activity
20242026
collaborators

13 papers

cs.CL2026

From Refuse to Richness: Rubric Rewards for Long-Form Hallucination Reinforcement Learning

Yudong Wang, Zhe Yang, Wenhan Ma +6

Rewards that penalize unsupported claims can improve grounding in long-form generation, but they can also teach models to answer less. We study this refusal-to-richness trade-off i…

cs.CL2026

MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training

Wenhan Ma, Jianyu Wei, Liang Zhao +10

Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains…

cs.CV2026

GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation

Rang Li, Lei Li, Shuhuai Ren +10

Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language mod…

cs.CL2026

Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity

Di Zhang, Xun Wu, Shaohan Huang +9

Semi-structured N:M sparsity and low-bit quantization (e.g., 1.58-bit BitNet) are two promising approaches for improving the efficiency of large language models (LLMs), yet they ha…

cs.CL2026

Towards Better RL Training Data Utilization via Second-Order Rollout

Zhe Yang, Yudong Wang, Rang Li +1

Reinforcement Learning (RL) has empowered Large Language Models (LLMs) with strong reasoning capabilities, but vanilla RL mainly focuses on generation capability improvement by tra…

cs.CL2025

Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning

Yudong Wang, Zhe Yang, Wenhan Ma +2

While reinforcement learning has unlocked unprecedented complex reasoning in large language models, it has also amplified their propensity for hallucination, creating a critical tr…