Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models.
Natural Language Processing Papers
30K posts
Natural Language Processing Papers
@HEI
New Natural Language Processing papers from arxiv.org: natural language processing. Thank you to arXiv for use of its open access interoperability.
- Evaluating Telugu Proficiency in Large Language Models_ A Comparative Analysis of ChatGPT and Gemini. arxiv.org/abs/2404.19369
- TextGram: Towards a better domain-adaptive pretraining. arxiv.org/abs/2404.18228
- DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines.
- Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages.
- LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models. arxiv.org/abs/2503.11898
- A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods. arxiv.org/abs/2501.13947
- Fast Word Error Rate Estimation Using Self-Supervised Representations For Speech And Text. arxiv.org/abs/2310.08225
- Unnatural Languages Are Not Bugs but Features for LLMs.
- TabLib: A Dataset of 627M Tables with Context. arxiv.org/abs/2310.07875
- LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.
- Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation service.
- LLMs as Repositories of Factual Knowledge: Limitations and Solutions. arxiv.org/abs/2501.12774
- Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation. arxiv.org/abs/2411.18337
