Papers by Wenbo Jiang
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training (2026.findings-acl)
Copied to clipboard
Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen, Wenbo Jiang, Guowen Xu, Yang Liu, Michael Backes, Yang Zhang
| Challenge: | Misaligned large language models can magnify harm by exploiting them to undermine safety . et al., 2022b; Bai e.t., 2023): misalignment, realignment and model-specific resistance are important . |
| Approach: | They evaluate four methods to identify a mechanism asymmetry between attack and defense . they find that ORPO is most effective for misalignment, but DPO excels in realignment . |
| Outcome: | The proposed methods show a mechanism asymmetry between attack and defense . the proposed methods excel in realignment, but at the expense of model utility . |
RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Experiments show that reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs) but requires a key prerequisite: the model must already be able to generate high-utility reasoning paths with non-negligible probability. |
| Approach: | They propose a framework that uses answer-conditioned reasoning as a variational surrogate for question-only reasoning. |
| Outcome: | Experiments on 11 benchmarks and 3 models show that RAVR reduces hesitation, strengthens conclusion consolidation, and promotes problem-specific strategies in reasoning. |
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Audio-Language Models (LALMs) are increasingly being deployed in real-world applications, yet their robustness against malicious audio injection remains underexplored. |
| Approach: | They quantitatively assess their vulnerabilities and resilience using metrics: the Defense Success Rate, Context Robustness Score, and Judgment Robustic Index. |
| Outcome: | The proposed models demonstrate significant performance disparities across four attack scenarios. |