"WikiChat: Combating Hallucination of Large Language Models by Few-Shot Grounding on Wikipedia" (Semnani et al, 2023) oval.cs.stanford.edu/local-papers/s…

"Wikidata, with its over 12 billion facts, can be used to ground LLMs to improve their factuality," reducing hallucinations arxiv.org/pdf/2305.14202… github.com/stanford-oval/… #SPARQL

Stanford’s CS 224V is hosting the final project expo on Wed, Dec. 6th, 3:00 - 5:30pm in Gates CS Building. ~50 teams worked to create LLM-powered conversational assistants. This is a great chance to meet top students in conversational assistant technology! web.stanford.edu/class/cs224v/

We introduce WikiChat, an LLM-based chatbot that almost never hallucinates, has high conversationality and low latency. Read more in our #EMNLP2023 findings paper arxiv.org/abs/2305.14292 Check out our demo: wikichat.genie.stanford.edu Or try our code: github.com/stanford-oval/… #NLProc

Can we teach LLMs to write long articles from scratch, grounded in trustworthy sources? Do Wikipedia editors think this can assist them? 📣Announcing STORM, a system that writes Wikipedia-like articles based on Internet search. I now use STORM in my daily research!🧵

3 OVAL projects are awarded 2024-2025 Magic Grants! “African History from the Bottom Up with LLM-Augmented Agents”, Sina Semnani et al. “Cross-Lingual Multi-Perspective News”, Jialiang Xu et al. “DataTalk: All Documents and Data, All at Once, All Verified”, Shicheng Liu et al.

Big congrats to the WikiChat team led by Sina Semnani !

Announcing WikiChat v2.0! 🌎Multilingual support for 🇺🇸🇨🇳🇪🇸🇵🇹🇷🇺🇩🇪🇮🇷🇯🇵🇫🇷🇮🇹 🔎Improved info retrieval with BGE-M3 embeddings & Qdrant ⚡Optimized pipeline and expanded LLM support 🔗Compatible with LangChain and Chainlit Code: github.com/stanford-oval/… #NLProc

🌱Excited to introduce SPINACH, a Knowledge Base Question Answering agent & dataset on Wikidata, presented at EMNLP 2024! It combines LLMs, semantic parsing and graph traversal to set a new SOTA & is actively used by the Wikidata community.