Research on Multi-hop Q/A

Integrated system for managing, querying, and generating responses related to interconnected data using a graph database, specialized loaders, natural language reasoning, and a multi-modal user interface. The system ingests structured, unstructured, and time-series data from diverse sources, transforms it into a unified graph representation, and enables sophisticated reasoning tasks across modalities. It provides a secure, scalable, and interoperable solution for integrating, analyzing, visualizing, and reasoning over heterogeneous data at scale.

Source

Graph-based natural language processing system for querying, analyzing, and visualizing complex data structures using AI language models. The system trains an AI language model on input data from original sources using a training algorithm with extraction and condensing steps. It extracts data from sources, loads it into a graph database, transforms into a condensed natural language format, trains on graph structure, and responds to natural language questions.

Source

This paper presents a novel Retrieval-AugmentedGeneration (RAG) framework tailored for complex questionanswering tasks, addressing challenges in multi-hop reasoningand contextual understanding across lengthy documents. Builtupon LLaMA 3, the integrates dense retrievalmodule with advanced context fusion and reasoningmechanisms, enabling more accurate coherent responsegeneration. A joint optimization strategy combining retrievallikelihood generation cross-entropy improves modelsrobustness adaptability. Experimental results show that theproposed system outperforms existing retrieval-augmented andgenerative baselines, confirming its effectiveness deliveringprecise, contextually grounded answers.

Source

Generative, graph-enhanced information retrieval approaches for cluttered datasets that enable more accurate and explainable search results for complex questions. The approach uses graph representation of documents with nodes representing entities and edges connecting relationships. Embedding-based retrieval finds relevant nodes, then graph-based retrieval extracts a path connecting them. This path is fed to a generative AI model to generate a customized response. It improves over embedding-only retrieval for complex queries by connecting dispersed information and explaining how it was assembled.

Source

A method for improving question answering (QA) accuracy across different structured databases like knowledge graphs and tables by training a unified QA model. The model is trained on samples with questions, database type, and query instructions. It learns to generate query instructions from questions and database types. This allows the model to understand and query multiple structured databases instead of degenerating to unstructured text QA.

Source

Multi-Hop Knowledge Graph Question Answering (multi-hop KGQA) aims to obtain answers by analyzing the semantics of natural language questions and performing multi-step reasoning across multiple entities relations in knowledge graphs. Traditional embedding-based methods map graphs into vector spaces for answer matching through operations. While these approaches have improved model performance, they face two critical challenges: lack clear interpretability caused implicit mechanisms, semantic gap between queries structured representations. This study proposes DRKG (Decomposed Reasoning over Graph), a constrained multi-hop framework based on large models (LLMs) that introduces explicit plans as logical boundary controllers. The innovation lies key aspects: First, generates hop-constrained parsing LLMs, explicitly defining traversal path length entity-retrieval logic Second, conducts selective retrieval during graph plans, ensuring faithfulness knowledge. We evaluate four datasets, experimental results demonstrate achieves 1%5% accuracy improvements best baseline models. Additional ab... Read More

Source

Using large language models to answer table question-answering tasks while preserving data security and privacy by having the model generate code to access the table instead of directly seeing the table data. The model, called the Solver, receives a user query and generates code based on instructions and schema provided by an Oracle. The Oracle evaluates the code and may ask follow-up questions. This allows the model to answer questions without exposing the underlying table data. If the answer is incorrect, the Oracle provides guidance to help the model improve. The game-like interaction between the Solver and Oracle allows the model to learn tabular reasoning while protecting the table data.

Source

Training natural language processing (NLP) models using knowledge graphs to improve their performance. The method involves processing a text sample based on triples extracted from the knowledge graph. This fused knowledge representation is used to train the NLP model. The triples contain entity and relation information in addition to the text. The fused knowledge vector contains features like entity meanings and relation contexts not present in the original text. This improves NLP model accuracy compared to just the text input.

Source

Question answering (QA) system based on a complex reasoning pipeline to improve performance on complex questions like bridge-type multi-hop QA. The system recognizes the reasoning type of an input question, decomposes it into sub-questions, and performs optimized reasoning pipelines for each type. The pipelines involve separate modules for question restructuring, search, and document reading. This allows customized reasoning for different question types instead of relying on a single large language model.

Source

Unsupervised multi-hop search for finding relationships between entities in a document corpus. The search involves iteratively finding intermediate entities that connect the initial entities. It uses graph search techniques like A* and beam search to efficiently find relationships through multiple hops. The search starts with a user-selected pair of entities, finds documents containing both, then searches for an intermediary entity in those documents. If too few documents are found, it repeats with more intermediate entities. By selectively expanding promising paths, it avoids exponential complexity.

