Papers by Wenyu Du
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Parallel reasoning enhances Large Reasoning Models but incurs prohibitive costs due to futile paths caused by early errors. |
| Approach: | They propose a systematic taxonomy of path pruning to categorize methods by signal source and learnability. |
| Outcome: | The proposed model improves LRMs but incurs prohibitive costs due to futile paths caused by early errors. |
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that Chain-of-thought (CoT) can enhance the performance of large language models (LLMs) however, there is limited understanding of the algorithms that Transformer+CoT can learn. |
| Approach: | They propose two metrics to evaluate Transformer+CoT's state tracking capabilities and identify the circuit responsible for tracking the world state. |
| Outcome: | The proposed model achieves 100% accuracy for each state, highlighting an implicit finite state automaton (FSA) embedded within the model. |
End-to-End AMR Coreference Resolution (2021.acl-long)
Copied to clipboard
| Challenge: | Existing work on AMR focuses on individual sentences, but there is a need for multi-sentence AMRs. |
| Approach: | They propose to use an end-to-end AMR coreference resolution model to generate multi-sentence AMRs. |
| Outcome: | The proposed model reduces error propagation and is more robust for both in- and out-domain situations. |
Unlocking Continual Learning Abilities in Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to learning models (LMs) incorporate old task data or task-wise inductive bias into LMs, but old data and accurate task information are often unavailable or costly to collect. |
| Approach: | They propose a rehearsal-free method that updates model parameters with large magnitudes . they found that the L1-normalized magnitude distribution is different when different task data is used . |
| Outcome: | The proposed method improves accuracy and performance on four CL benchmarks. |
Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach (2020.acl-main)
Copied to clipboard
| Challenge: | incorporating syntactic structure into language models has been a challenge since the 1990s. |
| Approach: | They propose to use syntactic information to integrate syntastic structure into neural language models by providing ground truth parse trees as additional training signals. |
| Outcome: | The proposed model achieves lower perplexity and better quality when ground truth parse trees are provided as training signals. |
f-Divergence Minimization for Sequence-Level Knowledge Distillation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge distillation approaches focus on minimizing a generalized f-divergence function. |
| Approach: | They propose a framework which formulates sequence-level knowledge distillation as minimizing a generalized f-divergence function. |
| Outcome: | The proposed framework outperforms existing methods and reduces intractable divergence to word-level losses. |
Linguistic Dependencies and Statistical Dependence (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that pairs of words that occur together are likely to stand in a linguistic dependency. |
| Approach: | They propose to use large pretrained language models to compute contextualized estimates of the pointwise mutual information between words (CPMI) |
| Outcome: | The proposed model maximizes CPMI and achieves an unlabelled undirected attachment score of 0.5 . |