Papers by Bowen Shen

The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service (2020.lrec-1)

Copied to clipboard

Meng Chen, Ruixue Liu, Lei Shen, Shaozu Yuan, Jingyan Zhou, Youzheng Wu, Xiaodong He, Bowen Zhou

Challenge:	Existing datasets for human-like dialogue tasks are deficient due to the complexity of human conversations.
Approach:	They construct a large-scale Chinese E-commerce conversation corpus with 1 million dialogues, 20 million utterances, and 150 million words.
Outcome:	The proposed dataset includes 1 million multi-turn dialogues, 20 million utterances, and 150 million words.

Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation (2026.acl-long)

Copied to clipboard

Huachen Qi, Ruiyu Zhuo, Bowen Shi, Xiang Chang, Fei Chao, Changjing Shang, Qiang Shen

Language Models

Challenge:	Large Language Models are scaling in size and capability, driving substantial computational and memory costs.
Approach:	They propose a mixed-precision quantization framework that uses fuzzy rule interpolation to predict quantization error from only sparse samples.
Outcome:	The proposed framework accelerates the profiling phase by up to 15.7 on DeepSeek-V2 while achieving comparable or slightly superior zero-shot accuracy.

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning (2024.findings-acl)

Copied to clipboard

Naibin Gu, Peng Fu, Xiyu Liu, Bowen Shen, Zheng Lin, Weiping Wang

Semantic Text Processing

Challenge:	Existing methods for fine-tuning large language models are inefficient and redundant . a light-PEFT framework can be used to prune redundant parameters during training .
Approach:	They propose a parameter-efficient fine-tuning framework that freezes most parameters of the foundation model and finetuns only a small number of parameters.
Outcome:	The proposed framework achieves training and inference speedup, reduces memory usage, and maintains comparable performance and plug-and-play feature of PEFT.

Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations (2024.findings-acl)

Copied to clipboard

Bowen Shen, Zheng Lin, Daren Zha, Wei Liu, Jian Luan, Bin Wang, Weiping Wang

Language Models

Challenge:	Structured pruning is a feasible solution for end-side LLM deployment . however, achieving a high compression ratio for scaled-up LLMs remains a challenge .
Approach:	They propose a task-agnostic structured pruning approach coupled with a compact Transformer architecture to prune LLMs into an intra-module low-rank architecture.
Outcome:	The proposed approach reduces transitional activations inside multi-head attention (MHA) and multi-layer perceptron (MLP) modules while preserving inter-module activations sensitive to perturbations.

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

Reasoning

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.

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization (2025.findings-acl)

Copied to clipboard

Dingyu Yao, Bowen Shen, Zheng Lin, Wei Liu, Jian Luan, Bin Wang, Weiping Wang

Challenge:	Existing work mitigates memory overhead by offloading or compressing the Key-Value cache.
Approach:	They propose a method that integrates quantization and offloading into a generative large language model by using a hybrid compression method.
Outcome:	The proposed method outperforms the state-of-the-art in long-context evaluations.

The Generation Gap: Exploring Age Bias in the Value Systems of Large Language Models (2024.emnlp-main)

Copied to clipboard

Siyang Liu, Trisha Maturi, Bowen Yi, Siqi Shen, Rada Mihalcea

Semantic Text Processing

Challenge:	Using the World Value Survey, we find a general inclination of LLM values towards younger demographics, especially when compared to the US population.
Approach:	They use data from the World Value Survey to examine the alignment of LLM values with specific age groups.
Outcome:	The proposed model can be used to predict the value of a large language model and to assess its performance on 13 categories.

Maximum Entropy Loss, the Silver Bullet Targeting Backdoor Attacks in Pre-trained Language Models (2023.findings-acl)

Copied to clipboard

Zhengxiao Liu, Bowen Shen, Zheng Lin, Fali Wang, Weiping Wang

Robustness in NLP

Challenge:	Existing backdoor defense paradigms focus on detecting and removing poisoned samples at pre-training or inference time.
Approach:	They propose a new approach where the backdoor attack is directly reversed by incorporating maximum entropy loss into training to neutralize the minimal cross-entropiness loss fine-tuning on poisoned data.
Outcome:	The proposed model significantly lowers the attack success rate on classification tasks and reduces the risk of backdoor attacks on clean data.

