Hasil untuk "Greek philology and language"

Ming Cheung

Since the introduction of ChatGPT, large language models (LLMs) have demonstrated significant utility in various tasks, such as answering questions through retrieval-augmented generation. Context can be retrieved using a vectorized database, serving as a foundation for LLMs to generate responses. However, hallucinations in responses can undermine the reliability of LLMs in practical applications, and they are not easily detectable in the absence of ground truth, particularly in question-and-answer scenarios. This paper proposes a framework that integrates multiple small language models to verify responses generated by LLMs using the retrieved context from a vectorized database. By breaking down the responses into individual sentences and utilizing the probability of generating "Yes" tokens from the outputs of multiple models for a given set of questions, responses, and relevant context, hallucinations can be detected. The proposed framework is validated through experiments with real datasets comprising over 100 sets of questions, answers, and contexts, including responses with fully and partially correct sentences. The results demonstrate a 10\% improvement in F1 scores for detecting correct responses compared to hallucinations, indicating that multiple small language models can be effectively employed for answer verification, providing a scalable and efficient solution for both academic and practical applications.

Belén Agüera-Marco, Itziar Gonzalez-Dios

In this work, we present LengClaro2023, a dataset of legal-administrative texts in Spanish. Based on the most frequently used procedures from the Spanish Social Security website, we have created for each text two simplified equivalents. The first version follows the recommendations provided by arText claro. The second version incorporates additional recommendations from plain language guidelines to explore further potential improvements in the system. The linguistic resource created in this work can be used for evaluating automatic text simplification (ATS) systems in Spanish.

Xiaoyu Luo, Yiyi Chen, Johannes Bjerva et al.

We present the first comprehensive study of Memorization in Multilingual Large Language Models (MLLMs), analyzing 95 languages using models across diverse model scales, architectures, and memorization definitions. As MLLMs are increasingly deployed, understanding their memorization behavior has become critical. Yet prior work has focused primarily on monolingual models, leaving multilingual memorization underexplored, despite the inherently long-tailed nature of training corpora. We find that the prevailing assumption, that memorization is highly correlated with training data availability, fails to fully explain memorization patterns in MLLMs. We hypothesize that the conventional focus on monolingual settings, effectively treating languages in isolation, may obscure the true patterns of memorization. To address this, we propose a novel graph-based correlation metric that incorporates language similarity to analyze cross-lingual memorization. Our analysis reveals that among similar languages, those with fewer training tokens tend to exhibit higher memorization, a trend that only emerges when cross-lingual relationships are explicitly modeled. These findings underscore the importance of a \textit{language-aware} perspective in evaluating and mitigating memorization vulnerabilities in MLLMs. This also constitutes empirical evidence that language similarity both explains Memorization in MLLMs and underpins Cross-lingual Transferability, with broad implications for multilingual NLP.

Antje Hellwig

Susanne Aretz

Silke Schepp, Susanne Aretz, Jochen Sauer

Fangru Lin, Daniel Altshuler, Janet B. Pierrehumbert

Scalar adjectives pertain to various domain scales and vary in intensity within each scale (e.g. certain is more intense than likely on the likelihood scale). Scalar implicatures arise from the consideration of alternative statements which could have been made. They can be triggered by scalar adjectives and require listeners to reason pragmatically about them. Some scalar adjectives are more likely to trigger scalar implicatures than others. This phenomenon is referred to as scalar diversity. In this study, we probe different families of Large Language Models such as GPT-4 for their knowledge of the lexical semantics of scalar adjectives and one specific aspect of their pragmatics, namely scalar diversity. We find that they encode rich lexical-semantic information about scalar adjectives. However, the rich lexical-semantic knowledge does not entail a good understanding of scalar diversity. We also compare current models of different sizes and complexities and find that larger models are not always better. Finally, we explain our probing results by leveraging linguistic intuitions and model training objectives.

Gunjan Balde, Soumyadeep Roy, Mainack Mondal et al.

In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. Current approaches trivially append the target domain-specific vocabulary at the end of the PLM vocabulary. This approach leads to a lower priority score and causes sub-optimal tokenization in BPE that iteratively uses merge rules to tokenize a given text. To mitigate this issue, we propose AdaptBPE where the BPE tokenization initialization phase is modified to first perform the longest string matching on the added (target) vocabulary before tokenizing at the character level. We perform an extensive evaluation of AdaptBPE versus the standard BPE over various classification and summarization tasks; AdaptBPE improves by 3.57% (in terms of accuracy) and 1.87% (in terms of Rouge-L), respectively. AdaptBPE for MEDVOC works particularly well when reference summaries have high OOV concentration or are longer in length. We also conduct a human evaluation, revealing that AdaptBPE generates more relevant and more faithful summaries as compared to MEDVOC. We make our codebase publicly available at https://github.com/gb-kgp/adaptbpe.