Source

This paper addresses key challenges in knowledge injection for large language models, including static representation, difficulty updating, and limited domain adaptability. It proposes a dynamic fine-tuning framework designed injection. The is based on parameter-efficient tuning strategies introduces learnable adapter modules gating mechanisms. These components enable selective integration control of both structured unstructured external knowledge. In the model design, query encoder extracts semantic vectors from input text. are matched with an base to construct subset. subset guides task generation. Adapter units then applied across layers adjust enhancement. ensures that contributes reasoning while preserving model's original capabilities. A unified joint loss function also introduced. coordinates optimization between modeling alignment objectives. To evaluate proposed method, WikiHop dataset multi-hop question answering used. behavior analyzed under various experimental settings, different parameter update ratios, densities, cross-domain transfer scenarios. results show method ach... Read More

Source

Large Language Models (LLMs) often tend to hallucinate, especially on domain-specific tasks and that require reasoning. Previously, we introduced SubGraph Retrieval Augmented Generation (SG-RAG) as a novel GraphRAG method for multi-hop question answering. SG-RAG leverages Cypher queries search the given knowledge graph retrieve necessary subgraph answer question. The results from our previous work showed higher performance of compared traditional (RAG). In this work, further enhance by proposing an additional step called Merging Ordering Triplets (MOT). new MOT seeks decrease redundancy in retrieved triplets applying hierarchical merging subgraphs. Moreover, it provides ordering among using Breadth First Search (BFS) traversal algorithm. We conducted experiments MetaQA benchmark, which is proposed question-answering movies domain. Our show more accurate answers than Chain-of-Though Graph Chain-of-Though. also find out (up some point) highly overlapping subgraphs defining order helps LLM generate precise answers.

Source

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 robustness enhances answer generation by incorporating Knowledge Graphs (KGs) built upon documents intrinsic structure into the pipeline. Through application of Design Science Research methodology, we systematically design, implement, evaluate GraphRAG, leveraging graph-based document structuring keyword-based semantic linking mechanism improve quality. The evaluation, conducted on well-established datasets including SQuAD, HotpotQA, newly developed manufacturing dataset, demonstrates consistent performance gains over naive baseline across both metrics. results indicate GraphRAG improves Context Relevance metrics, with task-dependent optimizations chunk size, keyword density, top-k further enhancing performance. Notably, multi-hop questions benefit most fro... Read More

Source

A system that uses generative AI to intelligently query heterogeneous data sources to answer natural language questions. The system breaks down complex questions into simpler sub-questions and uses AI to identify the appropriate data source for each sub-question. It then generates custom queries for each data source and executes them to gather the necessary information. The AI summarizes the results and returns a coherent response to the original question. The AI avoids sharing or training on the actual data, preserving privacy while leveraging AI's query generation and data source selection abilities.

Source

Using a retrieval system in conjunction with large language models (LLMs) to improve accuracy and reduce the need for re-training when underlying information changes. The system retrieves relevant documents based on a user's query using a retriever. These documents are then combined with the original query to form a prompt for the LLM. The LLM generates an output using this augmented prompt that incorporates the retrieved documents' information. This provides a more accurate response compared to just using the LLM alone, especially for complex domains where the LLM may lack specific knowledge.

Source

Creating a dynamic workflow data structure that can tailor responses to specific user queries and contexts. The method involves using a large language model (LLM) to process a corpus of documents, classify user queries based on context, construct a workflow structure from the classified segments, and generate personalized responses. The LLM segments the documents, analyzes the segments' semantics, and organizes them into a workflow structure. This structure is then used to generate customized responses for user queries based on the segment classification and query context.

Source

Using knowledge graphs and vector searches to improve the efficiency and accuracy of AI question answering systems. The method involves decomposing user queries into tasks, searching a knowledge graph to identify relevant entities, searching a vector database using the entities to find text chunks, and using an LLM to generate answers based on the identified text. This refined search scope improves the LLM's efficiency and accuracy compared to searching large text databases directly.

Source

Automatically generating context-based responses to natural language queries using knowledge graphs in combination with artificial intelligence techniques. The system generates queries in a predetermined query language from natural language inputs, processes them using enterprise knowledge graphs and AI models, and combines the results to provide more accurate and comprehensive responses. This allows users without technical knowledge to search and query knowledge graphs using natural language and make decisions based on the responses.

Source

Multi-Hop Question Answering over Knowledge Graphs (MHQA-KG) plays a pivotal role in various applications, including but not limited to Question Answering, Recommendation Systems, and Semantic Search. Nevertheless, current models for MHQA have limitations in their ability to grasp all the information included in the question, resulting a reduction in accuracy when producing answers. In order to mitigate this limitation, this paper proposes a novel Multi-Hop Question Answering over Knowledge Graphs approach. It mainly utilizes question and path embedding to answer multi-hop questions, significantly improving accuracy. This approach effectively captures auxiliary information that may present in the question. The experimental findings provide evidence that the suggested methodology outperforms the current state-of-the-art models, achieving highly accurate outcomes with improvements.

Source

Large language models (LLMs) have recently demonstrated remarkable performance across various Natual Language Processing tasks. In the field of multi-hop reasoning, the Chain-of-thought (CoT) prompt method has emerged as a paradigm, using curated stepwise reasoning demonstrations to enhance LLM's ability to reason and produce coherent rational pathways. To ensure the accuracy, reliability, and traceability of the generated answers, many studies have incorporated information retrieval (IR) to provide LLMs with external knowledge. However, existing CoT with IR methods decomposes questions into sub-questions based on a single compositionality type, which limits their effectiveness for questions involving multiple compositionality types. Additionally, these methods suffer from inefficient retrieval, as complex questions often contain abundant information, leading to the retrieval of irrelevant information inconsistent with the query's intent. In this work, we propose a novel question decomposition framework called TRQA for multi-hop question answering, which addresses these limitations. ... Read More

Source