STAIR: Learning Sparse Text and Image Representation in Grounded Tokens (2023.emnlp-main)

Copied to clipboard

Chen Chen, Bowen Zhang, Liangliang Cao, Jiguang Shen, Tom Gunter, Albin Jose, Alexander Toshev, Yantao Zheng, Jonathon Shlens, Ruoming Pang, Yinfei Yang

Representation Learning

Challenge:	State-of-the-art contrastive learning models like CLIP and ALIGN are less interpretable and suffer from inferior accuracy than dense representations.
Approach:	They extend CLIP and ALIGN models to build a sparse semantic representation that is interpretable and easy to integrate with existing retrieval systems.
Outcome:	The proposed model outperforms CLIP and ALIGN models on image and text retrieval tasks with a 4.9% and +4.3% improvement on COCO-5k textimage and imagetext retrieval respectively.

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts (2025.acl-long)

Copied to clipboard

Yuchen Feng, Bowen Shen, Naibin Gu, Jiaxuan Zhao, Peng Fu, Zheng Lin, Weiping Wang

Semantic Text Processing

Challenge:	Existing methods for reconstruction of large language models overlook diversity among experts, leading to potential redundancy.
Approach:	They propose a pruning-based expert reconstruction method that prunes a specific LLM and retrains it on routers, experts and normalization modules.
Outcome:	The proposed method outperforms pruning and MoE reconstruction methods on Llama-style models with open-source training corpora.

COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models (2022.emnlp-main)

Copied to clipboard

Bowen Shen, Zheng Lin, Yuanxin Liu, Zhengxiao Liu, Lei Wang, Weiping Wang

Language Models

Challenge:	Existing statically compressed pre-trained language models lack spatial and temporal efficiency due to their large size and wide width.
Approach:	They propose a spatially and temporally efficient model which retains the major capacity of PLMs.
Outcome:	The proposed model retains the major capacity of pre-trained language models at high compression and acceleration rate with 1/8 parameters and 1/19 FLOPs of BERT.

Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Human-LLM Dialogue (2026.findings-acl)

Copied to clipboard

Jonathan Ivey, Shivani Kumar, Jiayu Liu, Hua Shen, Sushrita Rakshit, Rohan Raju, Haotian Zhang, Aparna Ananthasubramaniam, Junghwan Kim, Bowen Yi, Dustin Wright, Abraham Israeli, Anders Giovanni Møller, Lechen Zhang, David Jurgens

Dialogue Systems & Conversational Agents

Challenge:	Recent work has sought to use large language models to simulate human-human and human-LLM interactions.
Approach:	They use a large-scale dataset to generate a paired LLM-LLM and human-LLm dialogues from the WildChat dataset and quantify how well they align with their human counterparts.
Outcome:	The proposed models perform similarly in simulating English, Chinese, and Russian dialogues.

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training (2025.emnlp-main)

Copied to clipboard

Haotian Dong, Jingyan Jiang, Rongwei Lu, Jiajun Luo, Jiajun Song, Bowen Li, Ying Shen, Zhi Wang

Text Clustering

Challenge:	Decentralized LLM training leverages dispersed resources at varying scales.
Approach:	They propose a resource-driven paradigm that leverages dispersed resources across clusters, datacenters and even regions.
Outcome:	The proposed model scales are 175 billion to 660 billion parameters, and the exponential growth in computational requirements poses significant challenges.

Causally Modeling the Linguistic and Social Factors that Predict Email Response (2025.naacl-long)

Copied to clipboard

Yinuo Xu, Hong Chen, Sushrita Rakshit, Aparna Ananthasubramaniam, Omkar Yadav, Mingqian Zheng, Michael Jiang, Lechen Zhang, Bowen Yi, Kenan Alkiek, Abraham Israeli, Bangzhao Shu, Hua Shen, Jiaxin Pei, Haotian Zhang, Miriam Schirmer, David Jurgens

Challenge:	a key intent behind many emails is to get a reply from the recipient.
Approach:	They propose to model the intents, expectations, and responsiveness in email exchanges by using a dataset containing 1800 emails annotated with nuanced types of intents and expectations.
Outcome:	The proposed model is based on 1800 emails annotated with nuanced types of intents and expectations . it shows that social status, argumentation, and strength of social connection influence email response rates .