A peek into token bias: Large language models are not yet genuine reasoners

B Jiang, Y **e, Z Hao, X Wang, T Mallick, WJ Su… - arxiv preprint arxiv …, 2024 - arxiv.org
This study introduces a hypothesis-testing framework to assess whether large language
models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We …

When Geoscience Meets Foundation Models: Toward a general geoscience artificial intelligence system

H Zhang, JJ Xu, HW Cui, L Li, Y Yang… - … and Remote Sensing …, 2024 - ieeexplore.ieee.org
Artificial intelligence (AI) has significantly advanced Earth sciences, yet its full potential in to
comprehensively modeling Earth's complex dynamics remains unrealized. Geoscience …

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 …

Towards Rationality in Language and Multimodal Agents: A Survey

B Jiang, Y **e, X Wang, Y Yuan, Z Hao, X Bai… - arxiv preprint arxiv …, 2024 - arxiv.org
Rationality is the quality of being guided by reason, characterized by decision-making that
aligns with evidence and logical principles. It plays a crucial role in reliable problem-solving …

Harnessing Large Language Models for Disaster Management: A Survey

Z Lei, Y Dong, W Li, R Ding, Q Wang, J Li - arxiv preprint arxiv …, 2025 - arxiv.org
Large language models (LLMs) have revolutionized scientific research with their exceptional
capabilities and transformed various fields. Among their practical applications, LLMs have …

Pre-trained Graphformer-based Ranking at Web-scale Search

Y Li, H **ong, L Kong, Z Sun, H Chen, S Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Both Transformer and Graph Neural Networks (GNNs) have been employed in the domain
of learning to rank (LTR). However, these approaches adhere to two distinct yet …

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 …