Can LLMs Identify Critical Limitations within Scientific Research? A Systematic Evaluation on AI Research Papers

Peer review is fundamental to scientific research, but the growing volume of publications has intensified the challenges of this expertiseintensive process. While LLMs show promise in various scientific tasks, their potential to assist with peer review, particularly in identifying paper limitations, remains understudied. We first present a comprehensive taxonomy of limitation types in scientific research, with a focus on AI. Guided by this taxonomy, for studying limitations, we present LIMITGEN, the first comprehensive benchmark for evaluating LLMs' capability to support early-stage feedback and complement human peer review. Our benchmark consists of two subsets: LIM-ITGEN-Syn, a synthetic dataset carefully created through controlled perturbations of highquality papers, and LIMITGEN-Human, a collection of real human-written limitations. To improve the ability of LLM systems to identify limitations, we augment them with literature retrieval, which is essential for grounding identifying limitations in prior scientific findings. Our approach enhances the capabilities of LLM systems to generate limitations in research papers, enabling them to provide more concrete and constructive feedback. Data yale-nlp/LimitGen Code yale-nlp/LimitGen * Equal Contributions. RQ1: How well do LLM-based systems perform in identifying limitations within scientific research? RQ2: Can RAG enhance LLMs' ability to identify limitations and provide constructive suggestions? RQ3: How can this research be applied in real-world scenarios to assist human researchers in improving their work? Read the following scientific paper and generate major limitations in this paper about its xxx.