Related papers: Analogical Structure, Minimal Contextual Cues and …

Large language models (LLMs) have revolutionized the landscape of Natural Language Processing systems, but are computationally expensive. To reduce the cost without sacrificing performance, previous studies have explored various approaches…

Research in analogical reasoning suggests that higher-order cognitive functions such as abstract reasoning, far transfer, and creativity are founded on recognizing structural similarities among relational systems. Here we integrate theories…

Large Language Models (LLMs) demonstrate strong in-context learning abilities, yet their effectiveness in text classification depends heavily on prompt design and incurs substantial computational cost. Conformal In-Context Learning (CICLe)…

Recent studies suggest that very small language models (SLMs) can generate surprisingly coherent text when trained on simplified, child-directed corpora such as TinyStories. These findings have been interpreted as evidence that readability…

Large Language Models (LLMs) exhibit impressive performance across various domains but still struggle with arithmetic reasoning tasks. Recent work shows the effectiveness of prompt design methods in enhancing reasoning capabilities.…

The performance of modern software systems is critically dependent on their complex configuration options. Building accurate performance models to navigate this vast space requires effective sampling strategies, yet existing methods often…

Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based NLP tasks, suggesting a degree of deductive reasoning capability. However, it remains unclear to which extent LLMs, in both informal and…

The vital role of analogical reasoning in human cognition allows us to grasp novel concepts by linking them with familiar ones through shared relational structures. Despite the attention previous research has given to word analogies, this…

Context: Large Language Models (LLMs) are increasingly influencing software engineering practice and education. While prior studies examine their technical performance and classroom use, limited research provides cost-aware and empirically…

Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized…

Finding the best way of adapting pre-trained language models to a task is a big challenge in current NLP. Just like the previous generation of task-tuned models (TT), models that are adapted to tasks via in-context-learning (ICL) are robust…

Large Language Models (LLMs) have demonstrated great performance in few-shot In-Context Learning (ICL) for a variety of generative and discriminative chemical design tasks. The newly expanded context windows of LLMs can further improve ICL…

Large language models (LLMs) have shown remarkable abilities in different fields, including standard Natural Language Processing (NLP) tasks. To elicit knowledge from LLMs, prompts play a key role, consisting of natural language…

In-context learning (ICL) enables large language models (LLMs) to perform new tasks by prompting them with a sequence of training examples. However, it is known that ICL is very sensitive to the choice of training examples: randomly…

Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompting. However, they remain suboptimal in multi-turn interactions, often relying on incorrect…

Pretrained language models (PLMs) have shown remarkable few-shot learning capabilities when provided with properly formatted examples. However, selecting the "best" examples remains an open challenge. We propose a complexity-based prompt…

Large language models (LLMs) have shown a remarkable ability to learn and perform complex tasks through in-context learning (ICL). However, a comprehensive understanding of its internal mechanisms is still lacking. This paper explores the…

Instruction-tuned large language models (LLMs) employ structured templates, such as role markers and special tokens, to enforce format consistency during inference. However, we identify a critical limitation of such formatting: it induces a…

A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a…

As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorrect samples, leading to a sub-optimal performance.…