Meta-Transformer: A Unified Framework for Multimodal Learning. (arXiv:2307.10802v1 [cs.CV])
Layer-wise Representation Fusion for Compositional Generalization. (arXiv:2307.10799v1 [cs.CL])
Extreme Multi-Label Skill Extraction Training using Large Language Models. (arXiv:2307.10778v1 [cs.CL])
Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition. (arXiv:2307.10757v1 [cs.SD])
Exploring Perspectives on the Impact of Artificial Intelligence on the Creativity of Knowledge Work: Beyond Mechanised Plagiarism and Stochastic Parrots. (arXiv:2307.10751v1 [cs.HC])
Large language models shape and are shaped by society: A survey of arXiv publication patterns. (arXiv:2307.10700v1 [cs.DL])
A Dataset and Strong Baselines for Classification of Czech News Texts. (arXiv:2307.10666v1 [cs.CL])
Exploring the Landscape of Natural Language Processing Research. (arXiv:2307.10652v1 [cs.CL])
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models. (arXiv:2307.10635v1 [cs.CL])
Generative Language Models on Nucleotide Sequences of Human Genes. (arXiv:2307.10634v1 [q-bio.GN])
Multi-Method Self-Training: Improving Code Generation With Text, And Vice Versa. (arXiv:2307.10633v1 [cs.CL])
A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos. (arXiv:2307.10587v1 [cs.CL])
Instruction-following Evaluation through Verbalizer Manipulation. (arXiv:2307.10558v1 [cs.CL])
Dynamic Large Language Models on Blockchains. (arXiv:2307.10549v1 [cs.CV])
Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models. (arXiv:2307.10522v1 [cs.CL])
Building Socio-culturally Inclusive Stereotype Resources with Community Engagement. (arXiv:2307.10514v1 [cs.CL])
IvyGPT: InteractiVe Chinese pathwaY language model in medical domain. (arXiv:2307.10512v1 [cs.CL])
General Debiasing for Multimodal Sentiment Analysis. (arXiv:2307.10511v1 [cs.CL])
(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs. (arXiv:2307.10490v1 [cs.CR])
SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval. (arXiv:2307.10488v1 [cs.IR])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl