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

Kai-Wei Chang

4 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

NLP×3AI×3Crypto×2Audio and Speech Processing×1Society×1ML×1

Frequent co-authors

Charith Peris2×
Aram Galstyan2×
Rahul Gupta2×
Ziqing Man1×
Di Wu1×
Jia-Chen Gu1×

Research Timeline

2026
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial prompts, leading to enhanced safety robustness.

SWAN: Semantic Watermarking with Abstract Meaning Representation

SWAN introduces a novel, training-free framework that embeds watermarks directly into the semantic structure of a sentence using Abstract Meaning Representation (AMR), achieving superior robustness against paraphrasing compared to existing methods.

Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering

This paper analyzes the internal mechanism of full-duplex spoken language models and proposes a method to improve their ability to handle interruptions.

KEEP-Bench: Evaluating Evidence Preservation in Context Compression

The authors introduce KEEP-Bench, a diagnostic benchmark to assess compression faithfulness and evaluate the performance of context compression models.

Highlighted terms show continued research focus across papers

Papers

cs.CLEmpiricalRecentOct 19, 2026

KEEP-Bench: Evaluating Evidence Preservation in Context Compression

Ziqing Man, Di Wu, Jia-Chen Gu, Junyi Zhang +2 more

The authors introduce KEEP-Bench, a diagnostic benchmark to assess compression faithfulness and evaluate the performance of context compression models.

View →
cs.CLcs.AIeess.ASEmpirical
Recent
Jun 9, 2026

Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering

Cheng-Kuang Chang, Kai-Wei Chang, Alexander H. Liu, James Glass

This paper analyzes the internal mechanism of full-duplex spoken language models and proposes a method to improve their ability to handle interruptions.

View →
cs.CLcs.AIcs.CRMay 5, 2026

SWAN: Semantic Watermarking with Abstract Meaning Representation

Ziping Ye, Gourab Dey, Christos Christodoulopoulos, Charith Peris +6 more

SWAN introduces a novel, training-free framework that embeds watermarks directly into the semantic structure of a sentence using Abstract Meaning Representation (AMR), achieving superior robustness ag…

View →
cs.AIcs.CRcs.LGApr 20, 2026

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System

Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna +4 more

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

View →