Show newer

Introspective Tips: Large Language Model for In-Context Decision Making. (arXiv:2305.11598v1 [cs.AI]) 

Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation. (arXiv:2305.11596v1 [cs.CL]) 

Diving into the Inter-Consistency of Large Language Models: An Insightful Analysis through Debate. (arXiv:2305.11595v1 [cs.CL]) 

IKDSumm: Incorporating Key-phrases into BERT for extractive Disaster Tweet Summarization. (arXiv:2305.11592v1 [cs.CL]) 

Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment. (arXiv:2305.11579v1 [cs.CL]) 

Language-universal phonetic encoder for low-resource speech recognition. (arXiv:2305.11576v1 [eess.AS]) 

Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition. (arXiv:2305.11569v1 [eess.AS]) 

Decouple knowledge from paramters for plug-and-play language modeling. (arXiv:2305.11564v1 [cs.CL]) 

Blank-regularized CTC for Frame Skipping in Neural Transducer. (arXiv:2305.11558v1 [eess.AS]) 

ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings. (arXiv:2305.11554v1 [cs.CL]) 

Unsupervised Scientific Abstract Segmentation with Normalized Mutual Information. (arXiv:2305.11553v1 [cs.CL]) 

Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens. (arXiv:2305.11550v1 [cs.CL]) 

Constructing Word-Context-Coupled Space Aligned with Associative Knowledge Relations for Interpretable Language Modeling. (arXiv:2305.11543v1 [cs.CL]) 

Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering. (arXiv:2305.11541v1 [cs.CL]) 

Efficient Cross-Lingual Transfer for Chinese Stable Diffusion with Images as Pivots. (arXiv:2305.11540v1 [cs.CV]) 

PORTRAIT: a hybrid aPproach tO cReate extractive ground-TRuth summAry for dIsaster evenT. (arXiv:2305.11536v1 [cs.CL]) 

A Sequence-to-Sequence Approach for Arabic Pronoun Resolution. (arXiv:2305.11529v1 [cs.CL]) 

InstructIE: A Chinese Instruction-based Information Extraction Dataset. (arXiv:2305.11527v1 [cs.CL]) 

DiffuSIA: A Spiral Interaction Architecture for Encoder-Decoder Text Diffusion. (arXiv:2305.11517v1 [cs.CL]) 

Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment. (arXiv:2305.11516v1 [cs.CL]) 

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.