相关论文: Towards Robust Reasoning over Knowledge Graphs

Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in…

Graph walking based on reinforcement learning (RL) has shown great success in navigating an agent to automatically complete various reasoning tasks over an incomplete knowledge graph (KG) by exploring multi-hop relational paths. However,…

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be…

Knowledge Graph Representation Learning (KGRL), or Knowledge Graph Embedding (KGE), is essential for AI applications such as knowledge construction and information retrieval. These models encode entities and relations into lower-dimensional…

Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents, but also opens up new attack surfaces. We study knowledge-base poisoning attacks in RAG, where an attacker injects…

Recent deep reinforcement learning (DRL) successes rely on end-to-end learning from fixed-size observational inputs (e.g. image, state-variables). However, many challenging and interesting problems in decision making involve observations or…

Knowledge-enhanced pre-trained language models (KEPLMs) leverage relation triples from knowledge graphs (KGs) and integrate these external data sources into language models via self-supervised learning. Previous works treat knowledge…

Deep learning models are increasingly deployed in real-world applications. These models are often deployed on the server-side and receive user data in an information-rich representation to solve a specific task, such as image…

Integrating causal inference (CI) with reinforcement learning (RL) has emerged as a powerful paradigm to address critical limitations in classical RL, including low explainability, lack of robustness and generalization failures. Traditional…

Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current…

Knowledge-Intensive Visual Grounding (KVG) requires models to localize objects using fine-grained, domain-specific entity names rather than generic referring expressions. Although Multimodal Large Language Models (MLLMs) possess rich entity…

Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves…

Knowledge graph (KG) is known to be helpful for the task of question answering (QA), since it provides well-structured relational information between entities, and allows one to further infer indirect facts. However, it is challenging to…

Retrieval-augmented generation (RAG) enables large language models (LLMs) to dynamically access external information, which is powerful for answering questions over previously unseen documents. Nonetheless, they struggle with high-level…

Retrieval-Augmented Generation (RAG) was introduced to enhance the capabilities of Large Language Models (LLMs) beyond their encoded prior knowledge. This is achieved by providing LLMs with an external source of knowledge, which helps…

Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy. While recent works equip reinforcement learning (RL)-based LRMs with retrieval capabilities, they…

Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the environment. However, datasets collected by humans in…

Large Language Models (LLMs) excel at intuitive, implicit reasoning. Guiding LLMs to construct thought chains can enhance their deliberate reasoning abilities, but also faces challenges such as hallucination. Knowledge Graphs (KGs) can…

Reinforcement learning (RL) is one of the most practical ways to learn from real-life use-cases. Motivated from the cognitive methods used by humans makes it a widely acceptable strategy in the field of artificial intelligence. Most of the…

The need for machine unlearning is critical for data privacy, yet existing methods often cause Knowledge Contamination by unintentionally damaging related knowledge. Such a degraded model performance after unlearning has been recently…