Papers by Ou Wu
AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for In-Context Learning (ICL) rely on a predetermined number of shots, leading to insufficient context or noise. |
| Approach: | They propose a probe-based evaluation mechanism that utilizes output entropy to determine the optimal number of shots and leverages KV cache reuse for efficient inference. |
| Outcome: | The proposed model achieves an average performance gain of 10% and a 4.64 speedup compared to state-of-the-art DBSA. |
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)
Copied to clipboard
Runxuan Liu, Xianhao Ou, Xinyan Ma, Jiyuan Wang, Jiafeng Liang, Jiaqi Li, Tao He, Zheng Chu, Rongchuan Mu, Zekun Wang, Baoxin Wang, Dayong Wu, Ming Liu, Shijin Wang, Guoping Hu, Bing Qin
| Challenge: | Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization. |
| Approach: | They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach. |
| Outcome: | The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks. |
Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy (2026.acl-long)
Copied to clipboard
Eric Hanchen Jiang, Weixuan Ou, Run Liu, Shengyuan Pang, Guancheng Wan, Ranjie Duan, Wei Dong, Kai-Wei Chang, XiaoFeng Wang, Ying Nian Wu, Xinfeng Li
| Challenge: | Existing safety alignment techniques prioritize mitigating harmful responses at the expense of overcautious behavior, leading models to incorrectly refuse benign requests. |
| Approach: | They propose a fine-tuning free framework to improve safety and reduce false refusals by dynamic, inference-time intervention. |
| Outcome: | The proposed framework raises compliance on the ORB-H benchmark from 57.3% to 82.6% while maintaining the baseline safety performance. |
Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods target instruction dialogues as learning goal and fine-tune user simulators to pose instructions. |
| Approach: | They propose to use real instruction dialogues to model complex dialogue flows and pose high-quality instructions. |
| Outcome: | The proposed method generates diverse, in-depth, and insightful instructions for a given dialogue history. |
Entropy-Based Decoding for Retrieval-Augmented Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Despite their success, retrieval-augmented LLMs still face the distractibility issue, where the generated responses are negatively influenced by noise from both external and intrinsic knowledge sources. |
| Approach: | They propose a entropy-based document-parallel ensemble decoding method that prioritizes low-entropies from retrieved documents and incorporates a contrastive decoding mechanism that contrasts the obtained low- and high-entropic ensemble distributions with the high-end internal knowledge across layers. |
| Outcome: | The proposed method improves on open-domain question answering datasets and shows that it is highly efficient. |
AlphaEdit+: Model Editing in the Presence of Conflicting and Inconsistent Knowledge (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for knowledge editing struggle with knowledge conflicts and inconsistencies. |
| Approach: | They propose a new method for knowledge editing that relaxes null-space constraints and introduces a weighting scheme to mitigate conflicts between new and historical knowledge. |
| Outcome: | The proposed method outperforms existing methods on challenging datasets and outperformed existing methods. |
BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents (2026.findings-acl)
Copied to clipboard
Litu Ou, Kuan Li, Huifeng Yin, Liwen Zhang, Zhongwang Zhang, Xixi Wu, Rui Ye, Zile Qiao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou
| Challenge: | Existing work on confidence in LLMs is limited. |
| Approach: | They propose to use confidence scores to determine model answer quality and encourage model to try again until it reaches satisfactory confidence level. |
| Outcome: | The proposed methods significantly reduce token consumption while demonstrating competitive performance compared to baseline fixed budget methods. |
UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent studies have shown that multi-task instruction tuning after pre-training greatly improves the model’s robustness and transfer ability, which is crucial for building a high-quality dialog system. |
| Approach: | They propose to use Task-aware Automatic Prompt generation (TAP) to automatically generate high-quality prompts from 15 dialog-related tasks. |
| Outcome: | The proposed model is robust to input prompts and capable of various dialog-related tasks. |