Show newer
arXiv - CSCL

Mitigating Hallucinations of Large Language Models via Knowledge Consistent Alignment. (arXiv:2401.10768v1 [cs.CL]) 

arxiv.org/abs/2401.10768

0
arXiv - CSCL

Multimodal Sentiment Analysis with Missing Modality: A Knowledge-Transfer Approach. (arXiv:2401.10747v1 [cs.SD]) 

arxiv.org/abs/2401.10747

0
arXiv - CSCL

Structured Code Representations Enable Data-Efficient Adaptation of Code Language Models. (arXiv:2401.10716v1 [cs.CL]) 

arxiv.org/abs/2401.10716

0
arXiv - CSCL

Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge. (arXiv:2401.10712v1 [cs.CV]) 

arxiv.org/abs/2401.10712

0
arXiv - CSCL

Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering. (arXiv:2401.10711v1 [cs.CV]) 

arxiv.org/abs/2401.10711

0
arXiv - CSCL

LangBridge: Multilingual Reasoning Without Multilingual Supervision. (arXiv:2401.10695v1 [cs.CL]) 

arxiv.org/abs/2401.10695

0
arXiv - CSCL

A Simple Framework to Accelerate Multilingual Language Model for Monolingual Text Generation. (arXiv:2401.10660v1 [cs.CL]) 

arxiv.org/abs/2401.10660

0
arXiv - CSCL

Attentive Fusion: A Transformer-based Approach to Multimodal Hate Speech Detection. (arXiv:2401.10653v1 [cs.CL]) 

arxiv.org/abs/2401.10653

0
arXiv - CSCL

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models. (arXiv:2401.10647v1 [cs.CL]) 

arxiv.org/abs/2401.10647

0
arXiv - CSCL

PHOENIX: Open-Source Language Adaption for Direct Preference Optimization. (arXiv:2401.10580v1 [cs.CL]) 

arxiv.org/abs/2401.10580

0
arXiv - CSCL

Self-training from Self-memory in Data-to-text Generation. (arXiv:2401.10567v1 [cs.CL]) 

arxiv.org/abs/2401.10567

0
arXiv - CSCL

OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy. (arXiv:2401.10559v1 [cs.LG]) 

arxiv.org/abs/2401.10559

0
arXiv - CSCL

Multilingual acoustic word embeddings for zero-resource languages. (arXiv:2401.10543v1 [eess.AS]) 

arxiv.org/abs/2401.10543

0
arXiv - CSCL

Speech Swin-Transformer: Exploring a Hierarchical Transformer with Shifted Windows for Speech Emotion Recognition. (arXiv:2401.10536v1 [cs.CL]) 

arxiv.org/abs/2401.10536

0
arXiv - CSCL

The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases. (arXiv:2401.10535v1 [cs.CL]) 

arxiv.org/abs/2401.10535

0
arXiv - CSCL

Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences. (arXiv:2401.10529v1 [cs.CV]) 

arxiv.org/abs/2401.10529

0
arXiv - CSCL

Cross-lingual Editing in Multilingual Language Models. (arXiv:2401.10521v1 [cs.CL]) 

arxiv.org/abs/2401.10521

0
arXiv - CSCL

A match made in consistency heaven: when large language models meet evolutionary algorithms. (arXiv:2401.10510v1 [cs.NE]) 

arxiv.org/abs/2401.10510

0
arXiv - CSCL

FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis. (arXiv:2401.10506v1 [cs.CL]) 

arxiv.org/abs/2401.10506

0
arXiv - CSCL

Knowledge Fusion of Large Language Models. (arXiv:2401.10491v1 [cs.CL]) 

arxiv.org/abs/2401.10491

0
Show older
Qoto Mastodon

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

Trending now

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy