Related papers: CHIME: Cross-passage Hierarchical Memory Network f…

A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even…

Recurrent Neural Networks (RNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering RNN-based approaches is improving their explainability and interpretability. In this work we present MEME: a model…

Using a Bayesian network to analyze the causal relationship between nodes is a hot spot. The existing network learning algorithms are mainly constraint-based and score-based network generation methods. The constraint-based method is mainly…

Automatic question generation (QG) serves a wide range of purposes, such as augmenting question-answering (QA) corpora, enhancing chatbot systems, and developing educational materials. Despite its importance, most existing datasets…

Domain-specific question answering (QA) systems for services face unique challenges in integrating heterogeneous knowledge sources while ensuring both accuracy and safety. Existing large language models often struggle with factual…

Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in long multimodal…

The vast majority of cybersecurity information is unstructured text, including critical data within databases such as CVE, NVD, CWE, CAPEC, and the MITRE ATT&CK Framework. These databases are invaluable for analyzing attack patterns and…

Question Answering (QA) systems have traditionally relied on structured text data, but the rapid growth of multimedia content (images, audio, video, and structured metadata) has introduced new challenges and opportunities for…

Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed…

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

In the field of code intelligence, effectively modeling long-range code poses a significant challenge. Existing pre-trained language models (PLMs) such as UniXcoder have achieved remarkable success, but they still face difficulties with…

Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to…

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable performance in long-term human-machine interactions, which basically relies on iterative recalling and reasoning of history to generate high-quality responses.…

Community question answering (CQA) gains increasing popularity in both academy and industry recently. However, the redundancy and lengthiness issues of crowdsourced answers limit the performance of answer selection and lead to reading…

This paper describes a novel hierarchical attention network for reading comprehension style question answering, which aims to answer questions for a given narrative paragraph. In the proposed method, attention and fusion are conducted…

Multi-hop question answering (QA) requires models to retrieve and reason over multiple pieces of evidence. While Retrieval-Augmented Generation (RAG) has made progress in this area, existing methods often suffer from two key limitations:…

Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage…

Existing long-horizon memory benchmarks mostly use multi-turn dialogues or synthetic user histories, which makes retrieval performance an imperfect proxy for person understanding. We present \BenchName, a publicly releasable benchmark built…

In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on exploring the memory content. Most research simply stores summarized versions of historical…

Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal,…