Large language models (LLMs) have demonstrated strong capabilities in various aspects.
However, when applying them to the highly specialized, safe-critical legal domain, it is …

Question answering over RDF data like knowledge graphs has been greatly advanced, with
a number of good systems providing crisp answers for natural language questions or …

In conversational question answering, users express their information needs through a
series of utterances with incomplete context. Typical ConvQA methods rely on a single …

Product question answering (PQA), aiming to automatically provide instant responses to
customer's questions in E-Commerce platforms, has drawn increasing attention in recent …

Large Language Models (LLMs) have exhibited impressive generation capabilities, but they
suffer from hallucinations when solely relying on their internal knowledge, especially when …

Fact-centric question answering (QA) often requires access to multiple, heterogeneous,
information sources. By jointly considering several sources like a knowledge base (KB), a …

Models for conversational question answering (ConvQA) over knowledge graphs (KGs) are
usually trained and tested on benchmarks of gold QA pairs. This implies that training is …

Neural ranking (NR) has become a key component for open-domain question-answering in
order to access external knowledge. However, training a good NR model requires …

Retrieval-augmented generation has gained popularity as a framework to enhance large
language models with external knowledge. However, its effectiveness hinges on the …

Abstract Product Question Answering (PQA) systems are key in e-commerce applications as
they provide responses to customers' questions as they shop for products. While existing …