We're heading to DIA from June 14-18 in Philly.
DIA brings together key stakeholders in life sciences across regulatory, clinical, safety, medical affairs, quality, and policy. We want to meet as many of you as we can and hear how AI is actually changing the day-to-day of your
Elicit
1,678 posts
- Replying to @elicitorg
- Can Elicit's full-text screening recall every relevant paper in a systematic review? We evaluated Elicit's recall using 74 Cochrane reviews and 377 studies. The results: 99.5% Paper-level recall 94.8% Per-criterion accuracy For teams running systematic reviews, this means
- As AI scales from basic tasks to complex automation, the ability to rigorously evaluate these tools is becoming the ultimate competitive advantage for life sciences teams. When AI starts drafting strategy documents or navigating autonomous goals, traditional metrics like
- We asked Elicit this question and got three answers 1. ITER's first plasma 2. Space – Artemis and SpaceX's missions have had their timelines pushed back 3. Solid state batteries. Toyota has pushed it's estimate of solid state EV batteries by about three yearsCan anyone think of a technology domain where the timelines for progress have gotten longer over the last 4 years? (Don’t look at other replies before thinking about it)
- GLP-1 receptor agonists like Ozempic have surprising effects! There is growing evidence that they 1. Reduce suicidal intentions 2. Reduce dementia 3. Reduce heavy drinking days for people suffering from alcoholism
- Elicit repostedTo what extent do scientists overall peak in their 20s? We asked Elicit this question and it gave us a really interesting answer - mostly not! - Most fields have it after their 20s - The mean Nobel winning age has gone up by about a decade - Experimental Nobel-winning
- To what extent do scientists overall peak in their 20s? We asked Elicit this question and it gave us a really interesting answer - mostly not! - Most fields have it after their 20s - The mean Nobel winning age has gone up by about a decade - Experimental Nobel-winning
01:21Mathematicians and scientists often peak in their 20s. Why? Maybe older scientists become stuck in their ways. Or maybe younger researchers feel free to be more creative. But @jacobkimmel's hypothesis is that this isn't because of social factors at all - it's evolution: - Elicit repostedMy work at Elicit is out! We spent a lot of time trying to build the world's best systematic review evaluations. I might be wrong, but I think this is the largest AI assisted SLR dataset in the *world* by 10x!!* We benchmark against ~994 papers versus ~100 for the next largestHow well does Elicit's semantic search work for systematic reviews? Cochrane reviews are the gold standard for evidence synthesis in health and medicine. We sampled 888 reviews across 12 MeSH areas. For each Cochrane systematic review, we ran Elicit using only the review title
- Does Elicit's abstract screening meet the sensitivity requirements of systematic reviews, while also maintaining high specificity? We evaluated Elicit on this stage using 108 Cochrane reviews. Our dataset included 931 studies that should be screened in, and 5,162 that should be
- When we launched the upgraded Elicit systematic review last month, we talked a lot about speed. Under the hood, here are the key features doing the actual work: Search - Boolean and MeSH keyword queries alongside high-recall semantic search - Autotranslate search strategies
00:00 - How well does Elicit's semantic search work for systematic reviews? Cochrane reviews are the gold standard for evidence synthesis in health and medicine. We sampled 888 reviews across 12 MeSH areas. For each Cochrane systematic review, we ran Elicit using only the review title















