Related papers: Look before you Hop: Conversational Question Answe…
Knowledge models are fundamental to dialogue systems for enabling conversational interactions, which require handling domain-specific knowledge. Ensuring effective communication in information-providing conversations entails aligning user…
Multi-hop question answering (QA) necessitates multi-step reasoning and retrieval across interconnected subjects, attributes, and relations. Existing retrieval-augmented generation (RAG) methods struggle to capture these structural…
While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques. Open Information Extraction (Open…
Understanding novel situations in the traffic domain requires an intricate combination of domain-specific and causal commonsense knowledge. Prior work has provided sufficient perception-based modalities for traffic monitoring, in this…
Commonsense question answering has demonstrated considerable potential across various applications like assistants and social robots. Although fully fine-tuned pre-trained Language Models(LM) have achieved remarkable performance in…
Representation learning for knowledge graphs (KGs) has focused on the problem of answering simple link prediction queries. In this work we address the more ambitious challenge of predicting the answers of conjunctive queries with multiple…
Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship. However, data scarcity makes it challenging for language models to learn to…
Assistive systems for visually impaired individuals must deliver rapid, interpretable, and adaptive feedback to facilitate real-time navigation. Current approaches face a trade-off between latency and semantic richness: natural…
In this paper, we are interested in developing semantic parsers which understand natural language questions embedded in a conversation with a user and ground them to formal queries over definitions in a general purpose knowledge graph (KG)…
While there has been substantial progress in text comprehension through simple factoid question answering, more holistic comprehension of a discourse still presents a major challenge (Dunietz et al., 2020). Someone critically reflecting on…
Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combining evidence from…
Recent generative approaches for multi-hop question answering (QA) utilize the fusion-in-decoder method~\cite{izacard-grave-2021-leveraging} to generate a single sequence output which includes both a final answer and a reasoning path taken…
Paragraph-style image captions describe diverse aspects of an image as opposed to the more common single-sentence captions that only provide an abstract description of the image. These paragraph captions can hence contain substantial…
Visual Question Answering (VQA) is of tremendous interest to the research community with important applications such as aiding visually impaired users and image-based search. In this work, we explore the use of scene graphs for solving the…
In this work, we benchmark various graph-based retrieval-augmented generation (RAG) systems across a broad spectrum of query types, including OLTP-style (fact-based) and OLAP-style (thematic) queries, to address the complex demands of…
Multi-hop reasoning question answering requires deep comprehension of relationships between various documents and queries. We propose a Bi-directional Attention Entity Graph Convolutional Network (BAG), leveraging relationships between…
When answering a question, people often draw upon their rich world knowledge in addition to the particular context. Recent work has focused primarily on answering questions given some relevant document or context, and required very little…
Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill user instructions. Existing approaches, such as…
Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, prevalent in domains…
Knowledge graph simple question answering (KGSQA), in its standard form, does not take into account that human-curated question answering training data only cover a small subset of the relations that exist in a Knowledge Graph (KG), or even…