:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Mo, Wenjie Jacky, Liu, Qin, Wen, Xiaofei, Zhou, Wenxuan, Zhao, Zhe, Chen, Muhao
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	https://arxiv.org/abs/2603.17884
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails
by: Wen, Xiaofei, et al.
Published: (2025)

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
by: Mo, Wenjie Jacky, et al.
Published: (2025)

Triaging Threats to Specialized Guardrails
by: Mo, Wenjie Jacky, et al.
Published: (2026)

OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
by: Zhu, Boyu, et al.
Published: (2025)

SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
by: Liu, Qin, et al.
Published: (2024)

Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
by: Wang, Cheng, et al.
Published: (2026)

Learning Efficient Guardrails for Compliance
by: Wen, Xiaofei, et al.
Published: (2025)

Code Execution as Grounded Supervision for LLM Reasoning
by: Jung, Dongwon, et al.
Published: (2025)

LeDex: Training LLMs to Better Self-Debug and Explain Code
by: Jiang, Nan, et al.
Published: (2024)

Red Teaming Language Models for Processing Contradictory Dialogues
by: Wen, Xiaofei, et al.
Published: (2024)

On-the-fly Denoising for Data Augmentation in Natural Language Understanding
by: Fang, Tianqing, et al.
Published: (2022)

How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities
by: Mo, Lingbo, et al.
Published: (2023)

Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
by: Mo, Wenjie, et al.
Published: (2023)

UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
by: Zhou, Wenxuan, et al.
Published: (2023)

TeachLM: Post-Training LLMs for Education Using Authentic Learning Data
by: Perczel, Janos, et al.
Published: (2025)

Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
by: Graf, Victoria, et al.
Published: (2024)

Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges
by: Liu, Qin, et al.
Published: (2024)

Rethinking Backdoor Detection Evaluation for Language Models
by: Yan, Jun, et al.
Published: (2024)

BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge
by: Tong, Terry, et al.
Published: (2025)

False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize
by: Wang, Cheng, et al.
Published: (2025)

Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
by: Fang, Tianqing, et al.
Published: (2023)

When Vision Speaks for Sound
by: Wen, Xiaofei, et al.
Published: (2026)

KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
by: Hu, Xinshuo, et al.
Published: (2025)

MetaScale: Test-Time Scaling with Evolving Meta-Thoughts
by: Liu, Qin, et al.
Published: (2025)

OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas
by: Huang, James Y., et al.
Published: (2025)

Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing
by: Askari, Hadi, et al.
Published: (2024)

DebugBench: Evaluating Debugging Capability of Large Language Models
by: Tian, Runchu, et al.
Published: (2024)

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging
by: Zhang, Weiming, et al.
Published: (2025)

The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning
by: Ahmed, Md Shamim, et al.
Published: (2026)

SynLexLM: Scaling Legal LLMs with Synthetic Data and Curriculum Learning
by: Upadhyay, Ojasw, et al.
Published: (2025)

QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA
by: Dineen, Jacob, et al.
Published: (2025)

BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data
by: Jumelet, Jaap, et al.
Published: (2025)

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
by: Jung, Dongwon, et al.
Published: (2024)

Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
by: Cai, Rui, et al.
Published: (2025)

Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
by: Huang, Yixu, et al.
Published: (2026)

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models
by: Zhu, Tinghui, et al.
Published: (2024)

KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
by: Zhao, Xinping, et al.
Published: (2025)

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
by: Zhu, Wang Bill, et al.
Published: (2026)

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
by: Wang, Fei, et al.
Published: (2024)

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
by: Liu, Qin, et al.
Published: (2023)