaluate such real-world scenarios faced by bots involving both these tasks. Towards this end, we introduce the task of Complex Sequential QA which combines the two tasks of (i) answering factual questions through complex inferencing over a realistic-sized KG of millions of entities, and (ii) learning to converse through a series of coherently linked QA pairs. Through a labor intensive semi-automatic process, involving in-house and crowdsourced workers, we created a dataset containing around 200K dialogs with a total of 1.6M turns. Further, unlike existing large scale QA datasets which contain simple questions that can be answered from a single tuple, the questions in our dialogs require a larger subgraph of the KG. Specifically, our dataset has questions which require logical, quantitative, and comparative reasoning as well as their combinations. This calls for models which can: (i) parse complex natural language questions, (ii) use conversation context to resolve coreferences and ellipsis in utterances, (iii) ask for clarifications for ambiguous queries, and finally (iv) retrieve relevant subgraphs of the KG to answer such questions. However, our experiments with a combination of state of the art dialog and QA models show that they clearly do not achieve the above objectives and are inadequate for dealing with such complex real world settings. We believe that this new dataset coupled with the limitations of existing models as reported in this paper should encourage further research in Complex Sequential QA.

Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQA). KGEs typically create an embedding for each entity in the graph, which results in large model sizes on real-world graphs with millions of entities. For downstream tasks these atomic entity representations often need to be integrated into a multi stage pipeline, limiting their utility. We show that an off-the-shelf encoder-decoder Transformer model can serve as a scalable and versatile KGE model obtaining state-of-the-art results for KG link prediction and incomplete KG question answering. We achieve this by posing KG link prediction as a sequence-to-sequence task and exchange the triple scoring approach taken by prior KGE methods with autoregressive decoding. Such a simple but powerful method reduces the model size up to 98% compared to conventional KGE models while keeping inference time tractable. After finetuning this model on the task of KGQA over incomplete KGs, our approach outperforms baselines on multiple large-scale datasets without extensive hyperparameter tuning.

No one is perfect: Analysing the performance of question answering components over the DBpedia knowledge graph

Multi-hop question answering (MHQA) requires integrating knowledge scattered across multiple passages to derive the correct answer. Traditional retrieval-augmented generation (RAG) methods primarily focus on coarse-grained textual semantic similarity and ignore structural associations among dispersed knowledge, which limits their effectiveness in MHQA tasks. GraphRAG methods address this by leveraging knowledge graphs (KGs) to capture structural associations, but they tend to overly rely on structural information and fine-grained word- or phrase-level retrieval, resulting in an underutilization of textual semantics. In this paper, we propose a novel RAG approach called HGRAG for MHQA that achieves cross-granularity integration of structural and semantic information via hypergraphs. Structurally, we construct an entity hypergraph where fine-grained entities serve as nodes and coarse-grained passages as hyperedges, and establish knowledge association through shared entities. Semantically, we design a hypergraph retrieval method that integrates fine-grained entity similarity and coarse-grained passage similarity via hypergraph diffusion. Finally, we employ a retrieval enhancement module, which further refines the retrieved results both semantically and structurally, to obtain the most relevant passages as context for answer generation with the LLM. Experimental results on benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in QA performance, and achieves a 6× speedup in retrieval efficiency.

Large Language Models (LLMs) face significant challenges when attempting to utilize knowledge not encoded during pre-training. In-context learning (ICL) addresses this limitation by embedding relevant information directly into prompts, enabling LLMs to leverage external knowledge without updating their parameters. Recent advances have explored integrating knowledge graph (KG) information into prompts, taking advantage of the structured and factual representations of entities and relationships that KGs provide. A common approach involves identifying key concepts in a task, grounding them to KG nodes, extracting ego-subgraphs centered on these concepts, and incorporating them into prompts. However, not all subgraphs are equally relevant to the task, and selecting appropriate knowledge remains a critical challenge, as irrelevant or noisy subgraphs can reduce model accuracy. This study investigates how KG-based information related to task-specific concepts influences LLM performance on multiple-choice question answering (MCQA) tasks. We implement a four-stage pipeline that (1) identifies key concepts from questions and grounds them in the KG, (2) extracts individual ego-subgraphs for each concept, (3) integrates these subgraphs into prompts, and (4) evaluates their impact on LLM reasoning via probability scoring. Our analysis highlights which concept-specific subgraphs enhance performance, which introduce misleading information, and which have neutral effects. We show that carefully selected KG subgraphs can substantially outperform others in semantic relevance. Furthermore, we examine how the size and connectivity of selected KG subgraphs influence model performance. Overall, this work deepens understanding of KG-based knowledge selection in ICL and informs the design of more effective, targeted prompting strategies. This project's source code is publicly available at https://github.com/maryam-ghanbari/InformativenessOfKGs.

