Papers by Luxi Xing
Guiding Neural Machine Translation with Semantic Kernels (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical studies show that our approach gains approximately an improvement of 1 BLEU score on most benchmarks over the Transformer baseline. |
| Approach: | They propose to extract several semantic kernels from a source sentence to capture global semantic information. |
| Outcome: | Empirical results show that the proposed approach improves 1 BLEU score on benchmarks . it is also 1.7 times faster than previous works on average at inference time . |
Uncertainty-Aware Semantic Augmentation for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for neural machine translation only observe one source sentence at training time . this discrepancy in data distribution leads to a formidable learning challenge . |
| Approach: | They propose an uncertainty-aware semantic augmentation approach to capture universal semantic information among multiple source sentences and enhance hidden representations with this information. |
| Outcome: | The proposed approach outperforms baseline and existing methods on translation tasks. |
Psychology-guided Controllable Story Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing controllable story generation systems ignore the psychological changes of the protagonists and focus on the appointed keywords or emotions. |
| Approach: | They propose a Psychology-guided Controllable Story Generation System (PICS) that generates stories that adhere to the given leading context and desired psychological state chains for the protagonist. |
| Outcome: | The proposed system outperforms baselines and shows that it can generate stories with more consistent psychological changes. |
Bi-directional CognitiveThinking Network for Machine Reading Comprehension (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for reading comprehension are still in their infancy at the level of cognitive intelligence. |
| Approach: | They propose a bi-directional cognitive knowledge framework to simulate reverse thinking and inertial thinking in the brain to answer questions. |
| Outcome: | The proposed framework shows that bi-directional knowledge helps the QA task. |
COMMA: Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for modeling motivations, emotions and actions in language-based human activities have been limited. |
| Approach: | They propose to model motivations, emotions and actions in language-based human activities using a dataset called Story Commonsense. |
| Outcome: | The proposed model can better reveal the essential relationship between motivations, emotions and actions than existing methods. |
Can We Steer Reasoning Direction by Thinking Intervention? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Reason Models suffer from overthinking and erroneous reasoning problems due to the lack of fine-grained control over their reasoning behaviors. |
| Approach: | They propose a paradigm to enable fine-grained control over LRMs’ reasoning behaviors by aligning reasoning trajectories with specific cognitive patterns. |
| Outcome: | The proposed paradigm achieves integration intervention throughout model reasoning processes. |
Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Ziheng Li, Liu Kang, Feng Xiao, Luxi Xing, Qingyi Si, Zhuoran Li, Weikang Gong, Deqing Yang, Yanghua Xiao, Hongcheng Guo
| Challenge: | Group Relative Policy Optimization (GRPO) uses a coarse-grained credit assignment mechanism that propagates group-level rewards uniformly to to every token in a sequence, neglecting the varying contribution of individual reasoning steps. |
| Approach: | They introduce Outcome-grounded Advantage Reshaping (OAR) which redistributes advantages based on how much each token influences the model’s final answer. |
| Outcome: | Empirical results show that OAR-G outperforms GRPO on a high-fidelity attribution signal and suppresses low-impact tokens while preserving the advantage mass. |