Papers by Sen Wu
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)
Copied to clipboard
Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei
| Challenge: | Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning. |
| Approach: | They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios. |
| Outcome: | The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics. |
Template-Based Named Entity Recognition Using BART (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fewshot NER do not make full use of knowledge transfer in NER model parameters. |
| Approach: | They propose a template-based method for NER that treats NER as a language model ranking problem in a sequence-to-sequence framework. |
| Outcome: | The proposed method achieves 92.55% F1 score on the CoNLL03 task and significantly better than fine-tuning BERT 10.88%, 15.34%, and 11.73% F1 scores on the MIT Movie, the ATIS, and the MATLAB task. |
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Domain-specific datasets of harmful prompts are scarce and often rely on manual construction. Existing efforts to improve domain knowledge and reduce harmful prompt generation are lacking. |
| Approach: | They propose a framework that transforms domain knowledge into actionable constraints and increases the implicitness of generated harmful prompts. |
| Outcome: | The proposed framework yields high-quality datasets combining strong domain relevance with implicitness, enabling more realistic red-teaming and advancing LLM safety research. |
Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) often struggle with the issue of generating inaccurate or fabricated content even when they possess correct knowledge. |
| Approach: | They propose a decoding method that mitigates hallucinations without extra training . they propose entropy eNhanced decoding that leverages inner probability changes . |
| Outcome: | The proposed method improves the truthfulness and informativeness of generation while maintaining robust QA accuracy. |
Challenges to Open-Domain Constituency Parsing (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing findings on cross-domain constituency parsing are only made on a limited number of domains. |
| Approach: | They manually annotate a high-quality constituency treebank containing five domains and analyze challenges to open-domain constituency parsing using a set of linguistic features. |
| Outcome: | The proposed model significantly improves the performance of the proposed model on the domain-variant features. |
Cross-Domain Data Integration for Named Entity Disambiguation in Biomedical Text (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for named entity disambiguation are limited by coarse-grained structural resources in biomedical knowledge bases and training datasets that provide low coverage over uncommon resources. |
| Approach: | They propose a method that integrates structural knowledge from general text knowledge bases to the medical domain. |
| Outcome: | The proposed method improves disambiguation accuracy on two benchmark medical NED datasets by up to 57 points. |
Metadata Shaping: A Simple Approach for Knowledge-Enhanced Language Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to capture entity knowledge with factual knowledge are limited . despite its simplicity, metadata shaping is quite effective . |
| Approach: | They propose a method which inserts substrings corresponding to readily available entity metadata into examples at train and inference time based on mutual information. |
| Outcome: | The proposed method exceeds the baseline model by 4.3 F1 points and achieves state-of-the-art results. |
Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for tuning large language models from dense to MoE face significant data requirements and require large-scale post-training. |
| Approach: | They propose an upcycling instruction tuning approach for tuning a dense pre-trained model into a MoE instruction model using genetic algorithm and parameter merging. |
| Outcome: | The proposed approach improves the performance of large language models with a small amount of seed data and improves their scaling. |
KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions (2026.acl-long)
Copied to clipboard
Tingyu Wu, Zhisheng Chen, Ziyan Weng, Shuhe Wang, Shuo Zhang, Sen Hu, Silin Wu, Qizhen Lan, Huacan Wang, Ronghao Chen
| Challenge: | Existing long-horizon memory benchmarks use multi-turn dialogues or synthetic user histories . despite rapid progress on long-term memory evaluation, there are gaps in existing benchmarks . |
| Approach: | They propose a long-form autobiographical narrative benchmark that reconstructs each narrative into a flashback-aware, time-anchored stream and evaluates models with evidence-linked questions. |
| Outcome: | The proposed benchmarks build from long-form autobiographical narratives . they show that retrieval-augmented systems improve factual accuracy while errors persist on temporally grounded explanations and higher-level inferences. |