5 citations · 7 across the 29 of their papers we have counts for
15 papers · 1 filter
EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion
Ruijie Jian, Benlei Cui, Ting Ma +8
Existing evaluations of harmful content detection rely predominantly on static benchmarks, which struggle to reflect the interactive adversarial ecosystem of real-world content pla…
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
Ting Ma, Xiufeng Huang, Benlei Cui +43
As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safet…
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
Yan Wang, Zhixuan Chu, Zihao Xue +9
Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful…
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Ziwen Xu, Kewei Xu, Haoming Xu +8
Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality,…
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
Ziwen Xu, Chenyan Wu, Hengyu Sun +9
Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation,…
YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models
Junyu Lin, Meizhen Liu, Xiufeng Huang +12
As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained filtering and support fine-grained,…
AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset
Bingxiang He, Wenbin Zhang, Jiaxi Song +11
Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Prefe…
Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper
Tianyi Xu, Kaixun Huang, Pengcheng Guo +4
Pre-trained multilingual speech foundation models, like Whisper, have shown impressive performance across different languages. However, adapting these models to new or specific lan…
fairBERTs: Erasing Sensitive Information Through Semantic and Fairness-aware Perturbations
Jinfeng Li, Yuefeng Chen, Xiangyu Liu +3
Pre-trained language models (PLMs) have revolutionized both the natural language processing research and applications. However, stereotypical biases (e.g., gender and racial discri…
R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models
Taolin Zhang, Dongyang Li, Qizhou Chen +5
Retrieval-augmented large language models (LLMs) leverage relevant content retrieved by information retrieval systems to generate correct responses, aiming to alleviate the halluci…
KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning
Dongyang Li, Taolin Zhang, Longtao Huang +3
Knowledge-enhanced pre-trained language models (KEPLMs) leverage relation triples from knowledge graphs (KGs) and integrate these external data sources into language models via sel…
UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding
Dongyang Li, Taolin Zhang, Jiali Deng +4
Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. Ho…
DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models
Taolin Zhang, Qizhou Chen, Dongyang Li +5
Recently, while large language models (LLMs) have demonstrated impressive results, they still suffer from hallucination, i.e., the generation of false information. Model editing is…
Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning
Qizhou Chen, Taolin Zhang, Xiaofeng He +4
Model editing aims to correct outdated or erroneous knowledge in large language models (LLMs) without the need for costly retraining. Lifelong model editing is the most challenging…
TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models
Junbing Yan, Chengyu Wang, Taolin Zhang +5
KEPLMs are pre-trained models that utilize external knowledge to enhance language understanding. Previous language models facilitated knowledge acquisition by incorporating knowled…