Papers by Shuoyang Ding
Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech (2026.acl-long)
Copied to clipboard
| Challenge: | Existing synthesis methods cannot guarantee data quality. |
| Approach: | They propose a hierarchical reward that balances translation quality and latency objectives by combining supervised fine-tuning data with supervised inputs. |
| Outcome: | The proposed model can reuse key-value caches across both modalities and eliminate redundant feature recomputation. |
Beyond instruction-conditioning, MoTE: Mixture of Task Experts for Multi-task Embedding Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Instruction-conditioning has become the dominant approach for embedding specialization, but its direct application to low-capacity models imposes representational constraints that limit the performance gains derived from specialization. |
| Approach: | They propose a mixture of task experts transformer block which leverages task-specialized parameters trained with Task-Aware Contrastive Learning to enhance the model’s ability to generate specialized embeddings. |
| Outcome: | The proposed model achieves 64% higher performance gains in retrieval datasets (+3.27 +5.21) and 43% higher performance gain across all datasets (+1.81 2.60). |
Evaluating Saliency Methods for Neural Language Models (2021.naacl-main)
Copied to clipboard
| Challenge: | a general complaint of neural network models is that their internal decision mechanisms are hard to understand. |
| Approach: | They evaluate the quality of prediction interpretations from two perspectives: plausibility and faithfulness. |
| Outcome: | The evaluation of saliency methods on neural language models shows they can be trusted . the methods can be used to interpret the same prediction, but they disagree on interpretations . |
Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to evaluate large language models fail to address cultural bias in non-Western languages . Chinese prompting shifts bias toward East Asian perspectives rather than eliminating it, authors say . |
| Approach: | They propose a Chinese–English bilingual benchmark and multi-agent vote frameworks that enable explicit "no bias" judgments. |
| Outcome: | The proposed framework achieves 57.6% average No Bias Rate on Chinese-English benchmark and 86.0% on Arabic CAMeL benchmark. |
Levenshtein Training for Word-level Quality Estimation (2021.emnlp-main)
Copied to clipboard
| Challenge: | a novel scheme to perform word-level quality estimation is proposed for word-based quality estimation . authors propose a two-stage transfer learning procedure on augmented and human data . a Levenshtein Transformer can learn to post-edit without explicit supervision. |
| Approach: | They propose a novel scheme to use a Levenshtein Transformer to perform word-level quality estimation. |
| Outcome: | The proposed method performs better under data-constrained and unconstrained conditions than existing methods. |
Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains (2024.acl-short)
Copied to clipboard
| Challenge: | a new dataset examines whether fine-tuned metrics are robust to domain shifts between training and inference. |
| Approach: | They use an annotated multidimensional quality metrics dataset to examine whether they are robust to domain shifts between training and inference. |
| Outcome: | The proposed metrics exhibit a substantial performance drop in the unseen domain scenario compared to metrics that rely on the surface form and pre-trained metrics that are not fine-tuned on MT quality judgments. |
Extending Automatic Machine Translation Evaluation to Book-Length Documents (2025.emnlp-main)
Copied to clipboard
Kuang-Da Wang, Shuoyang Ding, Chao-Han Huck Yang, Ping-Chun Hsieh, Wen-Chih Peng, Vitaly Lavrukhin, Boris Ginsburg
| Challenge: | Large Language Models (LLMs) have superior translation performance and long-context capabilities, but evaluation methodologies remain constrained to sentence-level assessment due to dataset limitations and token number restrictions in metrics. |
| Approach: | They propose an evaluation scheme that extends existing automatic metrics to long-document translation by treating documents as continuous text and applying sentence segmentation and alignment methods. |
| Outcome: | The proposed evaluation scheme outperforms existing long-form document evaluation schemes while accounting for under-/over-translations and varied sentence boundaries. |