Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Junhao Dong

Junhao Dong

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×2AI×1ML×1NLP×1

Frequent co-authors

Yujia Tong1×
Yuxi Wang1×
Yunyang Wan1×
Tian Zhang1×
Jingling Yuan1×
Junxi Chen1×

Research Timeline

2026
BiAxisAudit: A Novel Framework to Evaluate LLM Bias Across Prompt Sensitivity and Response-Layer Divergence

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing that simple aggregate scores are unreliable.

Adaptive Probe-based Steering for Robust LLM Jailbreaking

The paper introduces an adaptive probe-based steering method that significantly improves the robustness and effectiveness of LLM jailbreaking without requiring extra prompts or manual tuning.

Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction

This paper investigates whether model compression techniques (like quantization and pruning) preserve a Large Language Model's ability to quantify its own uncertainty, finding that accuracy-only evaluation is insufficient for assessing deployment readiness.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction

Yujia Tong, Yuxi Wang, Yunyang Wan, Tian Zhang +2 more

This paper investigates whether model compression techniques (like quantization and pruning) preserve a Large Language Model's ability to quantify its own uncertainty, finding that accuracy-only evalu…

View →
cs.CRcs.LGRecentMay 19, 2026

Adaptive Probe-based Steering for Robust LLM Jailbreaking

Junxi Chen, Junhao Dong, Xiaohua Xie

The paper introduces an adaptive probe-based steering method that significantly improves the robustness and effectiveness of LLM jailbreaking without requiring extra prompts or manual tuning.

View →
cs.CLcs.CRRecentMay 9, 2026

BiAxisAudit: A Novel Framework to Evaluate LLM Bias Across Prompt Sensitivity and Response-Layer Divergence

Jialing Gan, Junhao Dong, Songze Li

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing…

View →