Lei Sha - RankMe

92 papers A* 21A 1B 4Journal 42Unranked 22

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay. CoRR Hao Wang, Yanting Wang, Hao Li, Rui Li, Lei Sha
2026	A*	`conf`	Large Language Models Struggle with Unreasonability in Math Problems. AAAI Jingyuan Ma, Damai Dai, Zihang Yuan, Rui Li, Weilin Luo, Bin Wang, Qun Liu, Lei Sha, Zhifang Sui
2025	J	`jnl`	AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement. CoRR Zhexin Zhang, Leqi Lei, Junxiao Yang, Xijie Huang, Yida Lu, Shiyao Cui, Renmiao Chen, Qinglin Zhang, Xinyuan Wang, Hao Wang, Hao Li, Xianqi Lei, Chengwei Pan, Lei Sha, Hongning Wang, Minlie Huang
2025	J	`jnl`	BBox DocVQA: A Large Scale Bounding Box Grounded Dataset for Enhancing Reasoning in Document Visual Question Answer. CoRR Wenhan Yu, Wang Chen, Guanqiang Qi, Weikang Li, Yang Li, Lei Sha, Deguo Xia, Jizhou Huang
2025	J	`jnl`	Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming. CoRR Rui Li, Peiyi Wang, Jingyuan Ma, Di Zhang, Lei Sha, Zhifang Sui
2025	J	`jnl`	Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models. CoRR Wenhan Yu, Xinbo Lin, Lanxin Ni, Jinhua Cheng, Lei Sha
2025	J	`jnl`	CMRAG: Co-modality-based visual document retrieval and question answering. CoRR Wang Chen, Wenhan Yu, Guanqiang Qi, Weikang Li, Yang Li, Lei Sha, Deguo Xia, Jizhou Huang
2025	A*	`conf`	DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak. EMNLP Hao Wang, Hao Li, Junda Zhu, Xinyuan Wang, Chengwei Pan, Minlie Huang, Lei Sha
2025	—	`conf`	HSF: Defending against Jailbreak Attacks with Hidden State Filtering. WWW (Companion Volume) Cheng Qian, Hainan Zhang, Lei Sha, Zhiming Zheng
2025	J	`jnl`	HauntAttack: When Attack Follows Reasoning as a Shadow. CoRR Jingyuan Ma, Rui Li, Zheng Li, Junfeng Liu, Lei Sha, Zhifang Sui
2025	—	`conf`	How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation. ACL (Findings) Rui Li, Heming Xia, Xinfeng Yuan, Qingxiu Dong, Lei Sha, Wenjie Li, Zhifang Sui
2025	J	`jnl`	How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation. CoRR Rui Li, Heming Xia, Xinfeng Yuan, Qingxiu Dong, Lei Sha, Wenjie Li, Zhifang Sui
2025	—	`conf`	LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts. ACL (1) Qibing Ren, Hao Li, Dongrui Liu, Zhanxu Xie, Xiaoya Lu, Yu Qiao, Lei Sha, Junchi Yan, Lizhuang Ma, Jing Shao
2025	A*	`conf`	Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment. EMNLP Hao Li, Lijun Li, Zhenghao Lu, Xianyi Wei, Rui Li, Jing Shao, Lei Sha
2025	J	`jnl`	Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment. CoRR Hao Li, Lijun Li, Zhenghao Lu, Xianyi Wei, Rui Li, Jing Shao, Lei Sha
2025	A*	`conf`	Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models. ICLR Bofei Gao, Feifan Song, Zhe Yang, Zefan Cai, Yibo Miao, Qingxiu Dong, Lei Li, Chenghao Ma, Liang Chen, Runxin Xu, Zhengyang Tang, Benyou Wang, Daoguang Zan, Shanghaoran Quan, Ge Zhang, Lei Sha, Yichang Zhang, Xuancheng Ren, Tianyu Liu, Baobao Chang
2025	A*	`conf`	Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking. EMNLP Junda Zhu, Lingyong Yan, Shuaiqiang Wang, Dawei Yin, Lei Sha
2025	J	`jnl`	Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking. CoRR Junda Zhu, Lingyong Yan, Shuaiqiang Wang, Dawei Yin, Lei Sha
2025	J	`jnl`	Resource Allocation Algorithm for Sensing Video Transmission Over Cell-Free Radio Access Networks. IEEE Open J. Commun. Soc. Chunyang Liu, Li Yu, Lei Sha, Changwei Zhang, Dongming Wang
2025	—	`conf`	Towards Harmonized Uncertainty Estimation for Large Language Models. ACL (1) Rui Li, Jing Long, Muge Qi, Heming Xia, Lei Sha, Peiyi Wang, Zhifang Sui
2025	J	`jnl`	Towards Harmonized Uncertainty Estimation for Large Language Models. CoRR Rui Li, Jing Long, Muge Qi, Heming Xia, Lei Sha, Peiyi Wang, Zhifang Sui
