Chengzhi Zhang
5 papers · Latest:
Enhancing Research Idea Generation through Combinatorial Innovation and Multi-Agent Iterative Search Strategies
This paper introduces a multi-agent iterative search strategy using LLMs to generate diverse and novel research ideas, outperforming existing methods.
Impact of large language models on peer review opinions from a fine-grained perspective: Evidence from top conference proceedings in AI
This study reveals that LLMs make peer reviews longer and more fluent but reduce focus on deep evaluative aspects like originality.
Enhancing Unsupervised Keyword Extraction in Academic Papers through Integrating Highlights with Abstract
This paper shows that integrating academic paper highlights with abstracts significantly improves unsupervised keyword extraction performance.
Beyond Single-Dimension Novelty: How Combinations of Theory, Method, and Results-based Novelty Shape Scientific Impact
Research shows combinations of novelty, especially results-based alone, significantly impact scientific citations more than all three types.
NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment
NovBench is introduced as the first benchmark to evaluate large language models' ability to assess research paper novelty, revealing current LLMs' limitations.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.