Matīss Rikters, Sanita Reinsone

At the beginning of 2022, a simplistic word-guessing game took the world by storm and was further adapted to many languages beyond the original English version. In this paper, we examine the strategies of daily word-guessing game players that have evolved during a period of over two years. A survey gathered from 25% of frequent players reveals their strategies and motivations for continuing the daily journey. We also explore the capability of several popular open-access large language model systems and open-source models at comprehending and playing the game in two different languages. Results highlight the struggles of certain models to maintain correct guess length and generate repetitions, as well as hallucinations of non-existent words and inflections.

Kostas Karpouzis

This paper explores the ethical implications of integrating Artificial Intelligence (AI) in educational settings, from primary schools to universities, while drawing insights from ancient Greek philosophy to address emerging concerns. As AI technologies increasingly influence learning environments, they offer novel opportunities for personalized learning, efficient assessment, and data-driven decision-making. However, these advancements also raise critical ethical questions regarding data privacy, algorithmic bias, student autonomy, and the changing roles of educators. This research examines specific use cases of AI in education, analyzing both their potential benefits and drawbacks. By revisiting the philosophical principles of ancient Greek thinkers such as Socrates, Aristotle, and Plato, we discuss how their writings can guide the ethical implementation of AI in modern education. The paper argues that while AI presents significant challenges, a balanced approach informed by classical philosophical thought can lead to an ethically sound transformation of education. It emphasizes the evolving role of teachers as facilitators and the importance of fostering student initiative in AI-rich environments.

Andrea Busto-Castiñeira, Francisco J. González-Castaño, Silvia García-Méndez et al.

In recent years, the field of Natural Language Generation (NLG) has been boosted by the recent advances in deep learning technologies. Nonetheless, these new data-intensive methods introduce language-dependent disparities in NLG as the main training data sets are in English. Also, most neural NLG systems use decoder-only (causal) transformer language models, which work well for English, but were not designed with other languages in mind. In this work we depart from the hypothesis that they may introduce generation bias in target languages with less rigid word ordering, subject omission, or different attachment preferences for relative clauses, so that for these target languages other language generation strategies may be more desirable. This paper first compares causal and non-causal language modeling for English and Spanish, two languages with different grammatical structures and over 1.5 billion and 0.5 billion speakers, respectively. For this purpose, we define a novel metric of average causal and non-causal context-conditioned entropy of the grammatical category distribution for both languages as an information-theoretic a priori approach. The evaluation of natural text sources (such as training data) in both languages reveals lower average non-causal conditional entropy in Spanish and lower causal conditional entropy in English. According to this experiment, Spanish is more predictable than English given a non-causal context. Then, by applying a conditional relative entropy metric to text generation experiments, we obtain as insights that the best performance is respectively achieved with causal NLG in English, and with non-causal NLG in Spanish. These insights support further research in NLG in Spanish using bidirectional transformer language models.

Paloma Piot, Javier Parapar

Hate speech is a harmful form of online expression, often manifesting as derogatory posts. It is a significant risk in digital environments. With the rise of Large Language Models (LLMs), there is concern about their potential to replicate hate speech patterns, given their training on vast amounts of unmoderated internet data. Understanding how LLMs respond to hate speech is crucial for their responsible deployment. However, the behaviour of LLMs towards hate speech has been limited compared. This paper investigates the reactions of seven state-of-the-art LLMs (LLaMA 2, Vicuna, LLaMA 3, Mistral, GPT-3.5, GPT-4, and Gemini Pro) to hate speech. Through qualitative analysis, we aim to reveal the spectrum of responses these models produce, highlighting their capacity to handle hate speech inputs. We also discuss strategies to mitigate hate speech generation by LLMs, particularly through fine-tuning and guideline guardrailing. Finally, we explore the models' responses to hate speech framed in politically correct language.

Yi-Cheng Lin, Tzu-Quan Lin, Chih-Kai Yang et al.

Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability. However, these models may amplify biases present in training data, potentially leading to biased access to information for marginalized groups. This work introduces a curated spoken bias evaluation toolkit and corresponding dataset. We evaluate gender bias in SILLMs across four semantic-related tasks: speech-to-text translation (STT), spoken coreference resolution (SCR), spoken sentence continuation (SSC), and spoken question answering (SQA). Our analysis reveals that bias levels are language-dependent and vary with different evaluation methods. Our findings emphasize the necessity of employing multiple approaches to comprehensively assess biases in SILLMs, providing insights for developing fairer SILLM systems.

