PhonologyBench: Evaluating Phonological Skills of Large Language Models

• URL: http://arxiv.org/abs/2404.02456v2
• Date: Fri, 5 Apr 2024 04:55:24 GMT
• Title: PhonologyBench: Evaluating Phonological Skills of Large Language Models
• Authors: Ashima Suvarna, Harshita Khandelwal, Nanyun Peng,
• Abstract summary: Phonology, the study of speech's structure and pronunciation rules, is a critical yet often overlooked component in Large Language Model (LLM) research. We present PhonologyBench, a novel benchmark consisting of three diagnostic tasks designed to explicitly test the phonological skills of LLMs. We observe a significant gap of 17% and 45% on Rhyme Word Generation and Syllable counting, respectively, when compared to humans.
• Score: 57.80997670335227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Phonology, the study of speech's structure and pronunciation rules, is a critical yet often overlooked component in Large Language Model (LLM) research. LLMs are widely used in various downstream applications that leverage phonology such as educational tools and poetry generation. Moreover, LLMs can potentially learn imperfect associations between orthographic and phonological forms from the training data. Thus, it is imperative to benchmark the phonological skills of LLMs. To this end, we present PhonologyBench, a novel benchmark consisting of three diagnostic tasks designed to explicitly test the phonological skills of LLMs in English: grapheme-to-phoneme conversion, syllable counting, and rhyme word generation. Despite having no access to speech data, LLMs showcased notable performance on the PhonologyBench tasks. However, we observe a significant gap of 17% and 45% on Rhyme Word Generation and Syllable counting, respectively, when compared to humans. Our findings underscore the importance of studying LLM performance on phonological tasks that inadvertently impact real-world applications. Furthermore, we encourage researchers to choose LLMs that perform well on the phonological task that is closely related to the downstream application since we find that no single model consistently outperforms the others on all the tasks.

Related papers

• Prompt and circumstance: A word-by-word LLM prompting approach to interlinear glossing for low-resource languages [6.4977738682502295]
  We investigate the effectiveness of a retrieval-based LLM prompting approach to glossing, applied to the seven languages from the SIGMORPHON 2023 shared task. Our system beats the BERT-based shared task baseline for every language in the morpheme-level score category. In a case study on Tsez, we ask the LLM to automatically create and follow linguistic instructions, reducing errors on a confusing grammatical feature.
  arXiv  Detail & Related papers  (2025-02-13T21:23:16Z)
• One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks [68.33068005789116]
  We present the first study aimed at objectively assessing the fairness and robustness of Large Language Models (LLMs) in handling dialects in canonical reasoning tasks. We hire AAVE speakers, including experts with computer science backgrounds, to rewrite seven popular benchmarks, such as HumanEval and GSM8K. Our findings reveal that textbfalmost all of these widely used models show significant brittleness and unfairness to queries in AAVE.
  arXiv  Detail & Related papers  (2024-10-14T18:44:23Z)
• Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas [7.585433383340306]
  We show that tokenization-free, phoneme- and grapheme-based language models can achieve strong linguistic performance. Our findings suggest a promising direction for creating more linguistically plausible language models.
  arXiv  Detail & Related papers  (2024-10-02T12:36:08Z)
• Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models [117.20416338476856]
  Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. We propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons.
  arXiv  Detail & Related papers  (2024-02-26T09:36:05Z)
• Beware of Words: Evaluating the Lexical Diversity of Conversational LLMs using ChatGPT as Case Study [3.0059120458540383]
  We consider the evaluation of the lexical richness of the text generated by conversational Large Language Models (LLMs) and how it depends on the model parameters. The results show how lexical richness depends on the version of ChatGPT and some of its parameters, such as the presence penalty, or on the role assigned to the model.
  arXiv  Detail & Related papers  (2024-02-11T13:41:17Z)
• Boosting Large Language Model for Speech Synthesis: An Empirical Study [86.89548753080432]
  Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. We conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthesis model VALL-E. We compare three integration methods between LLMs and speech models, including directly fine-tuned LLMs, superposed layers of LLMs and VALL-E, and coupled LLMs and VALL-E using LLMs as a powerful text encoder
  arXiv  Detail & Related papers  (2023-12-30T14:20:04Z)
• Exploring the Potential of Large Language Models in Computational Argumentation [54.85665903448207]
  Large language models (LLMs) have demonstrated impressive capabilities in understanding context and generating natural language. This work aims to embark on an assessment of LLMs, such as ChatGPT, Flan models, and LLaMA2 models, in both zero-shot and few-shot settings.
  arXiv  Detail & Related papers  (2023-11-15T15:12:15Z)
• Establishing Vocabulary Tests as a Benchmark for Evaluating Large Language Models [2.7013338932521416]
  We advocate for the revival of vocabulary tests as a valuable tool for assessing Large Language Models (LLMs) performance. We evaluate seven LLMs using two vocabulary test formats across two languages and uncover surprising gaps in their lexical knowledge.
  arXiv  Detail & Related papers  (2023-10-23T08:45:12Z)
• Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study [0.0]
  This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems. Our primary focus is to investigate the potential of using an LLM's in-context learning capabilities to enhance the performance of ASR systems.
  arXiv  Detail & Related papers  (2023-07-13T02:31:55Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.