1 citations · 1 across the 5 of their papers we have counts for
5 papers
Writer-R1: Dynamic Rubric Mining for Reinforcement Learning of Open-Ended Writing
Jihao Zhao, Shuaishuai Zu, Zhiyuan Ji +2
Training models for open-ended writing requires diverse prompts and sufficiently precise specifications of response quality. Constructing such specifications at scale entails recov…
MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems
Jihao Zhao, Zhiyuan Ji, Simin Niu +3
The traditional RAG paradigm, which typically engages in the comprehension of relevant text chunks in response to received queries, inherently restricts both the depth of knowledge…
Beyond the Pre-Service Horizon: Infusing In-Service Behavior for Improved Financial Risk Forecasting
Senhao Liu, Zhiyu Guo, Zhiyuan Ji +5
Typical financial risk management involves distinct phases for pre-service risk assessment and in-service default detection, often modeled separately. This paper proposes a novel f…
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System
Jihao Zhao, Zhiyuan Ji, Zhaoxin Fan +5
Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline.…
Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception
Jihao Zhao, Zhiyuan Ji, Yuchen Feng +5
While Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for boosting large language models (LLMs) in knowledge-intensive tasks, it often overlooks the crucia…