Papers by Weiqiu You
Macro-Average: Rare Types Are Important Too (2021.naacl-main)
Copied to clipboard
| Challenge: | MT metrics trained on segment-level human judgments are inherently non-transparent and reflect undesirable biases. |
| Approach: | They propose to use a type-based classifier metric to evaluate machine translation and compare it with a supervised and unsupervised one. |
| Outcome: | The proposed model outperforms other models in indicating cross-lingual information retrieval task performance and shows that it can be used to compare supervised and unsupervised neural machine translation. |
NSF-SciFy: Mining the NSF Awards Database for Scientific Claims (2026.acl-long)
Copied to clipboard
| Challenge: | NSF-SciFy contains 2.8 million claims from 400,000 abstracts spanning all science and mathematics disciplines. |
| Approach: | They propose to use a dataset to extract scientific claims from National Science Foundation award abstracts and to use it to refine language models. |
| Outcome: | The proposed method improves non-technical abstract generation, claim extraction, and investigation proposal extraction tasks while maintaining high precision and lower recall. |
Causal Reasoning of Entities and Events in Procedural Texts (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing work on entity state tracking or event reasoning is limited to procedural texts. |
| Approach: | They propose a benchmark for causal reasoning of event plausibility and entity states . they represent entities as programming languages while prompting language models . |
| Outcome: | The proposed model outperforms existing models on human reasoning and event reasoning. |
A Pretrained Language Model for Cyber Threat Intelligence (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Earlier studies have shown that domain-specific LMs are crucial for domain-specific applications. |
| Approach: | They propose a new BERT model for the cybersecurity domain, CTI-BERT . they find it significantly outperforms general-domain and security-domain models . |
| Outcome: | The proposed model outperforms general-domain and security-domain models for cybersecurity tasks. |
Probabilistic Soundness Guarantees in LLM Reasoning Chains (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting propagated errors in reasoning chains are inadequate . author et al. (2017) show that initial errors propagate and undermine reliability of final conclusion . |
| Approach: | They propose a framework that evaluates each reasoning step based solely on previously-verified premises and provides certified statistical guarantees of its soundness. |
| Outcome: | ARES achieves state-of-the-art performance across four benchmarks and demonstrates superior robustness on very long synthetic reasoning chains. |
Hard-Coded Gaussian Attention for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work has questioned the importance of multi-headed attention in achieving high translation quality. |
| Approach: | They develop a “hard-coded” attention variant without any learned parameters. |
| Outcome: | The proposed model reduces BLEU scores by adding a single learned cross attention head to an otherwise hard-coded Transformer. |