Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works50 from public data
- Agent-SafetyBench: Evaluating the Safety of LLM Agents311
This paper introduces Agent-SafetyBench, a comprehensive benchmark designed to evaluate the safety of LLM agents, and summarizes two fundamental safety defects in current LLM agents: lack of robustness and lack of risk awareness.
- Safety Assessment of Chinese Large Language Models113
A Chinese LLM safety assessment benchmark is developed based on the LLM's strong evaluation ability and develops it as a safety evaluator by prompting, which finds that instruction attacks are more likely to expose safety issues of all LLMs.
- 88
- OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics83
OpenMEVA provides a comprehensive test suite to assess the capabilities of metrics, including the correlation with human judgments, the generalization to different model outputs and datasets, the ability to judge story coherence, and the robustness to perturbations.
- 56
- 37
- MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions30
This paper proposes a framework, MoralDial, to train and evaluate moral dialogue systems, and proposes a novel evaluation method under the framework, which evaluates the multiple aspects of morality by judging the relation between dialogue responses and human values in discussions.
- 23
- 17
- AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement16
AISafetyLab is introduced, a unified framework and toolkit that integrates representative attack, defense, and evaluation methodologies for AI safety and features an intuitive interface that enables developers to seamlessly apply various techniques while maintaining a well-structured and extensible codebase for future advancements.
- JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering14
This work proposes JPS, Jailbreak MLLMs with collaborative visual Perturbation and textual Steering, which achieves jailbreaks via corporation of visual image and textually steering prompt, and proposes the Malicious Intent Fulfillment Rate (MIFR) metric.
- 14
- 12
- 11
- ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs: ShieldVLM10
ShieldVLM is built, a model which identifies implicit toxicity in multimodal statements, prompts and dialogs via deliberative cross-modal reasoning and outperforms existing strong baselines in detecting both implicit and explicit toxicity.
- 10
- BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs9
This work identifies two pathological reasoning patterns characterized by overthinking that contribute to the overconfident and incorrect answers: last-minute guessing and second-thought spiraling and proposes BARREL-a novel framework that promotes concise and boundary-aware factual reasoning.
- Automatic Comment Generation for Chinese Student Narrative Essays8
A planning-based generation model is proposed, which first plans a sequence of keywords, and then expands these keywords into a complete comment, which outperforms strong baselines significantly and exerts explicit control on the model to generate comments to describe the strengths or weaknesses of inputs.
- Selecting Stickers in Open-Domain Dialogue through Multitask Learning7
A multitask learning method comprised of three auxiliary tasks to enhance the understanding of dialogue history, emotion and semantic meaning of stickers is proposed and extensive experiments show that the model can better combine the multimodal information and achieve significantly higher accuracy over strong baselines.
- Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation6
AugCOLD (Augmented Chinese Offensive Language Dataset), a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model generation, is introduced and a multiteacher distillation framework is employed to enhance detection performance with unsuper supervised data.
- 6
- Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!5
These comprehensive experiments suggest that the extraction performance can be strikingly high: in practical settings, as much as 76.3% downstream fine-tuning data (queries) out of a total 5,000 samples can be perfectly extracted, and the success rate can increase to 94.9% in more ideal settings.
- 5
- Psychological distance and user engagement in online exhibitions: Visualization of moiré patterns based on electroencephalography signals5
Electroencephalography signal visualization media devices can reduce the psychological distance between two participants when experiencing an online exhibition and can increase user engagement to some extent, this study shows.
- 4
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.