11 papers
Learning Latent Reasoning Traces for Scalar Reward Models End-to-End
Sanwoo Lee, Clive Bai, Hsiu-Yuan Huang +3
Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs enable efficient and probabilis…
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…
Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error
Chenming Tang, Hsiu-Yuan Huang, Weijie Liu +3
Reinforcement learning with verifiable rewards (RLVR) has significantly boosted the reasoning capability of language models (LMs). However, existing RLVR approaches train LMs based…
Think Outside the Policy: In-Context Steered Policy Optimization
Hsiu-Yuan Huang, Chenming Tang, Weijie Liu +3
Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reason…
CFMS: Towards Explainable and Fine-Grained Chinese Multimodal Sarcasm Detection Benchmark
Junzhao Zhang, Hsiu-Yuan Huang, Chenming Tang +2
Multimodal sarcasm detection has recently garnered significant attention. However, existing benchmarks suffer from coarse-grained annotations and limited cultural coverage, which h…