170 citations · 981 across the 54 of their papers we have counts for
7 papers · 1 filter
Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions
Zahra Abbasiantaeb, Yifei Yuan, Evangelos Kanoulas +1
Conversational question-answering (CQA) systems aim to create interactive search systems that effectively retrieve information by interacting with users. To replicate human-to-huma…
Data Augmentation for Conversational AI
Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi
Advancements in conversational systems have revolutionized information access, surpassing the limitations of single queries. However, developing dialogue systems requires a large a…
Stress Testing BERT Anaphora Resolution Models for Reaction Extraction in Chemical Patents
Chieling Yueh, Evangelos Kanoulas, Bruno Martins +2
The high volume of published chemical patents and the importance of a timely acquisition of their information gives rise to automating information extraction from chemical patents.…
MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering
Vaishali Pal, Andrew Yates, Evangelos Kanoulas +1
Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table. However, real-world q…
Generating Synthetic Documents for Cross-Encoder Re-Rankers: A Comparative Study of ChatGPT and Human Experts
Arian Askari, Mohammad Aliannejadi, Evangelos Kanoulas +1
We investigate the usefulness of generative Large Language Models (LLMs) in generating training data for cross-encoder re-rankers in a novel direction: generating synthetic documen…
Perspectives on Large Language Models for Relevance Judgment
Guglielmo Faggioli, Laura Dietz, Charles Clarke +8
When asked, large language models (LLMs) like ChatGPT claim that they can assist with relevance judgments but it is not clear whether automated judgments can reliably be used in ev…