Multi-hop question answering (QA) requires a model to retrieve and integrate information from multiple passages to answer a question. Rapid progress has been made on multi-hop QA systems with regard to standard evaluation metrics, including EM and F1. However, by simply evaluating the correctness of the answers, it is unclear to what extent these systems have learned the ability to perform multi-hop reasoning. In this paper, we propose an additional sub-question evaluation for the multi-hop QA dataset HotpotQA, in order to shed some light on explaining the reasoning process of QA systems in answering complex questions. We adopt a neural decomposition model to generate sub-questions for a multi-hop question, followed by extracting the corresponding sub-answers. Contrary to our expectation, multiple state-of-the-art multi-hop QA models fail to answer a large portion of sub-questions, although the corresponding multi-hop questions are correctly answered. Our work takes a step forward towards building a more explainable multi-hop QA system.

We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. Unlike many neural ranking methods that use dense vector nearest neighbor search, SPARTA learns a sparse representation that can be efficiently implemented as an Inverted Index. The resulting representation enables scalable neural retrieval that does not require expensive approximate vector search and leads to better performance than its dense counterpart. We validated our approaches on 4 open-domain question answering (OpenQA) tasks and 11 retrieval question answering (ReQA) tasks. SPARTA achieves new state-of-the-art results across a variety of open-domain question answering tasks in both English and Chinese datasets, including open SQuAD, CMRC and etc. Analysis also confirms that the proposed method creates human interpretable representation and allows flexible control over the trade-off between performance and efficiency.

Retrieval-Augmented Generation (RAG) systems have shown significant potential for domain-specific Question Answering (QA) tasks, although persistent challenges in retrieval precision and context selection continue to hinder their effectiveness. This study introduces Document Graph RAG (GraphRAG), a novel framework that bolsters retrieval robustness and enhances answer generation by incorporating Knowledge Graphs (KGs) built upon a document’s intrinsic structure into the RAG pipeline. Through the application of the Design Science Research methodology, we systematically design, implement, and evaluate GraphRAG, leveraging graph-based document structuring and a keyword-based semantic linking mechanism to improve retrieval quality. The evaluation, conducted on well-established datasets including SQuAD, HotpotQA, and a newly developed manufacturing dataset, demonstrates consistent performance gains over a naive RAG baseline across both retrieval and generation metrics. The results indicate that GraphRAG improves Context Relevance metrics, with task-dependent optimizations for chunk size, keyword density, and top-k retrieval further enhancing performance. Notably, multi-hop questions benefit most from GraphRAG’s structured retrieval strategy, highlighting its advantages in complex reasoning tasks.

This paper introduces a general question answering (QA) framework for Chinese domain knowledge graphs to serve various industries. The question is analyzed by shielding invalid characters in this framework, and the TransE calculation of entities and relations is used to search answer, rather than traditional logical queries that rely heavily on predefined rules. In this way, the QA framework can be easily applied to different fields with little manual participation, and reduce the migration cost caused by the lack of scalability of the existing QA systems, which are designed only for specific domains. Then, the proposed framework is operated on the space launch knowledge graph and has achieved HITS@1, HITS@3, HITS@5 scores of 60.60%, 80.87%, 85.61% separately, which is competitive with other restricted domain knowledge graphs. In addition, numerical results on the knowledge graph of the Three Kingdoms and the COVID-19-Character verified the scalability of the QA framework.

