Related papers: ConlangCrafter: Constructing Languages with a Mult…
Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode substantial cross-lingual knowledge in a unified semantic space, they often struggle to…
Large language models (LLMs), such as ChatGPT and Copilot, are transforming software development by automating code generation and, arguably, enable rapid prototyping, support education, and boost productivity. Therefore, correctness and…
Yes! In the present-day documenting and preserving endangered languages, the application of Large Language Models (LLMs) presents a promising approach. This paper explores how LLMs, particularly through in-context learning, can assist in…
Lyric generation is a popular sub-field of natural language generation that has seen growth in recent years. Pop lyrics are of unique interest due to the genre's unique style and content, in addition to the high level of collaboration that…
Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel,…
Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept…
We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse compositional spatial reasoning ability. The generation of DecompSR allows users to…
Large language models (LLMs) excel in program synthesis, yet their capacity for neural architecture design -- balancing syntactic reliability, performance, and structural novelty -- remains underexplored. We present a closed-loop…
Despite the success of generative pre-trained language models on a series of text generation tasks, they still suffer in cases where reasoning over underlying commonsense knowledge is required during generation. Existing approaches that…
This paper explores the multilingual commonsense generation abilities of Large Language Models (LLMs). To facilitate this investigation, we introduce MULTICOM, a novel benchmark that extends the COCOTEROS dataset to four languages: English,…
Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers…
Large language models appear quite creative, often performing on par with the average human on creative tasks. However, research on LLM creativity has focused solely on \textit{products}, with little attention on the creative…
The integration of Large Language Models (LLMs) into the scientific ecosystem raises fundamental questions about the creativity and originality of AI-generated research. Recent work has identified ``smart plagiarism'' as a concern in…
Slang is a commonly used type of informal language that poses a daunting challenge to NLP systems. Recent advances in large language models (LLMs), however, have made the problem more approachable. While LLM agents are becoming more widely…
Text-to-image (T2I) generation has made remarkable progress, yet existing systems still lack intuitive control over spatial composition, object consistency, and multi-step editing. We present $\textbf{LayerCraft}$, a modular framework that…
Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all…
Analogies help learners understand unfamiliar concepts by relating them to known concepts. Despite recent advances, large language models (LLMs) continue to struggle to generate analogies of comparable quality to those produced by humans.…
Designing robotic hand morphologies for diverse manipulation tasks requires balancing dexterity, manufacturability, and task-specific functionality. While open-source frameworks and parametric tools support reproducible design, they still…
Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on…
Natural language generation (NLG) is a critical component in spoken dialogue systems. Classic NLG can be divided into two phases: (1) sentence planning: deciding on the overall sentence structure, (2) surface realization: determining…