Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings
https://arxiv.org/abs/2311.18034

Look-back Decoding for Open-Ended Text Generation
https://arxiv.org/abs/2305.13477

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models
https://arxiv.org/abs/2310.10378

Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning
https://arxiv.org/abs/2305.14160

Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models
https://arxiv.org/abs/2311.05746

Some highlights from EMNLP 2023

https://health-nlp.com/posts/emnlp23.html

#EMNLP2023 #ml #machinelearning #NLProc #NLP #ai #artificialintelligence #conference

By popular request: We analyzed over 40,000 papers and computed 2022 Impact Factors for all 88 Computer Science Conferences listed on csrankings.org and CORE A*. See them here: https://github.com/eickhoff/csimpact

#computerscience #academia #conferences

Join our team! Tübingen is hiring an Assistant Professor of Human Language Technologies.

https://www.nature.com/naturecareers/job/12807722

#nlproc #ai #ml #jobs #academia

Our lab (and the wider IMPRS community in Tübingen and Stuttgart) are admitting doctoral researchers for the 2024 cycle.

Apply by Nov 15th!

http://imprs.is.mpg.de/application

#jobs #phd #gradschool

@Ian web-crawled news and Q&A? It didn't raise eyebrows for me as far as the paper is concerned, but I would be curious to see how their guarantees hold up in other domains. Especially the ones for which society most worries about LLM cheats (education, medicine, research...).

SparseGPT: Massive Language Models can be Accurately Pruned in One-Shot
https://arxiv.org/abs/2301.00774

Hyena Hierarchy: Towards Larger Convolutional Language Models
https://arxiv.org/abs/2302.10866

SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification
https://arxiv.org/abs/2301.11309

Retrieval-Augmented Multimodal Language Modeling
https://openreview.net/pdf?id=VZ8bs0fwoO

Whose Opinions do Language Models Reflect?
https://arxiv.org/abs/2303.17548

A Watermark for Large Language Models
https://arxiv.org/abs/2301.10226

Some highlights from ICML 2023

https://health-nlp.com/posts/icml23.html

#icml #ml #machinelearning #NLProc #NLP #ai #artificialintelligence #conference

More 2022 CS Conference Impact Factors!

AAAI has an impact factor of 15.02

https://health-nlp.com/posts/2022_journal_impact_factors_for_CS_conferences.html

#conference #conferencepaper #computerscience #science #academia #impactfactors #machinelearning #ai #NLProc #NLP #ir #AAAI

Hurra, Schibsted, for your key role in developing a Norwegian language model. Hope the rest of the Nordics join

https://schibsted.com/news/schibsteds-key-role-in-developing-a-norwegian-language-model/

#llm #ai #monopoly

#weird #corpus #request #NLProc #DigitalHumanities

i'd like to get a pdf of the official 7th grade state history books (e.g., Texas History, Illinois History) for each US state in 2001 or the same in text format...for reasons...can anyone help me figure out how to query *something* for this? please boost