Learning structured embeddings of knowledge graphs with generative adversarial framework

It is challenging to generate high quality answers for healthcare queries in online platforms. Recent studies proposed deep models for healthcare question answering (HQA) tasks. However, these models have not been thoroughly compared, and they were only tested on self-created datasets. This paper demonstrates a novel system, denoted by HQADeepHelper, to facilitate the learning and practicing of deep models for HQA. We have implemented a wide spectrum of state-of-the-art deep models for HQA retrieval. Users can upload self-collected HQA datasets and knowledge graphs, and do simple configurations by selecting datasets, knowledge graphs, neural network models, and evaluation metrics. Based on user’s configuration specified, the system can automatically train and test the model, conduct extensive experimental evaluation of the models selected, and report comprehensive findings. The reports provide new insights about the strengths and weaknesses of deep models that can guide practitioners to select appropriate models for various scenarios. Moreover, users can download the datasets, knowledge graphs, experimental reports and source codes of neural network models for their own practice and evaluations further.

Over the past decade, Knowledge Graphs (KG) have emerged as a prominent repository for storing facts about the world in a linked data architecture. Providing machines with the capability of exploring such Knowledge Graphs and answering natural language questions over them, has been an active area of research. The purpose of this work, is to delve further into the research of retrieving information stored in KGs, based on the natural language questions posed by the user. Knowledge Graph Question Answering (KGQA) aims to produce a concise answer to a user question, such that the user is exempt from using KG vocabulary and overheads of learning a formal query language. Existing KGQA systems have achieved excellent results over Simple Questions, where the information required is limited to a single triple and a single formal query pattern. Our motivation is to improve the performance of KGQA over Complex Questions, where formal query patterns significantly vary, and a single triple is not confining for all the required information. Complex KGQA provides several challenges such as understanding semantics and syntactic structure of questions, Entity Linking, Relation Linking and Answer Representation. Lack of suitable datasets for complex question answering further adds to research gaps. Hence, in this thesis, we focus the research objective of laying the foundations for the advancement of the state-of-the-art for Complex Question Answering over Knowledge Graphs, by providing techniques to solve various challenges and provide resources to fill the research gaps. First, we propose Normalized Query Structure (NQS), which is a linguistic analyzer module that helps the QA system to detect inputs and intents and the relation between them in the users' question. NQS acts like an intermediate language between natural language questions and formal expressions to ease the process of query formulation for complex questions. We then developed a framework named LC-QuAD to generate large scale question answering dataset by reversing the process of question answering, thereby translating natural language questions from the formal query using intermediate templates. Our goal is to use this framework for high variations in the query patterns and create a large size dataset with minimum human effort. The first version of the dataset consists of 5,000 complex questions. By extending the LC-QuAD framework to support Reified KGs and crowd-sourcing, we published the second version of the dataset as LC-QuAD 2.0, consisting of 30,000 questions with their paraphrases and has higher complexity and new variations in the questions. To overcome the problem of Entity Linking and Relation Linking in KGQA, we develop EARL, a module performing these two tasks as a single joint task for complex question answering. We develop approaches for this module, first by formalizing the task as an instance of the Generalized Traveling Salesman Problem (GTSP) and the second approach uses machine learning to exploit the connection density between nodes in the Knowledge Graph. Lastly, we create another large scale dataset to answer verbalization and provide results for multiple baseline system s on it. The Verbalization dataset is introduced to make the system's response more human-like. The NQS based KGQA system was next to the best system in terms of accuracy on the QALD-5 dataset. We empirically prove that NQS is robust to tackle paraphrases of the questions. EARL achieves the state of the art results in Entity Linking and Relation Linking for question answering on several KGQA datasets. The dataset curated in this thesis has helped the research community to move forward in the direction of improving the accuracy of complex question answering as a task as other researchers too developed several KGQA systems and modules around these published datasets. With the large-scale datasets, we have encouraged the use of large scale machine learning, deep learning and emergence of new techniques to advance the state-of-the-art in complex question answering over knowledge graphs. We further developed core components for the KGQA pipeline to overcome the challenges of Question Understanding, Entity-Relation Linking and Answer Verbalization and thus achieve our research objective. All the proposed approaches mentioned in this thesis and the published resources are available at https://github.com/AskNowQA and are released under the umbrella project AskNow.