This study explores the use of low-shot prompt-ing techniques for the lemmatization of ancient cuneiform languages using Large Language Models (LLMs). To structure the input data and systematically design effective prompt tem-plates, we employed a hierarchical clustering approach based on Levenshtein distance The prompt design followed established engineer-ing patterns, incorporating instructional and response-guiding elements to enhance model comprehension. We employed the In-Context Learning (ICL) prompting strategy, selecting example words primarily based on lemma fre-quency, ensuring a balance between commonly occurring words and rare cases to improve gen-eralization. During testing on the develop-ment set, prompts included structured examples and explicit formatting rules, with accuracy assessed by comparing model predictions to ground truth lemmas. The results showed that model performance varied significantly across different configurations, with accuracy reach-ing approximately 90% in the best case for in-vocabulary words and around 9% in the best case for out-of-vocabulary (OOV) words. De-spite resource constraints and the lack of input from a language expert, oour findings suggest that prompt engineering strategies hold promise for improving LLM performance in cuneiform language lemmatization.

Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption generation and music-related query responses. MusiLingo employs a single projection layer to align music representations from the pre-trained frozen music audio model MERT (CITATION) with a frozen LLM, bridging the gap between music audio and textual contexts. We train it on an extensive music caption dataset and fine-tune it with instructional data. Due to the scarcity of high-quality music Q&A datasets, we created the MusicInstruct (MI) dataset from captions in the MusicCaps datasets, tailored for open-ended music inquiries. Empirical evaluations demonstrate its competitive performance in generating music captions and composing music-related Q&A pairs. Our introduced dataset enables notable advancements beyond previous ones.

The study of Sumerian texts often requires domain experts to examine a vast number of tables. However, the absence of user-friendly tools for this process poses challenges and consumes significant time. In addressing this issue, we introduce an open-source library that empowers domain experts with minimal technical expertise to automate manual and repetitive tasks using a no-code dashboard. Our library includes an information extraction module that enables the automatic extraction of names and relations based on the user-defined lists of name tags and relation types. By utilizing the tool to facilitate the creation of knowledge graphs which is a data representation method offering insights into the relationships among entities in the data, we demonstrate its practical application in the analysis of Sumerian texts.

This paper presents our study in exploring the task of named entity recognition (NER) in a low resource setting, focusing on few-shot learning on the Sumerian NER task. The Sumerian language is deemed as an extremely low-resource language due to that (1) it is a long dead language, (2) highly skilled language experts are extremely scarce. NER on Sumerian text is important in that it helps identify the actors and entities active in a given period of time from the collections of tens of thousands of texts in building socio-economic networks of the archives of interest. As a text classification task, NER tends to become challenging when the amount of annotated data is limited or the model is required to handle new classes. The Sumerian NER is no exception. In this work, we propose to use two few-shot learning systems, ProtoBERT and NNShot, to the Sumerian NER task. Our experiments show that the ProtoBERT NER generally outperforms both the NNShot NER and the fully supervised BERT NER in low resource settings on the predictions of rare classes. In particular, F1-score of ProtoBERT on unseen entity types on our test set has achieved 89.6% that is significantly better than the F1-score of 84.3% of the BERT NER.

We examine the task of generating unique content for the spell system of the tabletop roleplaying game Dungeons and Dragons Fifth Edition using several generative language models. Due to the descriptive nature of the game Dungeons and Dragons Fifth Edition, it presents a number of interesting avenues for generation and analysis of text. In particular, the “spell” system of the game has interesting and unique characteristics as it is primarily made up of high level and descriptive text but has many of the game’s main rules embedded with that text. Thus, we examine the capabilities of several models on the task of generating new content for this game, evaluating the performance through the use of both score-based methods and a survey on the best performing model to determine how the generated content conforms to the rules of the game and how well they might be used in the game.