Ragtruth: A hallucination corpus for developing trustworthy retrieval-augmented language models
Retrieval-augmented generation (RAG) has become a main technique for alleviating
hallucinations in large language models (LLMs). Despite the integration of RAG, LLMs may still …
hallucinations in large language models (LLMs). Despite the integration of RAG, LLMs may still …
VeraCT scan: Retrieval-augmented fake news detection with justifiable reasoning
…, Y Guan, Y Wu, J Zhu, J Song, R Zhong, K Zhu… - arXiv preprint arXiv …, 2024 - arxiv.org
The proliferation of fake news poses a significant threat not only by disseminating misleading
information but also by undermining the very foundations of democracy. The recent …
information but also by undermining the very foundations of democracy. The recent …
RAG-HAT: A hallucination-aware tuning pipeline for LLM in retrieval-augmented generation
J Song, X Wang, J Zhu, Y Wu, X Cheng… - Proceedings of the …, 2024 - aclanthology.org
Retrieval-augmented generation (RAG) has emerged as a significant advancement in the
field of large language models (LLMs). By integrating up-to-date information not available …
field of large language models (LLMs). By integrating up-to-date information not available …
Simulation software of the JUNO experiment
… The JUNO experiment has the world’s largest liquid scintillator detector instrumented with
… This paper describes the JUNO simulation software, highlighting the challenges of JUNO …
… This paper describes the JUNO simulation software, highlighting the challenges of JUNO …
JUNO conceptual design report
T Adam, F An, G An, Q An, N Anfimov… - arXiv preprint arXiv …, 2015 - arxiv.org
… JUNO is also sensitive to new physics beyond the Standard Model, including sterile …
The energy resolution of JUNO is required to be 3% at 1MeV, corresponding to at least 1,100 …
The energy resolution of JUNO is required to be 3% at 1MeV, corresponding to at least 1,100 …
RAG-Reward: Optimizing RAG with Reward Modeling and RLHF
Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) with
relevant and up-to-date knowledge, improving their ability to answer knowledge-intensive …
relevant and up-to-date knowledge, improving their ability to answer knowledge-intensive …
Verification of the calibration method for the boundary effect in JUNO
K Zhu, Y Guo, Z Cai, Y Liu, F Zhang… - Journal of …, 2022 - iopscience.iop.org
… the JUNO is still under construction and the JUNO detector … JUNO simulation to estimate
systematic uncertainty in the Daya Bay benchmark measurement and future GTCS data in JUNO…
systematic uncertainty in the Daya Bay benchmark measurement and future GTCS data in JUNO…
JUNO: optimizing high-dimensional approximate nearest neighbour search with sparsity-aware algorithm and ray-tracing core mapping
… We present Juno, a fast and high-… Juno to support inner product similarity with no extra
dimensions as other works have, and efficient RT-Tensor core pipelining [57]. We evaluate Juno …
dimensions as other works have, and efficient RT-Tensor core pipelining [57]. We evaluate Juno …
A method of detector and event visualization with Unity in JUNO
… the Jiangmen Underground Neutrino Observatory (JUNO) experiment. The method has …
JUNO offline software but shares the same detector description and event data model in JUNO …
JUNO offline software but shares the same detector description and event data model in JUNO …
Prediction of energy resolution in the JUNO experiment
A Abusleme, T Adam, K Adamowicz, S Ahmad… - Chinese …, 2025 - iopscience.iop.org
This paper presents an energy resolution study of the JUNO experiment, incorporating the
latest knowledge acquired during the detector construction phase. The determination of …
latest knowledge acquired during the detector construction phase. The determination of …