Show newer
arXiv - CSCL

Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning. (arXiv:2310.08166v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.08166

0
arXiv - CSCL

Teaching Language Models to Hallucinate Less with Synthetic Tasks. (arXiv:2310.06827v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.06827

0
arXiv - CSCL

Exploring Embeddings for Measuring Text Relatedness: Unveiling Sentiments and Relationships in Online Comments. (arXiv:2310.05964v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.05964

0
arXiv - CSCL

DeBERTinha: A Multistep Approach to Adapt DebertaV3 XSmall for Brazilian Portuguese Natural Language Processing Task. (arXiv:2309.16844v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.16844

0
arXiv - CSCL

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs. (arXiv:2309.14356v2 [cs.LG] UPDATED) 

arxiv.org/abs/2309.14356

0
arXiv - CSCL

D-Separation for Causal Self-Explanation. (arXiv:2309.13391v2 [cs.AI] UPDATED) 

arxiv.org/abs/2309.13391

0
arXiv - CSCL

Evaluating the Ebb and Flow: An In-depth Analysis of Question-Answering Trends across Diverse Platforms. (arXiv:2309.05961v2 [cs.SI] UPDATED) 

arxiv.org/abs/2309.05961

0
arXiv - CSCL

Beyond Document Page Classification: Design, Datasets, and Challenges. (arXiv:2308.12896v3 [cs.CV] UPDATED) 

arxiv.org/abs/2308.12896

0
arXiv - CSCL

How is ChatGPT's behavior changing over time?. (arXiv:2307.09009v3 [cs.CL] UPDATED) 

arxiv.org/abs/2307.09009

0
arXiv - CSCL

Towards Personalized Cold-Start Recommendation with Prompts. (arXiv:2306.17256v3 [cs.IR] UPDATED) 

arxiv.org/abs/2306.17256

0
arXiv - CSCL

Propagating Knowledge Updates to LMs Through Distillation. (arXiv:2306.09306v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.09306

0
arXiv - CSCL

TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models. (arXiv:2306.06815v3 [cs.CR] UPDATED) 

arxiv.org/abs/2306.06815

0
arXiv - CSCL

Investigating the Effectiveness of ChatGPT in Mathematical Reasoning and Problem Solving: Evidence from the Vietnamese National High School Graduation Examination. (arXiv:2306.06331v3 [cs.CL] UPDATED) 

arxiv.org/abs/2306.06331

0
arXiv - CSCL

FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering. (arXiv:2306.05523v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.05523

0
arXiv - CSCL

How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources. (arXiv:2306.04751v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.04751

0
arXiv - CSCL

Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models. (arXiv:2306.04746v2 [stat.ME] UPDATED) 

arxiv.org/abs/2306.04746

0
arXiv - CSCL

Multimodal Fusion Interactions: A Study of Human and Automatic Quantification. (arXiv:2306.04125v2 [cs.LG] UPDATED) 

arxiv.org/abs/2306.04125

0
arXiv - CSCL

Structural Similarities Between Language Models and Neural Response Measurements. (arXiv:2306.01930v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.01930

0
arXiv - CSCL

Learning Transformer Programs. (arXiv:2306.01128v2 [cs.LG] UPDATED) 

arxiv.org/abs/2306.01128

0
arXiv - CSCL

Faith and Fate: Limits of Transformers on Compositionality. (arXiv:2305.18654v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.18654

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