EMNLP 2023 Primer

Sebastian Ruder · 5 Dec 2023 · ruder.io ↗

3 korrents from this piece

Sebastian Ruder did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
Large language models remain limited in non-English settings, making further multilingual development an important research direction.

Their wordsLLMs are still limited in non-English settings and that making LLMs more multilingual is an important direction.
Our reading
The rise of closed-source large language models makes preserving an open culture of sharing knowledge and software important for NLP.

Their wordsIn light of the increasing number of closed-source LLMs, it is important to continue to promote an open culture of sharing knowledge, data, and software, from which the NLP community has benefited greatly.
Our reading
Full fine-tuning of large language models has become too costly, making parameter-efficient fine-tuning methods necessary.

Their wordsFull fine-tuning of LLMs has become prohibitive and requires parameter-efficient methods instead.