12 citations · 39 across the 53 of their papers we have counts for
22 papers · 1 filter
SFAD: Speculative Factuality-Aware Decoding
Guanqiao Chen, Di Wang, Lijie Hu
As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive applications. This task is par…
Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
Hongji Li, Junchi yao, Manjiang Yu +4
Machine unlearning aims to erase requested data from trained models without full retraining. For Reasoning Multimodal Large Language Models (RMLLMs), this is uniquely challenging:…
The Compositional Architecture of Regret in Large Language Models
Xiangxiang Cui, Shu Yang, Tianjin Huang +3
Regret in Large Language Models refers to their explicit regret expression when presented with evidence contradicting their previously generated misinformation. Studying the regret…
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
Wenshuo Dong, Qingsong Yang, Shu Yang +5
Large Language Models (LLMs) trained on massive data capture rich information embedded in the training data. However, this also introduces the risk of privacy leakage, particularly…
COMPKE: Complex Question Answering under Knowledge Editing
Keyuan Cheng, Zijian Kan, Zhixian He +5
Knowledge Editing, which efficiently modifies the knowledge in large language models, has gathered great attention. Current benchmarks primarily use multi-hop question answering to…
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
Wenrui Zhou, Mohamed Hendy, Shu Yang +5
As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reasoning, ensuring their factual consistenc…
Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
Yi Su, Jiayi Zhang, Shu Yang +3
Rapid integration of large language models (LLMs) into societal applications has intensified concerns about their alignment with universal ethical principles, as their internal val…
Understanding the Repeat Curse in Large Language Models from a Feature Perspective
Junchi Yao, Shu Yang, Jianhua Xu +3
Large language models (LLMs) have made remarkable progress in various domains, yet they often suffer from repetitive text generation, a phenomenon we refer to as the "Repeat Curse"…
Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation
Tong Li, Shu Yang, Junchao Wu +6
We present a comprehensive evaluation framework for assessing Large Language Models' (LLMs) capabilities in suicide prevention, focusing on two critical aspects: the Identification…
Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
Shu Yang, Shenzhe Zhu, Zeyu Wu +7
We introduce Fraud-R1, a benchmark designed to evaluate LLMs' ability to defend against internet fraud and phishing in dynamic, real-world scenarios. Fraud-R1 comprises 8,564 fraud…
Dissecting Fine-Tuning Unlearning in Large Language Models
Yihuai Hong, Yuelin Zou, Lijie Hu +3
Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabiliti…
Private Language Models via Truncated Laplacian Mechanism
Tianhao Huang, Tao Yang, Ivan Habernal +2
Deep learning models for NLP tasks are prone to variants of privacy attacks. To prevent privacy leakage, researchers have investigated word-level perturbations, relying on the form…
Exploring the Personality Traits of LLMs through Latent Features Steering
Shu Yang, Shenzhe Zhu, Liang Liu +3
Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown…
Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
Zhuoran Zhang, Yongxiang Li, Zijian Kan +3
The locate-then-edit paradigm has shown significant promise for knowledge editing (KE) in Large Language Models (LLMs). While previous methods perform well on single-hop fact recal…
Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top
Keyuan Cheng, Muhammad Asif Ali, Shu Yang +7
Multi-hop Question Answering (MQA) under knowledge editing (KE) is a key challenge in Large Language Models (LLMs). While best-performing solutions in this domain use a plan and so…
Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression
Muhammad Asif Ali, Zhengping Li, Shu Yang +8
Large Language Models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we obse…
Multi-hop Question Answering under Temporal Knowledge Editing
Keyuan Cheng, Gang Lin, Haoyang Fei +5
Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE ex…
Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs
Shu Yang, Jiayuan Su, Han Jiang +5
With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While exi…
MONAL: Model Autophagy Analysis for Modeling Human-AI Interactions
Shu Yang, Muhammad Asif Ali, Lu Yu +2
The increasing significance of large models and their multi-modal variants in societal information processing has ignited debates on social safety and ethics. However, there exists…
MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning
Shu Yang, Muhammad Asif Ali, Cheng-Long Wang +2
Adapting large language models (LLMs) to new domains/tasks and enabling them to be efficient lifelong learners is a pivotal challenge. In this paper, we propose MoRAL, i.e., Mixtur…
Differentially Private Natural Language Models: Recent Advances and Future Directions
Lijie Hu, Ivan Habernal, Lei Shen +1
Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensiti…
SEAT: Stable and Explainable Attention
Lijie Hu, Yixin Liu, Ninghao Liu +3
Currently, attention mechanism becomes a standard fixture in most state-of-the-art natural language processing (NLP) models, not only due to outstanding performance it could gain,…