Papers by Xinghao Yang

6 papers
Disentangled Information Bottleneck for Adversarial Text Defense (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies have proven that these deep models are super vulnerable to adversarial examples, which are slightly modified inputs.
Approach: They propose a novel text defense method that separates the robust and non-robust features with a disentangled two-line framework rather than the one-line compression network in IB.
Outcome: The proposed method outperforms six baselines on four datasets with accuracy improvements ranging from 3.8% to 20.7%.
Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance (2026.acl-long)

Copied to clipboard

Challenge: Existing token-level attacks have shown efficacy on open-source models but suffer from poor cross-model transferability.
Approach: They propose a framework to improve cross-model transferability by modifying model parameters and generating update directions according to differences in output distributions rather than parameter-space distances.
Outcome: The proposed framework improves cross-model transferability and success rates on open-source models.
I²B-LPO: Latent Policy Optimization via Iterative Information Bottleneck (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for large language model reasoning suffer from exploration collapse due to the semantic homogeneity of random rollouts.
Approach: They propose to use latent policy optimization via iterative information bottleneck to optimize reasoning trajectories by diversifying reasoning .
Outcome: Empirical results show that the proposed method achieves state-of-the-art performance with margins of up to 5.3% in accuracy and 7.4% in diversity metrics.
Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks (2024.emnlp-main)

Copied to clipboard

Challenge: Existing text attack methods are designed for English text, but robust implementation of Chinese text is understudied.
Approach: They propose an adaptive immune-based sound-shape code algorithm for Chinese text attacks . they leverage the Sound-Shape Code to generate natural substitutions .
Outcome: The proposed algorithm produces high-quality Chinese adversarial examples . it can reduce duplication of population and improve search ability .
Curr-ReFT: Overcoming Training Bottlenecks in Small-scale Vision-Language Models via Curriculum Reinforcement Finetuning (2025.findings-emnlp)

Copied to clipboard

Challenge: State-of-the-art vision-language models require massive scaling that limits practical deployment.
Approach: They propose to use supervised fine-tuning to train small-scale vision-language models but face out-of-domain collapse when trained with traditional supervised learning (SFT).
Outcome: Experiments show that curr-reFT achieves state-of-the-art performance across visual tasks in both in- and out-of domain settings and benchmarks.
Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods suffer from key information loss and difficulty in adjusting the length of compressed sequences based on documentation lengths.
Approach: They propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models.
Outcome: The proposed approach achieves comparable performance to the upper-bound baseline under 16x compression ratio.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations