Kai-Wei Chang
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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 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.
This paper analyzes the internal mechanism of full-duplex spoken language models and proposes a method to improve their ability to handle interruptions.
The authors introduce KEEP-Bench, a diagnostic benchmark to assess compression faithfulness and evaluate the performance of context compression models.
Papers
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.