9 papers · 1 filter
Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
Qingyu Ren, Qianyu He, Powei Chang +5
Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dep…
Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts
Xinyi Wang, Jinyi Han, Zishang Jiang +7
Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods…
Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
Zishang Jiang, Jinyi Han, Tingyun Li +7
Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Models (LLMs). However, the effect…
Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
Jinyi Han, Ying Huang, Ying Liao +11
Large Reasoning Models (LRMs) have achieved impressive performance on challenging tasks, yet their deep reasoning often incurs substantial computational costs. To achieve efficient…
Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following
Qingyu Ren, Qianyu He, Bowei Zhang +6
Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for imp…
A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
Jinyi Han, Xinyi Wang, Haiquan Zhao +9
Recent advances in self-refinement have demonstrated significant potential for improving the outputs of large language models (LLMs) through iterative refinement. However, most exi…
Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following
Jie Zeng, Qianyu He, Qingyu Ren +5
Real-world instructions with multiple constraints pose a significant challenge to existing large language models (LLMs). An observation is that the LLMs exhibit dramatic performanc…
Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation
Qianxi He, Qianyu He, Jiaqing Liang +4
Logical reasoning is essential for large language models (LLMs) to ensure accurate and coherent inference. However, LLMs struggle with reasoning order variations and fail to genera…
Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models
Qingyu Ren, Jie Zeng, Qianyu He +5
It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints. However, it is an unexplored area to enhance LLMs' ability to follow soft c…