Related papers: AstroReview: An LLM-driven Multi-Agent Framework f…
Peer review is central to scientific quality, yet reliance on simple heuristics -- lazy thinking -- has lowered standards. Prior work treats lazy thinking detection as a single-label task, but review segments may exhibit multiple issues,…
Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…
The automation of scientific discovery has been a long-standing goal within the research community, driven by the potential to accelerate knowledge creation. While significant progress has been made using commercial large language models…
The software engineering research community faces a systemic crisis: peer review is failing under growing submissions, misaligned incentives, and reviewer fatigue. Community surveys reveal that researchers perceive the process as "broken."…
The efficacy of large language models (LLMs) on downstream tasks usually hinges on instruction tuning, which relies critically on the quality of training data. Unfortunately, collecting high-quality and diverse data is both expensive and…
Telescope arrays are receiving increasing attention due to their promise of higher resource utilization, greater sky survey area, and higher frequency of full space-time monitoring than single telescopes. Compared with the ordinary…
Astronomy relies heavily on time domain observations. To maximize the scientific yield of such observations, astronomers must carefully match the observational cadence to the phenomena of interest. This presents significant scheduling…
Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks. Recent studies have explored human-like problem-solving strategies, such as…
Identifying and articulating limitations is essential for transparent and rigorous scientific research. However, zero-shot large language models (LLMs) approach often produce superficial or general limitation statements (e.g., dataset bias…
The automation of resume screening is a crucial aspect of the recruitment process in organizations. Automated resume screening systems often encompass a range of natural language processing (NLP) tasks. This paper introduces a novel Large…
The exponential growth of astronomical literature poses significant challenges for researchers navigating and synthesizing general insights or even domain-specific knowledge. We present Pathfinder, a machine learning framework designed to…
Large Language Models (LLMs) are increasingly utilized in scientific research assessment, particularly in automated paper review. However, existing LLM-based review systems face significant challenges, including limited domain expertise,…
Systematic reviews are fundamental to evidence-based medicine. Creating one is time-consuming and labour-intensive, mainly due to the need to screen, or assess, many studies for inclusion in the review. Several tools have been developed to…
Vision Language Models (VLMs) have been applied to several specific domains and have shown strong problem-solving capabilities. However, astronomical imaging, a quite complex problem involving multidisciplinary knowledge and several…
We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for each query, harnessing the collective wisdom of multiple models with diverse strengths.…
Academic advising is critical to student success in higher education, yet high student-to-advisor ratios limit advisors' capacity to provide timely support, particularly during peak periods. Recent advances in Large Language Models (LLMs)…
Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of…
Automatic reviewing helps handle a large volume of papers, provides early feedback and quality control, reduces bias, and allows the analysis of trends. We evaluate the alignment of automatic paper reviews with human reviews using an arena…
As the volume of peer-reviewed research surges, scholars increasingly rely on social platforms for discovery, while authors invest considerable effort in promoting their work to ensure visibility and citations. To streamline this process…
One of the most important yet onerous tasks in the academic peer-reviewing process is composing meta-reviews, which involves assimilating diverse opinions from multiple expert peers, formulating one's self-judgment as a senior expert, and…