Are we there yet? revealing the risks of utilizing large language models in scholarly peer review

R Ye, X Pang, J Chai, J Chen, Z Yin, Z **ang… - arxiv preprint arxiv …, 2024 - arxiv.org
Scholarly peer review is a cornerstone of scientific advancement, but the system is under
strain due to increasing manuscript submissions and the labor-intensive nature of the …

Multi-modal and multi-agent systems meet rationality: A survey

B Jiang, Y **e, X Wang, WJ Su, CJ Taylor… - ICML 2024 Workshop …, 2024 - openreview.net
Rationality is characterized by logical thinking and decision-making that align with evidence
and logical rules. This quality is essential for effective problem-solving, as it ensures that …

Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?

Y Huang, Z Yuan, Y Zhou, K Guo, X Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Large Language Models (LLMs) are increasingly employed for simulations, enabling
applications in role-playing agents and Computational Social Science (CSS). However, the …

Proteingpt: Multimodal llm for protein property prediction and structure understanding

Y **ao, E Sun, Y **, Q Wang, W Wang - arxiv preprint arxiv:2408.11363, 2024 - arxiv.org
Understanding biological processes, drug development, and biotechnological
advancements requires detailed analysis of protein structures and sequences, a task in …

Piecing It All Together: Verifying Multi-Hop Multimodal Claims

H Wang, A Rangapur, X Xu, Y Liang, H Gharwi… - arxiv preprint arxiv …, 2024 - arxiv.org
Existing claim verification datasets often do not require systems to perform complex
reasoning or effectively interpret multimodal evidence. To address this, we introduce a new …

From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents

X Mou, X Ding, Q He, L Wang, J Liang, X Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
Traditional sociological research often relies on human participation, which, though
effective, is expensive, challenging to scale, and with ethical concerns. Recent …

Scito2M: A 2 Million, 30-Year Cross-disciplinary Dataset for Temporal Scientometric Analysis

Y **, Y **ao, Y Wang, J Wang - arxiv preprint arxiv:2410.09510, 2024 - arxiv.org
Understanding the creation, evolution, and dissemination of scientific knowledge is crucial
for bridging diverse subject areas and addressing complex global challenges such as …

Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale

Y Li, H **ong, L Kong, J Bian, S Wang, G Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages
from retrieved content based on input queries. However, traditional LTR models encounter …

SEAGraph: Unveiling the Whole Story of Paper Review Comments

J Yu, J Tan, Z Ding, J Zhu, J Li, Y Cheng, Q Cui… - arxiv preprint arxiv …, 2024 - arxiv.org
Peer review, as a cornerstone of scientific research, ensures the integrity and quality of
scholarly work by providing authors with objective feedback for refinement. However, in the …

What Limits LLM-based Human Simulation: LLMs or Our Design?

Q Wang, J Wu, Z Tang, B Luo, N Chen, W Chen… - arxiv preprint arxiv …, 2025 - arxiv.org
We argue that advancing LLM-based human simulation requires addressing both LLM's
inherent limitations and simulation framework design challenges. Recent studies have …