2024	B	`conf`	A Cross-Site Scripting Attack Protection Framework Based on Managed Proxy. TrustCom Cheng Tang, Qingfeng Wang, Guozhen Cheng, Hao Liang, Jianhua Peng, Meiyue Yang, Wenyan Liu, Ming Liu, Lei Sha
2024	A*	`conf`	A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks. ICLR Tommaso Salvatori, Yuhang Song, Yordan Yordanov, Beren Millidge, Lei Sha, Cornelius Emde, Zhenghua Xu, Rafal Bogacz, Thomas Lukasiewicz
2024	A*	`conf`	ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings. EMNLP Hao Wang, Hao Li, Minlie Huang, Lei Sha
2024	A*	`conf`	ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator. EMNLP Junda Zhu, Lingyong Yan, Haibo Shi, Dawei Yin, Lei Sha
2024	J	`jnl`	ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator. CoRR Junda Zhu, Lingyong Yan, Haibo Shi, Dawei Yin, Lei Sha
2024	—	`conf`	Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming. EMNLP (Findings) Rui Li, Peiyi Wang, Jingyuan Ma, Di Zhang, Lei Sha, Zhifang Sui
2024	J	`jnl`	BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models. CoRR Xinyuan Wang, Victor Shea-Jay Huang, Renmiao Chen, Hao Wang, Chengwei Pan, Lei Sha, Minlie Huang
2024	J	`jnl`	Correcting Flaws in Common Disentanglement Metrics. Trans. Mach. Learn. Res. Louis Mahon, Lei Sha, Thomas Lukasiewicz
2024	J	`jnl`	Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues. CoRR Qibing Ren, Hao Li, Dongrui Liu, Zhanxu Xie, Xiaoya Lu, Yu Qiao, Lei Sha, Junchi Yan, Lizhuang Ma, Jing Shao
2024	J	`jnl`	DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak. CoRR Hao Wang, Hao Li, Junda Zhu, Xinyuan Wang, Chengwei Pan, Minlie Huang, Lei Sha
2024	J	`jnl`	From Noise to Clarity: Unraveling the Adversarial Suffix of Large Language Model Attacks via Translation of Text Embeddings. CoRR Hao Wang, Hao Li, Minlie Huang, Lei Sha
2024	J	`jnl`	HSF: Defending against Jailbreak Attacks with Hidden State Filtering. CoRR Cheng Qian, Hainan Zhang, Lei Sha, Zhiming Zheng
2024	J	`jnl`	Harnessing the Plug-and-Play Controller by Prompting. CoRR Hao Wang, Lei Sha
2024	J	`jnl`	Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models. CoRR Bofei Gao, Feifan Song, Zhe Yang, Zefan Cai, Yibo Miao, Qingxiu Dong, Lei Li, Chenghao Ma, Liang Chen, Runxin Xu, Zhengyang Tang, Benyou Wang, Daoguang Zan, Shanghaoran Quan, Ge Zhang, Lei Sha, Yichang Zhang, Xuancheng Ren, Tianyu Liu, Baobao Chang
2024	J	`jnl`	Plug-and-Play Training Framework for Preference Optimization. CoRR Jingyuan Ma, Rui Li, Zheng Li, Lei Sha, Zhifang Sui
2024	—	`conf`	ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors. EMNLP (Findings) Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang
2024	J	`jnl`	ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors. CoRR Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang
2024	J	`jnl`	Text Attribute Control via Closed-Loop Disentanglement. Trans. Assoc. Comput. Linguistics Lei Sha, Thomas Lukasiewicz
2024	J	`jnl`	Towards a Unified View of Preference Learning for Large Language Models: A Survey. CoRR Bofei Gao, Feifan Song, Yibo Miao, Zefan Cai, Zhe Yang, Liang Chen, Helan Hu, Runxin Xu, Qingxiu Dong, Ce Zheng, Wen Xiao, Ge Zhang, Daoguang Zan, Keming Lu, Bowen Yu, Dayiheng Liu, Zeyu Cui, Jian Yang, Lei Sha, Houfeng Wang, Zhifang Sui, Peiyi Wang, Tianyu Liu, Baobao Chang
2024	J	`jnl`	Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation. CoRR Guanhua Chen, Wenhan Yu, Lei Sha
2023	J	`jnl`	Rationalizing Predictions by Adversarial Information Calibration. CoRR Lei Sha, Oana-Maria Camburu, Thomas Lukasiewicz
2023	J	`jnl`	Rationalizing predictions by adversarial information calibration. Artif. Intell. Lei Sha, Oana-Maria Camburu, Thomas Lukasiewicz
