Improving causal reasoning in large language models: A survey
Causal reasoning (CR) is a crucial aspect of intelligence, essential for problem-solving,
decision-making, and understanding the world. While large language models (LLMs) can …
decision-making, and understanding the world. While large language models (LLMs) can …
Humans learn language from situated communicative interactions. What about machines?
K Beuls, P Van Eecke - Computational Linguistics, 2024 - direct.mit.edu
Humans acquire their native languages by taking part in communicative interactions with
their caregivers. These interactions are meaningful, intentional, and situated in their …
their caregivers. These interactions are meaningful, intentional, and situated in their …
The secrets to high-level green technology innovation of China's waste power battery recycling enterprises
J Jiao, Y Chen, J Li, S Yang - Journal of Environmental Management, 2025 - Elsevier
Green technology innovation (GTI) in China's waste power battery recycling (WPBR) sector
is a key driver for sustainable resource management, environmental protection, and …
is a key driver for sustainable resource management, environmental protection, and …
Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities
F Kankowski, T Solstad, S Zarriess, O Bott - arXiv preprint arXiv …, 2025 - arxiv.org
In this paper, we compare data generated with mono-and multilingual LLMs spanning a
range of model sizes with data provided by human participants in an experimental setting …
range of model sizes with data provided by human participants in an experimental setting …
Large language models fail to derive atypicality inferences in a human-like manner
Recent studies have claimed that large language models (LLMs) are capable of drawing
pragmatic inferences (Qiu et al., 2023; Hu et al., 2022; Barattieri di San Pietro et al., 2023) …
pragmatic inferences (Qiu et al., 2023; Hu et al., 2022; Barattieri di San Pietro et al., 2023) …