Related papers: John Clark's Latin Verse Machine: 19th Century Com…
Small language models (SLMs) are inherently limited in knowledge-intensive tasks due to their constrained capacity. While test-time computation offers a path to enhanced performance, most approaches treat reasoning as a fixed or heuristic…
Uncertainty quantification (UQ) methods for large language models are predominantly designed by hand based on domain knowledge and heuristics, limiting their scalability and generality. We apply LLM-powered evolutionary search to…
We collect nine corpora of representative Chinese poetry for the time span of 1046 BCE and 1644 CE for studying the history of Chinese words, collocations, and patterns. By flexibly integrating our own tools, we are able to provide new…
Visual Entailment with natural language explanations aims to infer the relationship between a text-image pair and generate a sentence to explain the decision-making process. Previous methods rely mainly on a pre-trained vision-language…
Herewith, a fairly old concept is published for the first time and named "Lucas Interpretation". This has been implemented in a prototype, which has been proved useful in educational practice and has gained academic relevance with an…
The rapid development of large language models (LLMs) has extended text generation tasks into the literary domain. However, AI-generated literary creations has raised increasingly prominent issues of creative authenticity and ethics in…
Poetry generation has long been a challenge for artificial intelligence. In the scope of Japanese poetry generation, many researchers have paid attention to Haiku generation, but few have focused on Waka generation. To further explore the…
Computer poetry generation is our first step towards computer writing. Writing must have a theme. The current approaches of using sequence-to-sequence models with attention often produce non-thematic poems. We present a novel conditional…
We take the generation of Chinese classical poem lines as a sequence-to-sequence learning problem, and build a novel system based on the RNN Encoder-Decoder structure to generate quatrains (Jueju in Chinese), with a topic word as input. Our…
We present Erato, a framework designed to facilitate the automated evaluation of poetry, including that generated by poetry generation systems. Our framework employs a diverse set of features, and we offer a brief overview of Erato's…
This article presents the results of a study involving the translation of a short story by Kurt Vonnegut from English to Catalan and Dutch using three modalities: machine-translation (MT), post-editing (PE) and translation without aid (HT).…
This paper introduces the first \emph{self-evolving} logic synthesis framework, which leverages Large Language Model (LLM) agents to autonomously improve the source code of \textsc{ABC}, the widely adopted logic synthesis system. Our…
The rapid advancements in large language models (LLMs) have significantly improved their ability to generate natural language, making texts generated by LLMs increasingly indistinguishable from human-written texts. Recent research has…
To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions. However, the mainstream sequence-to-sequence approach of automatic solvers aims to decode a fixed solution…
Automatic algorithm configuration tools such as irace efficiently tune parameter values but leave algorithmic code unchanged. This paper introduces a first version of irace-evo, an extension of irace that integrates code evolution through…
We have developed a method for extracting the coherence features from a paragraph by matching similar words in its sentences. We conducted an experiment with a parallel German corpus containing 2000 human-created and 2000 machine-translated…
It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn…
The level of abstraction at which application experts reason about linear algebra computations and the level of abstraction used by developers of high-performance numerical linear algebra libraries do not match. The former is conveniently…
Periodic lattices have been widely explored for decades, owing to their peculiar vibrational behavior. On the other hand, certain types of aperiodic lattices have enabled new phenomena that may not be otherwise attainable in periodic ones.…
Effective generation of novel hypotheses is instrumental to scientific progress. So far, researchers have been the main powerhouse behind hypothesis generation by painstaking data analysis and thinking (also known as the Eureka moment). In…