2023	J	`jnl`	Text Attribute Control via Closed-Loop Disentanglement. CoRR Lei Sha, Thomas Lukasiewicz
2022	J	`jnl`	Bird-Eye Transformers for Text Generation Models. CoRR Lei Sha, Yuhang Song, Yordan Yordanov, Tommaso Salvatori, Thomas Lukasiewicz
2022	J	`jnl`	Incremental Predictive Coding: A Parallel and Fully Automatic Learning Algorithm. CoRR Tommaso Salvatori, Yuhang Song, Beren Millidge, Zhenghua Xu, Lei Sha, Cornelius Emde, Rafal Bogacz, Thomas Lukasiewicz
2022	—	`conf`	RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models. AACL/IJCNLP (1) Lingzhi Wang, Huang Hu, Lei Sha, Can Xu, Daxin Jiang, Kam-Fai Wong
2022	A	`conf`	Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning. INTERSPEECH Yuntao Li, Can Xu, Huang Hu, Lei Sha, Yan Zhang, Daxin Jiang
2021	A*	`conf`	Associative Memories via Predictive Coding. NeurIPS Tommaso Salvatori, Yuhang Song, Yujian Hong, Lei Sha, Simon Frieder, Zhenghua Xu, Rafal Bogacz, Thomas Lukasiewicz
2021	J	`jnl`	Associative Memories via Predictive Coding. CoRR Tommaso Salvatori, Yuhang Song, Yujian Hong, Simon Frieder, Lei Sha, Zhenghua Xu, Rafal Bogacz, Thomas Lukasiewicz
2021	—	`conf`	Controlling Text Edition by Changing Answers of Specific Questions. ACL/IJCNLP (Findings) Lei Sha, Patrick Hohenecker, Thomas Lukasiewicz
2021	J	`jnl`	Controlling Text Edition by Changing Answers of Specific Questions. CoRR Lei Sha, Patrick Hohenecker, Thomas Lukasiewicz
2021	J	`jnl`	Finetuning Large-Scale Pre-trained Language Models for Conversational Recommendation with Knowledge Graph. CoRR Lingzhi Wang, Huang Hu, Lei Sha, Can Xu, Kam-Fai Wong, Daxin Jiang
2021	A*	`conf`	Learning from the Best: Rationalizing Predictions by Adversarial Information Calibration. AAAI Lei Sha, Oana-Maria Camburu, Thomas Lukasiewicz
2021	A*	`conf`	Multi-type Disentanglement without Adversarial Training. AAAI Lei Sha, Thomas Lukasiewicz
2021	J	`jnl`	Rationale production to support clinical decision-making. CoRR Niall Taylor, Lei Sha, Dan W. Joyce, Thomas Lukasiewicz, Alejo J. Nevado-Holgado, Andrey Kormilitzin
2021	J	`jnl`	Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning. CoRR Yuntao Li, Can Xu, Huang Hu, Lei Sha, Yan Zhang, Daxin Jiang
2020	B	`conf`	Estimating Minimum Operation Steps via Memory-based Recurrent Calculation Network. IJCNN Lei Sha, Chen Shi, Qi Chen, Lintao Zhang, Houfeng Wang
2020	—	`conf`	Gradient-guided Unsupervised Lexically Constrained Text Generation. EMNLP (1) Lei Sha
2020	—	`conf`	Improved Nagata Current Source Insensitive to Temperature and Power Supply Voltage. ISOCC Takashi Hosono, Lei Sha, Souma Yamamoto, Mayu Hirano, Takashi Ida, Anna Kuwana, Haruo Kobayashi, Yoichi Moroshima, Hiromichi Harakawa, Takeshi Oikawa
2020	J	`jnl`	Learning from the Best: Rationalizing Prediction by Adversarial Information Calibration. CoRR Lei Sha, Oana-Maria Camburu, Thomas Lukasiewicz
2020	J	`jnl`	Multi-type Disentanglement without Adversarial Training. CoRR Lei Sha, Thomas Lukasiewicz
2020	—	`conf`	Simple Reference Voltage Generation Circuit Insensitive to Temperature. ISOCC Lei Sha, Anna Kuwana, Masashi Horiguchi, Haruo Kobayashi
2019	—	`conf`	Fine Time Resolution TDC Architectures -Integral and Delta-Sigma Types. ASICON Haruo Kobayashi, Kosuke Machida, Yuto Sasaki, Yusuke Osawa, Pengfei Zhang, Lei Sha, Yuki Ozawa, Anna Kuwana
2019	—	`conf`	High-Resolution Low-Sampling-Rate Δ∑ ADC Linearity Short-Time Testing Algorithm. ASICON Jiang-Lin Wei, Takashi Ishida, Toshiyuki Okamoto, Tamotsu Ichikawa, Nene Kushita, Takahiro Arai, Lei Sha, Anna Kuwana, Haruo Kobayashi, Takayuki Nakatani, Kazumi Hatayama, Keno Sato
