Relevance Feedback with Brain Signals

Z Ye, X Xie, Q Ai, Y Liu, Z Wang, W Su… - ACM Transactions on …, 2024 - dl.acm.org
The Relevance Feedback (RF) process relies on accurate and real-time relevance
estimation of feedback documents to improve retrieval performance. Since collecting explicit …

Mitigating entity-level hallucination in large language models

W Su, Y Tang, Q Ai, C Wang, Z Wu, Y Liu - Proceedings of the 2024 …, 2024 - dl.acm.org
The emergence of Large Language Models (LLMs) has revolutionized how users access
information, shifting from traditional search engines to direct question-and-answer …

Unsupervised real-time hallucination detection based on the internal states of large language models

W Su, C Wang, Q Ai, Y Hu, Z Wu, Y Zhou… - arXiv preprint arXiv …, 2024 - arxiv.org
Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs
producing responses that are coherent yet factually inaccurate. This issue undermines the …

Dragin: Dynamic retrieval augmented generation based on the real-time information needs of large language models

W Su, Y Tang, Q Ai, Z Wu, Y Liu - arXiv preprint arXiv:2403.10081, 2024 - arxiv.org
Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what
to retrieve during the text generation process of Large Language Models (LLMs). There are …

Why Don't You Click: Understanding Non-Click Results in Web Search with Brain Signals

Z Ye, X Xie, Y Liu, Z Wang, X Li, J Li, X Chen… - Proceedings of the 45th …, 2022 - dl.acm.org
Web search heavily relies on click-through behavior as an essential feedback signal for
performance evaluation and improvement. Traditionally, click is usually treated as a positive …

Understanding User Immersion in Online Short Video Interaction

Z He, S Zhang, P Sun, J Li, X Xie, M Zhang… - Proceedings of the 32nd …, 2023 - dl.acm.org
Short video~(SV) online streaming has been one of the most popular Internet applications in
recent years. When browsing SVs, users gradually immerse themselves and derive …

Brain topography adaptive network for satisfaction modeling in interactive information access system

Z Ye, X Xie, Y Liu, Z Wang, X Chen, M Zhang… - Proceedings of the 30th …, 2022 - dl.acm.org
With the growth of information on the Web, most users heavily rely on information access
systems (eg, search engines, recommender systems, etc.) in their daily lives. During this …

Towards a better understanding of human reading comprehension with brain signals

Z Ye, X Xie, Y Liu, Z Wang, X Chen, M Zhang… - Proceedings of the ACM …, 2022 - dl.acm.org
Reading comprehension is a complex cognitive process involving many human brain
activities. However, little is known about what happens in human brain during reading …

STARD: A Chinese Statute Retrieval Dataset Derived from Real-life Queries by Non-professionals

W Su, Y Hu, A Xie, Q Ai, Q Bing, N Zheng… - Findings of the …, 2024 - aclanthology.org
Statute retrieval aims to find relevant statutory articles for specific queries. This process is the
basis of a wide range of legal applications such as legal advice, automated judicial …

Query augmentation by decoding semantics from brain signals

Z Ye, J Zhan, Q Ai, Y Liu, M de Rijke, C Lioma… - arXiv preprint arXiv …, 2024 - arxiv.org
Query augmentation is a crucial technique for refining semantically imprecise queries.
Traditionally, query augmentation relies on extracting information from initially retrieved …