Related papers: Neural Path Hunter: Reducing Hallucination in Dial…

While neural networks have been used extensively to make substantial progress in the machine translation task, they are known for being heavily dependent on the availability of large amounts of training data. Recent efforts have tried to…

Large language models (LLMs) often struggle with knowledge-intensive tasks due to a lack of background knowledge and a tendency to hallucinate. To address these limitations, integrating knowledge graphs (KGs) with LLMs has been intensively…

Conventional Retrieval Augmented Generation (RAG) approaches are common in text-based applications. However, they struggle with structured, interconnected datasets like knowledge graphs, where understanding underlying relationships is…

Large language models (LLMs) demonstrate exceptional capabilities, yet still face the hallucination issue. Typical text generation approaches adopt an auto-regressive generation without deliberate reasoning, which often results in…

Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…

Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or domain-specific knowledge. Nonetheless, current models still produce closed-domain…

Multi-hop question answering is a challenging task in which language models must reason over multiple steps to reach the correct answer. With the help of Large Language Models and their reasoning capabilities, existing systems are able to…

Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions. However, the sparse reward signals offered by the KG during traversal are often…

Graph-based retrieval-augmented generation (RAG) methods, typically built on knowledge graphs (KGs) with binary relational facts, have shown promise in multi-hop open-domain QA. However, their rigid retrieval schemes and dense similarity…

A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. While large language models (LLM) have taken the world by storm, without eliminating or at least reducing hallucinations, real-world GenAI…

Large Language Models (LLMs) often generate incorrect or unsupported content, known as hallucinations. Existing detection methods rely on heuristics or simple models over isolated computational traces such as activations, or attention maps.…

Knowledge graph-based retrieval-augmented generation seeks to mitigate hallucinations in Large Language Models (LLMs) caused by insufficient or outdated knowledge. However, existing methods often fail to fully exploit the prior knowledge…

Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reasoning tasks: low context utilization and frequent…

Human smuggling networks are increasingly adaptive and difficult to analyze. Legal case documents offer valuable insights but are unstructured, lexically dense, and filled with ambiguous or shifting references-posing challenges for…

"The greatest enemy of knowledge is not ignorance, it is the illusion of knowledge." Large Language Models have conquered natural language but remain prisoners of their own probabilistic nature--confidently hallucinating facts they never…

Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health…

The rapid advancement of large language models (LLMs) has significantly impacted various domains, including healthcare and biomedicine. However, the phenomenon of hallucination, where LLMs generate outputs that deviate from factual accuracy…

Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommender systems. In recent years,…

Recent advancements in large language models (LLMs) have shown impressive versatility across various tasks. To eliminate their hallucinations, retrieval-augmented generation (RAG) has emerged as a powerful approach, leveraging external…

Answering open-domain questions requires world knowledge about in-context entities. As pre-trained Language Models (LMs) lack the power to store all required knowledge, external knowledge sources, such as knowledge graphs, are often used to…