RT @seirasto: 🌟New Benchmark! 🌟. Do you work on RAG? Are you interested in Multi-Turn conversations? Very excited to share the new MTRAG be….

RT @danmcduff: See our ICML'24 position paper for more information:

RT @danmcduff: The @ResponsibleAIL License Generator ( is now live. If you have an #AI/#ML project consider using….

RT @seirasto: Are you building and evaluating RAG systems? Presenting InspectorRAGet a platform for easily analyzin….

RT @iamrana: Sunehri Masjid, near Udyog Bhavan.There are many Sunehri masjids in Delhi, but its the one near Udyog bhavan, from the Mughal….

RT @BigCodeProject: Exciting times: we are working on the next generation of StarCoder trained on a new dataset! 🚀. If you would like to ha….

Summer Internship: Interested in working on methods for reducing LLM hallucinations in conversations, developing suitable prompt-controls for enterprise-grade chat solutions, enabling trusted responses in LLMs and more? DM me!

RT @hanlinliii: We are so excited to host a panel of speakers for our upcoming #cscw2023 workshop on data licensing, web scraping, and crea….

RT @ResponsibleAIL: Given the waves of lawsuits filed against AI firms, our member Jenny Lee wrote a blog post providing some legal context….

RT @danmcduff: This has been a really exciting week for #RAIL ( - First #Llama2 was released with a RAIL-like licen….

RT @RealAAAI: Open Responsible AI Licenses (Open RAIL) are licenses designed to permit free and open access, re-use, and downstream distrib….

RT @Cyber_Clinics: Developers, researchers, & policymakers have been brainstorming ways to establish responsible #AI practices — is Respons….

RT @RealAAAI: Responsible AI Pubs Licenses are built on a model for behavioral-use that aims to reduce the risk of negative outcomes and mi….

RT @RealAAAI: AAAI announces a new way to release code and trained models associated with accepted papers. Through the use of an AI Pubs RA….

the paper announcements after the #emnlp anonymity deadline feels like there was a virtual conference with thousands of accepted papers! #NLProc.

Zero-shot prompting of both families of pre-trained models with pseudo-code prompts results in better performance than natural language prompts!

We converted the instructions of 132 tasks from the SuperNatural Instructions dataset to pseudo-code and prompted CodeGen 2B,6B and BLOOM 3B,7B using pseudo-code instructions and NL instructions!.

Could prompting with less ambiguous prompt styles, such as the use of pseudo-code, help improve the performance of pre-trained LLMs?.Our experiments suggest they could!. #NLProc #LLMs.

RT @leavittron: v excited to finally announce our new work that formalizes one of the most effective practices for training LLMs—something….

RT @mmitchell_ai: I am SO EXCITED about a FEW different ethics-relevant things on @huggingface. BIG THING AS OF *TODAY*: GATING of dataset….