A new instruction dataset for Arabic poetry tasks enables fine-tuned LLMs to generate poems matching user-specified styles, rhymes, and criteria, as shown by automated metrics and native-speaker evaluations.
ArXiv preprint
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Subword tokenization impairs phonological knowledge encoding in LMs, but an IPA-based fine-tuning method restores it with minimal impact on other capabilities.
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.
citing papers explorer
-
Instruction-Guided Poetry Generation in Arabic and Its Dialects
A new instruction dataset for Arabic poetry tasks enables fine-tuned LLMs to generate poems matching user-specified styles, rhymes, and criteria, as shown by automated metrics and native-speaker evaluations.
-
How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them
Subword tokenization impairs phonological knowledge encoding in LMs, but an IPA-based fine-tuning method restores it with minimal impact on other capabilities.
-
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.