alphaFeedback
YD

Yijiang River Dong

cs.CLcs.AIcs.CYcs.CRcs.LG

On Valency

published · living versions
W_dm5xu66x·v1 · currentpublished
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
with Zexue He, Cheng Yu, Tiancheng Hu, Michael J Ryan +7
1 version

Preprints & journals

11 papers in the corpus · 2022–2026
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use2610.31272v1 · Yijiang River Dong, Zexue He, Cheng Yu et al.2026 · 0 citationsarXivon Valency
Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding2601.06403v1 · Yijiang River Dong, Tiancheng Hu, Zheng Hui et al.2026 · 0 citationsarXiv
Value of Information: A Framework for Human-Agent Communication2601.06407v1 · Yijiang River Dong, Tiancheng Hu, Zheng Hui et al.2026 · 0 citationsarXiv
Confidence Estimation for LLMs in Multi-turn Interactions2601.02179v2 · Caiqi Zhang, Ruihan Yang, Xiaochen Zhu et al.2026 · 0 citationsarXiv
Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning2510.16054v2 · Zheng Hui, Yijiang River Dong, Sanhanat Sivapiromrat et al.2025 · 1 citationarXiv
TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law2507.21134v2 · Zheng Hui, Yijiang River Dong, Ehsan Shareghi et al.2025 · 0 citationsarXiv
When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning2502.19158v2 · Yijiang River Dong, Tiancheng Hu, Yinhong Liu et al.2025 · 0 citationsarXiv
Can LLM be a Personalized Judge?2406.11657v1 · Yijiang River Dong, Tiancheng Hu, Nigel Collier2024 · 24 citationsarXiv
UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models2402.10052v2 · Yijiang River Dong, Hongzhou Lin, Mikhail Belkin et al.2024 · 7 citationsarXiv
CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding2212.10754v3 · Yijiang River Dong, Lara J. Martin, Chris Callison-Burch2022 · 1 citationFindings of ACL 2023, pp. 13152-13168
Informative Text Generation from Knowledge Triples2209.12733v1 · Zihao Fu, Yijiang River Dong, Lidong Bing et al.2022 · 0 citationsarXiv
Career total: 11 works. 11 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.