8 papers
LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models
Qingyu Ren, Qianyu He, Jingwen Chang +9
Instruction following is critical for large language models, yet real-world instructions often involve multiple constraints with logical structures, such as parallel composition, s…
SEIF: Self-Evolving Reinforcement Learning for Instruction Following
Qingyu Ren, Qianyu He, Jiajie Zhu +7
Instruction following is a fundamental capability of large language models (LLMs), yet continuously improving this capability remains challenging. Existing methods typically rely e…
From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks
Qingyu Ren, Tianjun Pan, Xingzhou Chen +1
Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, existing benchmarks evaluate wr…
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…
Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning
Qianxi He, Qingyu Ren, Shanzhe Lei +2
Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement…
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…