Zunino, Maddalena Luisa

Come le altre, anche la ϝράτρα per gli Elei è un oracolo di Zeus Olimpio; in questo caso, il dio ordina di trattare lo straniero – e segretario – Patrias come fosse un eleo, quando sia vittima di una maledizione. Il protagonismo dell’ellanodica nella procedura di giustizia che viene stabilita e il ricorso alla punizione della frusta ambientano inoltre quella procedura (che dimostra anche una certa competenza ‘panellenica’ degli Elei) e il reato che deve punire nel santuario di Olimpia. Appare infine richiesta anche da un più rigoroso rispetto dello spazio a disposizione la nuova proposta di integrazione della lacuna all’inizio della linea 9.

Gelone, Marcello

Sul pendio di Monte di Vico a Ischia si trovava un’iscrizione che ricordava l’erezione di una fortificazione ad opera di due personaggi con nomi oschi e di alcuni soldati. Nel riportare le diverse ipotesi avanzate sul suo contesto storico, si condivide la più recente e altrettanto trascurata: i due personaggi erano arconti di Neapolis che approntarono le difese di Aenaria in occasione della Prima o Seconda guerra punica. Riprendendo questa tesi, si forniscono nuove riflessioni sull’arcontato a Neapolis e un completo commento storico del documento, del quale si vuole evidenziare l’importanza per la storia della costituzione della città.

Petros Marazopoulos, Eirini Sevastikoglou

Badr AlKhamissi, Siddharth Verma, Ping Yu et al.

In this paper, we conduct a thorough investigation into the reasoning capabilities of Large Language Models (LLMs), focusing specifically on the Open Pretrained Transformers (OPT) models as a representative of such models. Our study entails finetuning three different sizes of OPT on a carefully curated reasoning corpus, resulting in two sets of finetuned models: OPT-R, finetuned without explanations, and OPT-RE, finetuned with explanations. We then evaluate all models on 57 out-of-domain tasks drawn from the SUPER-NATURALINSTRUCTIONS benchmark, covering 26 distinct reasoning skills, utilizing three prompting techniques. Through a comprehensive grid of 27 configurations and 6,156 test evaluations, we investigate the dimensions of finetuning, prompting, and scale to understand the role of explanations on different reasoning skills. Our findings reveal that having explanations in the fewshot exemplar has no significant impact on the model's performance when the model is finetuned, while positively affecting the non-finetuned counterpart. Moreover, we observe a slight yet consistent increase in classification accuracy as we incorporate explanations during prompting and finetuning, respectively. Finally, we offer insights on which skills benefit the most from incorporating explanations during finetuning and prompting, such as Numerical (+20.4%) and Analogical (+13.9%) reasoning, as well as skills that exhibit negligible or negative effects.

Schyan Zafar, Geoff K. Nicholls

Word meanings change over time, and word senses evolve, emerge or die out in the process. For ancient languages, where the corpora are often small and sparse, modelling such changes accurately proves challenging, and quantifying uncertainty in sense-change estimates consequently becomes important. GASC (Genre-Aware Semantic Change) and DiSC (Diachronic Sense Change) are existing generative models that have been used to analyse sense change for target words from an ancient Greek text corpus, using unsupervised learning without the help of any pre-training. These models represent the senses of a given target word such as "kosmos" (meaning decoration, order or world) as distributions over context words, and sense prevalence as a distribution over senses. The models are fitted using Markov Chain Monte Carlo (MCMC) methods to measure temporal changes in these representations. This paper introduces EDiSC, an Embedded DiSC model, which combines word embeddings with DiSC to provide superior model performance. It is shown empirically that EDiSC offers improved predictive accuracy, ground-truth recovery and uncertainty quantification, as well as better sampling efficiency and scalability properties with MCMC methods. The challenges of fitting these models are also discussed.

Thomas Doepner

Young-Ho Kim, Sungdong Kim, Minsuk Chang et al.

Current natural language interaction for self-tracking tools largely depends on bespoke implementation optimized for a specific tracking theme and data format, which is neither generalizable nor scalable to a tremendous design space of self-tracking. However, training machine learning models in the context of self-tracking is challenging due to the wide variety of tracking topics and data formats. In this paper, we propose a novel NLP task for self-tracking that extracts close- and open-ended information from a retrospective activity log described as a plain text, and a domain-agnostic, GPT-3-based NLU framework that performs this task. The framework augments the prompt using synthetic samples to transform the task into 10-shot learning, to address a cold-start problem in bootstrapping a new tracking topic. Our preliminary evaluation suggests that our approach significantly outperforms the baseline QA models. Going further, we discuss future application domains toward which the NLP and HCI researchers can collaborate.