Show newer
arXiv - CSCL

Flover: A Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference. (arXiv:2305.13484v2 [cs.DC] UPDATED) 

arxiv.org/abs/2305.13484

0
arXiv - CSCL

Adaptive Chameleon or Stubborn Sloth: Unraveling the Behavior of Large Language Models in Knowledge Clashes. (arXiv:2305.13300v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13300

0
arXiv - CSCL

AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web. (arXiv:2305.13117v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13117

0
arXiv - CSCL

Can Large Language Models emulate an inductive Thematic Analysis of semi-structured interviews? An exploration and provocation on the limits of the approach and the model. (arXiv:2305.13014v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13014

0
arXiv - CSCL

MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering. (arXiv:2305.12820v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12820

0
arXiv - CSCL

TheoremQA: A Theorem-driven Question Answering dataset. (arXiv:2305.12524v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12524

0
arXiv - CSCL

XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages. (arXiv:2305.11938v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11938

0
arXiv - CSCL

LLM Itself Can Read and Generate CXR Images. (arXiv:2305.11490v2 [cs.CV] UPDATED) 

arxiv.org/abs/2305.11490

0
arXiv - CSCL

Towards the Automatic Generation of Conversational Interfaces to Facilitate the Exploration of Tabular Data. (arXiv:2305.11326v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11326

0
arXiv - CSCL

Evidence of Meaning in Language Models Trained on Programs. (arXiv:2305.11169v2 [cs.LG] UPDATED) 

arxiv.org/abs/2305.11169

0
arXiv - CSCL

The Web Can Be Your Oyster for Improving Large Language Models. (arXiv:2305.10998v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.10998

0
arXiv - CSCL

DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining. (arXiv:2305.10429v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.10429

0
arXiv - CSCL

Better speech synthesis through scaling. (arXiv:2305.07243v2 [cs.SD] UPDATED) 

arxiv.org/abs/2305.07243

0
arXiv - CSCL

When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks. (arXiv:2305.06626v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.06626

0
arXiv - CSCL

Chain-of-Dictionary Prompting Elicits Translation in Large Language Models. (arXiv:2305.06575v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.06575

0
arXiv - CSCL

AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment. (arXiv:2305.04476v4 [eess.AS] UPDATED) 

arxiv.org/abs/2305.04476

0
arXiv - CSCL

LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions. (arXiv:2304.14402v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.14402

0
arXiv - CSCL

Why Does ChatGPT Fall Short in Providing Truthful Answers?. (arXiv:2304.10513v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.10513

0
arXiv - CSCL

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models. (arXiv:2304.09842v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.09842

0
arXiv - CSCL

Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data. (arXiv:2304.01196v3 [cs.CL] UPDATED) 

arxiv.org/abs/2304.01196

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