Muhan Chen

Chenyu Lin, Yilin Wen, Du Su et al.

Retrieval-augmented generation (RAG) improves performance on knowledge-intensive tasks but can be derailed by wrong, irrelevant, or conflicting retrieved text, causing models to rely on inaccurate evidence and cascade errors. We propose Knowledgeable-R1, a reinforcement-learning framework that explicitly trains large language models to use parametric knowledge (PK) to resist contextual interference while still exploiting external context when it is reliably helpful. Knowledgeable-R1 introduces a joint sampling scheme that generates paired responses with and without retrieval, and learns both local advantages (within each decoding regime) and global advantages under the same input to quantify when to ignore misleading context versus adopt it. We employ an asymmetric advantage transformation that amplifies exploratory behaviors toward parametric knowledge. Experiments show that \method significantly improves robustness and reasoning accuracy in knowledge conflict scenarios and general RAG scenarios, outperforming SOTA baselines by 23% in counterfactual scenarios, and without degradation when the retrieved context is fully accurate.Our code are available at https://github.com/lcy80366872/knowledgeable-R1.

Muhan Chen, Jiajia Guo, Chao-Kai Wen et al.

Massive multiple-input multiple-output can obtain more performance gain by exploiting the downlink channel state information (CSI) at the base station (BS). Therefore, studying CSI feedback with limited communication resources in frequency-division duplexing systems is of great importance. Recently, deep learning (DL)-based CSI feedback has shown considerable potential. However, the existing DL-based explicit feedback schemes are difficult to deploy because current fifth-generation mobile communication protocols and systems are designed based on an implicit feedback mechanism. In this paper, we propose a DL-based implicit feedback architecture to inherit the low-overhead characteristic, which uses neural networks (NNs) to replace the precoding matrix indicator (PMI) encoding and decoding modules. By using environment information, the NNs can achieve a more refined mapping between the precoding matrix and the PMI compared with codebooks. The correlation between subbands is also used to further improve the feedback performance. Simulation results show that, for a single resource block (RB), the proposed architecture can save 25.0% and 40.0% of overhead compared with Type I codebook under two antenna configurations, respectively. For a wideband system with 52 RBs, overhead can be saved by 30.7% and 48.0% compared with Type II codebook when ignoring and considering extracting subband correlation, respectively.