R to @BlancheMinerva: I'm enjoying using @ConsensusNLP plugin for finding current research while using @OpenAI chat gpt plus. Excited to have tools like this!

Has IKIGAI a positive influence on health? Yes! Scientific studies confirm that. Please have a look: Results from @ConsensusNLP: https://consensus.app/results/?q=Has%20IKIGAI%20a%20positive%20influence%20on%20health%3F&synthesize=on

R to @KarlEtzel: FYI for anyone interested in the literature "Chronic supplementation of caffeine during creatine loading may interfere with the beneficial effect of creatine, according to a systematic review of ten studies." https://www.consensus.app/details/supplementation-caffeine-creatine-loading-effect-elosegui/d53fa357bcfe5143b7d0afaeae305ad8/ Via @ConsensusNLP

RT by @ConsensusNLP: Cet outil est génial pour rechercher facilement et rapidement des études scientifiques publiées. Très utile en ces temps de désinformation et de manipulation. https://consensus.app/

R to @domenic_rosati: The last thing I will say is it doesn't really help with pointing to the relevancy issues we are facing - it seems to still really have a bias towards semantic similarity evals which is simple to solve for but doesn't get at our users relvency problems of citation appropriateness

R to @domenic_rosati: I have made a RAGAs fork to remdiate this since their code is tied to sentences but it didn't seem to help... So for now it only really works for Context sentences and doesn't help with grounding in longer form text which is kind of important in scientific RAG systems

R to @domenic_rosati: Context Precision/Relevancy doesn't seem to work very well for longform contexts and outputs. We can boost our scores 0.4 points on an in-house dataset of 200 user questions just by using sentences from papers instead of paragraphs... this seems wrong.

R to @domenic_rosati: Just to follow up on this there are a number of problems I think with RAGAs that make it maybe less interesting... its really easy to just maximize the score on trivial tweeks but im not sure they are meaningful

R to @ResearchHubF: 3. Consensus @ConsensusNLP is known for its indubitable scientific findings. It provides information from published sources which makes it a reliable source. Also, through peer-reviewed research, it scans each topic thoroughly, so it can provide a well-researched article.

R to @ConsensusNLP: Your post is a fantastic source of inspiration

RT by @SuhnyllaKler: ChatGPT may have read all the studies (seriously, there should be a list of training data), but falls for the hype. When trying to understand the literature we should probably ask it less for answers and more to run a proper search for us ( here with the @ConsensusNLP plugin).

R to @scottsantens: Results from @ConsensusNLP https://consensus.app/results/?q=do%20cash%20transfers%20reduce%20poverty%3F&synthesize=on

RT by @Vugar_Ibrahimov: 10 AI Apps to Accelerate Your Academic Research (updated, alphabetical order) [Bookmark 🔖 for later reference] 1⃣Consensus @ConsensusNLP ✅Find insights in research papers with evidence-based Answers 2⃣Elicit @elicitorg ✅Find articles & concepts and analyse papers 3⃣Litmaps @LitmapsApp ✅Find academic articles and visualise your research (one of the bests) 4⃣Perplexity @perplexity_ai ✅Search for any knowledge 5⃣ResearchRabbit @RsrchRabbit ✅Literature search, alerts, and more 6⃣Scite @scite ✅Find best articles and citations (one of the bests) 7⃣Scinapse @Scinapse_ ✅Search for papers, authors and trends 8⃣Scispace @scispace_ ✅Do hours worth of reading in minutes 9⃣Semantic Scholar @SemanticScholar ✅A free, AI-powered research tool for scientific literature 🔟Sourcely @sourcelyai ✅Finding academic sources in seconds (one of the bests)