11 papers
Select-And-Extract: A Lightweight Plugin for Retrieval-Augmented Generation
Chenming Tang, Jiawei Han
Retrieval-augmented generation (RAG) for language model (LM) systems fundamentally has two failure modes: retrieval failure and reading failure. The former fails to recall the righ…
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
Kun Liang, Chenming Tang, Clive Bai +3
On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties ev…
RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data
Hsiu-Yuan Huang, Weijie Liu, Chenming Tang +5
The proliferation of Reinforcement Learning from Verifiable Rewards (RLVR) datasets has exacerbated provenance collapse due to unclear lineage among existing datasets. To bridge th…
Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
Chenming Tang, Hsiu-Yuan Huang, Weijie Liu +3
Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments. Existing approaches either r…
Aligning Language Models with Real-time Knowledge Editing
Chenming Tang, Yutong Yang, Kexue Wang +1
Knowledge editing aims to modify outdated knowledge in language models efficiently while retaining their original capabilities. Mainstream datasets for knowledge editing are predom…
ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
Kun Liang, Clive Bai, Xin Xu +5
Recent Large Reasoning Models (LRMs) achieve strong performance by leveraging long-form Chain-of-Thought (CoT) reasoning, but uniformly applying overlong reasoning at inference tim…