Show newer
arXiv - CSCL

mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs. (arXiv:2307.06930v2 [cs.CV] UPDATED) 

arxiv.org/abs/2307.06930

0
arXiv - CSCL

On decoder-only architecture for speech-to-text and large language model integration. (arXiv:2307.03917v3 [eess.AS] UPDATED) 

arxiv.org/abs/2307.03917

0
arXiv - CSCL

Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments. (arXiv:2307.03354v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.03354

0
arXiv - CSCL

Textbooks Are All You Need. (arXiv:2306.11644v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.11644

0
arXiv - CSCL

Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models. (arXiv:2306.08018v3 [q-bio.QM] UPDATED) 

arxiv.org/abs/2306.08018

0
arXiv - CSCL

Enhancing Robustness of AI Offensive Code Generators via Data Augmentation. (arXiv:2306.05079v2 [cs.LG] UPDATED) 

arxiv.org/abs/2306.05079

0
arXiv - CSCL

Stable Anisotropic Regularization. (arXiv:2305.19358v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.19358

0
arXiv - CSCL

Passive learning of active causal strategies in agents and language models. (arXiv:2305.16183v2 [cs.LG] UPDATED) 

arxiv.org/abs/2305.16183

0
arXiv - CSCL

Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation. (arXiv:2305.15852v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15852

0
arXiv - CSCL

STAR: Improving Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models. (arXiv:2305.15090v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15090

0
arXiv - CSCL

Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs. (arXiv:2305.14279v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14279

0
arXiv - CSCL

Unsupervised ASR via Cross-Lingual Pseudo-Labeling. (arXiv:2305.13330v2 [eess.AS] UPDATED) 

arxiv.org/abs/2305.13330

0
arXiv - CSCL

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. (arXiv:2305.11738v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11738

0
arXiv - CSCL

RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought. (arXiv:2305.11499v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11499

0
arXiv - CSCL

Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning. (arXiv:2305.10865v2 [cs.LG] UPDATED) 

arxiv.org/abs/2305.10865

0
arXiv - CSCL

ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing. (arXiv:2305.09770v5 [cs.HC] UPDATED) 

arxiv.org/abs/2305.09770

0
arXiv - CSCL

Working Memory Capacity of ChatGPT: An Empirical Study. (arXiv:2305.03731v3 [cs.AI] UPDATED) 

arxiv.org/abs/2305.03731

0
arXiv - CSCL

Factify 2: A Multimodal Fake News and Satire News Dataset. (arXiv:2304.03897v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.03897

0
arXiv - CSCL

Memotion 3: Dataset on Sentiment and Emotion Analysis of Codemixed Hindi-English Memes. (arXiv:2303.09892v3 [cs.CL] UPDATED) 

arxiv.org/abs/2303.09892

0
arXiv - CSCL

IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models. (arXiv:2303.03124v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.03124

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.

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy