Related papers: Pico: A Modular Framework for Hypothesis-Driven Sm…

Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhance trust and task accuracy. Yet existing methods face…

Training language models (LMs) and their application agents is increasingly costly due to large datasets and models, making test failures difficult to bear. Simplified language environments serve as primordial training and testing grounds,…

Significant scientific discoveries have driven the progress of human civilisation. The explosion of scientific literature and data has created information barriers across disciplines that have slowed the pace of scientific discovery. Large…

Large Language Models (LLMs) have emerged as powerful candidates to inform clinical decision-making processes. While these models play an increasingly prominent role in shaping the digital landscape, two growing concerns emerge in…

Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary systems with tens or hundreds of billions of parameters. Such reliance limits reproducibility and…

Generative AI increasingly supports educational design tasks, e.g., through Large Language Models (LLMs), demonstrating the capability to design assessment questions that are aligned with pedagogical frameworks (e.g., Bloom's taxonomy).…

Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex and often…

Multilingual Large Language Models (MLLMs) represent a pivotal advancement in democratizing artificial intelligence across linguistic boundaries. While theoretical foundations are well-established, practical implementation guidelines remain…

Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on…

We review discourses about the philosophy of science in qualitative research and evidence from cognitive linguistics in order to ground a framework for discussing the use of Large Language Models (LLMs) to support the qualitative analysis…

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

While large language models (LLMs) have introduced novel paradigms in science and education, their adoption in higher education is constrained by inherent limitations. These include a tendency to produce inaccuracies and high computational…

Modern language models (LMs) pose a new challenge in capability assessment. Static benchmarks inevitably saturate without providing confidence in the deployment tolerances of LM-based systems, but developers nonetheless claim that their…

We introduce a novel framework, LM-Guided CoT, that leverages a lightweight (i.e., <1B) language model (LM) for guiding a black-box large (i.e., >10B) LM in reasoning tasks. Specifically, the lightweight LM first generates a rationale for…

Language models have gained significant interest due to their general-purpose capabilities, which appear to emerge as models are scaled to increasingly larger parameter sizes. However, these large models impose stringent requirements on…

Small Language Models (SLMs) have gained substantial attention due to their ability to execute diverse language tasks successfully while using fewer computer resources. These models are particularly ideal for deployment in limited…

Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms and risking confirmation bias. We introduce a simple,…

With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that the ensemble of multiple simple biases still exerts a significant adverse impact on LLMs.…

This work presents an analytical framework for the design and analysis of LLM-based algorithms, i.e., algorithms that contain one or multiple calls of large language models (LLMs) as sub-routines and critically rely on the capabilities of…

Large language models (LLMs) increasingly help people solve problems, from debugging code to repairing machinery. This process requires generating plausible hypotheses from partial descriptions, then updating them as more information…