Show newer
arXiv - CSCL

SLiC-HF: Sequence Likelihood Calibration with Human Feedback. (arXiv:2305.10425v1 [cs.CL]) 

arxiv.org/abs/2305.10425

0
arXiv - CSCL

Extracting Blockchain Concepts from Text. (arXiv:2305.10408v1 [cs.IR]) 

arxiv.org/abs/2305.10408

0
arXiv - CSCL

BAD: BiAs Detection for Large Language Models in the context of candidate screening. (arXiv:2305.10407v1 [cs.CL]) 

arxiv.org/abs/2305.10407

0
arXiv - CSCL

PaLM 2 Technical Report. (arXiv:2305.10403v1 [cs.CL]) 

arxiv.org/abs/2305.10403

0
arXiv - CSCL

What You See is What You Read? Improving Text-Image Alignment Evaluation. (arXiv:2305.10400v1 [cs.CL]) 

arxiv.org/abs/2305.10400

0
arXiv - CSCL

Elaborative Simplification as Implicit Questions Under Discussion. (arXiv:2305.10387v1 [cs.CL]) 

arxiv.org/abs/2305.10387

0
arXiv - CSCL

Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties. (arXiv:2305.10384v1 [cs.LG]) 

arxiv.org/abs/2305.10384

0
arXiv - CSCL

Large-Scale Text Analysis Using Generative Language Models: A Case Study in Discovering Public Value Expressions in AI Patents. (arXiv:2305.10383v1 [cs.CL]) 

arxiv.org/abs/2305.10383

0
arXiv - CSCL

Evaluating Object Hallucination in Large Vision-Language Models. (arXiv:2305.10355v1 [cs.CV]) 

arxiv.org/abs/2305.10355

0
arXiv - CSCL

Interactive Learning of Hierarchical Tasks from Dialog with GPT. (arXiv:2305.10349v1 [cs.HC]) 

arxiv.org/abs/2305.10349

0
arXiv - CSCL

Using a Large Language Model to Control Speaking Style for Expressive TTS. (arXiv:2305.10321v1 [cs.CL]) 

arxiv.org/abs/2305.10321

0
arXiv - CSCL

LeTI: Learning to Generate from Textual Interactions. (arXiv:2305.10314v1 [cs.CL]) 

arxiv.org/abs/2305.10314

0
arXiv - CSCL

FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy. (arXiv:2305.10307v1 [cs.CL]) 

arxiv.org/abs/2305.10307

0
arXiv - CSCL

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective. (arXiv:2305.10306v1 [cs.CL]) 

arxiv.org/abs/2305.10306

0
arXiv - CSCL

Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks. (arXiv:2305.10284v1 [cs.CL]) 

arxiv.org/abs/2305.10284

0
arXiv - CSCL

Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models. (arXiv:2305.10276v1 [cs.CL]) 

arxiv.org/abs/2305.10276

0
arXiv - CSCL

Boosting Local Spectro-Temporal Features for Speech Analysis. (arXiv:2305.10270v1 [cs.CL]) 

arxiv.org/abs/2305.10270

0
arXiv - CSCL

Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability. (arXiv:2305.10266v1 [cs.CL]) 

arxiv.org/abs/2305.10266

0
arXiv - CSCL

M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models. (arXiv:2305.10263v1 [cs.CL]) 

arxiv.org/abs/2305.10263

0
arXiv - CSCL

MemoryBank: Enhancing Large Language Models with Long-Term Memory. (arXiv:2305.10250v1 [cs.CL]) 

arxiv.org/abs/2305.10250

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