R.V.Guha (@rv_guha) 's Twitter Profile
R.V.Guha

@rv_guha

ID: 20967973

calendar_today16-02-2009 07:01:58

5 Tweet

79 Takipçi

0 Takip Edilen

Neel Guha (@neelguha) 's Twitter Profile Photo

So proud to know the folks who built this, and so excited to see the myriad of ways in which it's used! blog.google/outreach-initi…

Neel Guha (@neelguha) 's Twitter Profile Photo

In case it's helpful, here's a really quick-and-dirty python library for segmenting legal texts (judicial opinions, statutes, etc) into sentences. It relies on hand-coded rules, and checks against Bluebook acronyms/abbreviations. github.com/neelguha/legal…

Neel Guha (@neelguha) 's Twitter Profile Photo

We’re excited to share Embroid: a method for “stitching” together an LLM with embedding information from multiple smaller models (e.g., BERT), allowing us to automatically correct LLM predictions without supervision. ✍️: hazyresearch.stanford.edu/blog/2023-08-1… 📜: arxiv.org/abs/2307.11031

We’re excited to share Embroid: a method for “stitching” together an LLM with embedding information from multiple smaller models (e.g., BERT), allowing us to automatically correct LLM predictions without supervision.

✍️: hazyresearch.stanford.edu/blog/2023-08-1…
📜: arxiv.org/abs/2307.11031
Neel Guha (@neelguha) 's Twitter Profile Photo

We’re beyond excited to share the first release of LegalBench–a collaboratively constructed open-source benchmark for evaluating legal reasoning in English large language models. 🔗hazyresearch.stanford.edu/legalbench/ 📜arxiv.org/abs/2308.11462

We’re beyond excited to share the first release of LegalBench–a collaboratively constructed open-source benchmark for evaluating legal reasoning in English large language models.

🔗hazyresearch.stanford.edu/legalbench/
📜arxiv.org/abs/2308.11462