2019	—	`conf`	We Know What You Will Ask: A Dialogue System for Multi-intent Switch and Prediction. NLPCC (1) Chen Shi, Qi Chen, Lei Sha, Hui Xue, Sujian Li, Lintao Zhang, Houfeng Wang
2018	A*	`conf`	A Multi-View Fusion Neural Network for Answer Selection. AAAI Lei Sha, Xiaodong Zhang, Feng Qian, Baobao Chang, Zhifang Sui
2018	A*	`conf`	Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning. EMNLP Chen Shi, Qi Chen, Lei Sha, Sujian Li, Xu Sun, Houfeng Wang, Lintao Zhang
2018	A*	`conf`	Jointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction. AAAI Lei Sha, Feng Qian, Baobao Chang, Zhifang Sui
2018	A*	`conf`	Order-Planning Neural Text Generation From Structured Data. AAAI Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui
2018	A*	`conf`	Table-to-Text Generation by Structure-Aware Seq2seq Learning. AAAI Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui
2017	—	`conf`	A Progressive Learning Approach to Chinese SRL Using Heterogeneous Data. ACL (1) Qiaolin Xia, Lei Sha, Baobao Chang, Zhifang Sui
2017	A*	`conf`	Attentive Interactive Neural Networks for Answer Selection in Community Question Answering. AAAI Xiaodong Zhang, Sujian Li, Lei Sha, Houfeng Wang
2017	—	`ch.`	Image Compression. Encyclopedia of GIS Lei Sha
2017	J	`jnl`	Order-Planning Neural Text Generation From Structured Data. CoRR Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui
2017	J	`jnl`	Syntax Aware LSTM Model for Chinese Semantic Role Labeling. CoRR Feng Qian, Lei Sha, Baobao Chang, Luchen Liu, Ming Zhang
2017	—	`conf`	Syntax Aware LSTM model for Semantic Role Labeling. SPNLP@EMNLP Feng Qian, Lei Sha, Baobao Chang, Luchen Liu, Ming Zhang
2017	J	`jnl`	Table-to-text Generation by Structure-aware Seq2seq Learning. CoRR Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui
2017	—	`conf`	Topic medical concept embedding: Multi-sense representation learning for medical concept. BIBM Feng Qian, Chengyue Gong, Luchen Liu, Lei Sha, Ming Zhang
2017	—	`conf`	Will Repeated Reading Benefit Natural Language Understanding? NLPCC Lei Sha, Feng Qian, Zhifang Sui
2016	A*	`conf`	Capturing Argument Relationship for Chinese Semantic Role Labeling. EMNLP Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui, Tingsong Jiang
2016	A*	`conf`	Encoding Temporal Information for Time-Aware Link Prediction. EMNLP Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui
2016	—	`conf`	Joint Learning Templates and Slots for Event Schema Induction. HLT-NAACL Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui
2016	J	`jnl`	Joint Learning Templates and Slots for Event Schema Induction. CoRR Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui
2016	—	`conf`	RBPB: Regularization-Based Pattern Balancing Method for Event Extraction. ACL (1) Lei Sha, Jing Liu, Chin-Yew Lin, Sujian Li, Baobao Chang, Zhifang Sui
2016	B	`conf`	Reading and Thinking: Re-read LSTM Unit for Textual Entailment Recognition. COLING Lei Sha, Baobao Chang, Zhifang Sui, Sujian Li
2016	—	`conf`	Recognizing Textual Entailment via Multi-task Knowledge Assisted LSTM. CCL Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui
2016	B	`conf`	Towards Time-Aware Knowledge Graph Completion. COLING Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Baobao Chang, Sujian Li, Zhifang Sui
2015	A*	`conf`	Multi-label Text Categorization with Joint Learning Predictions-as-Features Method. EMNLP Li Li, Houfeng Wang, Xu Sun, Baobao Chang, Shi Zhao, Lei Sha
2015	A*	`conf`	Recognizing Textual Entailment Using Probabilistic Inference. EMNLP Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui, Tingsong Jiang
2014	—	`conf`	Event Schema Induction Based on Relational Co-occurrence over Multiple Documents. NLPCC Tingsong Jiang, Lei Sha, Zhifang Sui
2008	—	`ch.`	Image Compression. Encyclopedia of GIS Lei Sha