Papers by Qiming Ge
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law (2025.acl-long)
Copied to clipboard
Qiming Ge, Shuhao Xing, Songyang Gao, Yunhua Zhou, Yicheng Zou, Songyang Zhang, Zhi Chen, Hang Yan, Qi Zhang, Qipeng Guo, Kai Chen
| Challenge: | Large language models have demonstrated impressive performance across a wide range of tasks, but this achievement comes with the trade-off of significant computational demands. |
| Approach: | They propose a scaling law that decomposes the overall validation loss and assigns different importance weights to tokens to assess a specific meta-capability. |
| Outcome: | The proposed model can predict the loss trending of models across different levels of computation without a gap between validation loss and model's downstream capabilities. |
Orthogonal Subspace Learning for Language Model Continual Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for continual learning in language models suffer catastrophic forgetting when learning sequential tasks. |
| Approach: | They propose an orthogonal low-rank adaptation approach for continual learning in language models that uses orthogons to learn sequentially. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on continual learning benchmarks and preserves generalization ability of LLMs on unseen tasks. |
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design (2026.findings-acl)
Copied to clipboard
Xu Guo, Qiming Ge, Jian Tong, Kedi Chen, Jin Zhang, Xiaogui Yang, Xuan Gao, Haijun Lv, Zhihui Lu, Yicheng Zou, Qipeng Guo
| Challenge: | Existing approaches to RLVR use multiple-choice questions as verifiable rewards . however, not all tasks provide reliable verification . |
| Approach: | They propose a framework that actively constructs high-quality distractors to block elimination shortcuts and promote deep reasoning. |
| Outcome: | The proposed method significantly improves reasoning capabilities of Large Language Models. |
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability. |
| Approach: | They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses. |
| Outcome: | The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences. |
Navigating the OverKill in Large Language Models (2024.acl-long)
Copied to clipboard
Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin
| Challenge: | Recent studies have highlighted a tendency among large language models to refuse to answer benign queries. |
| Approach: | They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding. |
| Outcome: | The proposed approach reduces the refusal rate by 20% while having little impact on safety. |