Don't miss our #ACL2023 tutorial on Retrieval-based LMs and Applications this Sunday! acl2023-retrieval-lm.github.io with Sewon Min, Zexuan Zhong, Danqi Chen We'll cover everything from architecture design and training to exploring applications and tackling open challenges! [1/2]

Try DeepOnto: A Python package recently implemented for ontology engineering with deep learning and language models (arxiv.org/abs/2307.03067), Github: github.com/KRR-Oxford/Dee……. By @lawhy_AI Jiaoyan Chen Hang Dong Ian Horrocks, etc. #ontology #KnowledgeGraphs #LLM #PLM #OWL

How can we humans verify the truthfulness of LLM outputs (or any claims you see on the Internet)? Should we ask ChatGPT (#LLMs)? Search on Google (retrieval)? Are they complementary? Tldr: LLMs Help Humans Verify Truthfulness - Except When They Are Convincingly Wrong! 1/n

My favorite Gemini demo:

Happy to share our new preprint on understanding how reasoning emerges from language model pre-training: arxiv.org/abs/2402.03268 We hypothesize that language models can aggregate reasoning paths seen in pre-training data to draw new conclusions at inference time.