Related papers: Uncertainty Guided Global Memory Improves Multi-Ho…

Multi-hop question answering (MHQA) enables accurate answers to complex queries by retrieving and reasoning over evidence dispersed across multiple documents. Existing MHQA approaches mainly rely on iterative retrieval-augmented generation,…

To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must. Existing multi-modal VQA models achieve promising…

Multi-hop question answering (MHQA) involves reasoning across multiple documents to answer complex questions. Dense retrievers typically outperform sparse methods like BM25 by leveraging semantic embeddings; however, they require labeled…

The Attention module finds common usage in language modeling, presenting distinct challenges within the broader scope of Natural Language Processing. Multi-Head Attention (MHA) employs an absolute positional encoding, which imposes…

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…

Multimodal reasoning has emerged as a powerful framework for enhancing reasoning capabilities of reasoning models. While multi-turn table reasoning methods have improved reasoning accuracy through tool use and reward modeling, they rely on…

Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its…

Transformer models have achieved promising results on natural language processing (NLP) tasks including extractive question answering (QA). Common Transformer encoders used in NLP tasks process the hidden states of all input tokens in the…

Recent research has explored the memorization capacity of multi-head attention, but these findings are constrained by unrealistic limitations on the context size. We present a novel proof for language-based Transformers that extends the…

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from…

Effective multi-hop question answering (QA) requires reasoning over multiple scattered paragraphs and providing explanations for answers. Most existing approaches cannot provide an interpretable reasoning process to illustrate how these…

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Multimodal multihop question answering (MMQA) requires reasoning over images and text from multiple sources. Despite advances in visual question answering, this multihop setting remains underexplored due to a lack of quality datasets.…

This study investigates an explainable reasoning method for financial decision-making based on knowledge-enhanced large language model agents. To address the limitations of traditional financial decision methods that rely on parameterized…

The primary focus of recent work with largescale transformers has been on optimizing the amount of information packed into the model's parameters. In this work, we ask a different question: Can multimodal transformers leverage explicit…

How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks are usually a great choice and a promising way. However,…

Recent advances in multimodal question answering have primarily focused on combining heterogeneous modalities or fine-tuning multimodal large language models. While these approaches have shown strong performance, they often rely on a…

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…

Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which…

Understanding complex biomolecular mechanisms requires multi-step reasoning across molecular interactions, signaling cascades, and metabolic pathways. While large language models(LLMs) show promise in such tasks, their application to…