Elicit @elicitorg Twitter profile | Pikagi

Pikagi

Elicit

@elicitorg

12,666

Followers

15

Following

106

Media

1,315

Statuses

The AI research assistant • Demos • Jobs

San Francisco, CA

https://t.co/A7wyxQPX9g

Joined October 2020

Don't wanna be here? Send us removal request.

Pinned Tweet

@elicitorg

Elicit

3 months

🚨 We completely overhauled our pricing! We now offer an UNLIMITED FREE TIER that is the most generous of any research tool. Searches, summaries, and chats are completely free and completely unlimited, every single month. We also launched Elicit Pro, a new plan specifically

Tweet media one

6

9

60

Last Seen Profiles

@frances_pai

@MehdiBzs

@hs2909

@AnonmasterAnon

@ArisoniaP

@Anne__K6051

@nwrnwr192000

@heresibyfoz

@TechWomen

@megamiandyami

@hectoribar16

@sido_erumesu

@alarym2

@bokeplokalmalam

@TheTrojanBlade

@madbair

@CirtonAc

@pacomarhuenda

@bokeplokalmalam

@wgtmy_

@ThomasWayneRil1

@Turk

@CryptoSA0

@FStuenke

@dame_ter

@amourviess

@gadahmobar11434

@stwmaniax

@ModnStoryteller

@nightkeepermx

@ammt409062691

@avisorr23

@ribboneels

@agensitp

@PCABlackpool

@MudCrewEvents

@elicitorg

Elicit

1 year

1/ Announcing our spinoff from @oughtinc into a public benefit corporation, our $9 million seed round, and a much more powerful Elicit! This new Elicit takes the components of the popular literature review workflow and extends them to automate more research workflows.

Tweet media one

14

69

316

@elicitorg

Elicit

7 months

Introducing Elicit Notebooks! Notebooks take your research broader & deeper, all on one page. You can now: - Run multiple queries on the same page - Combine papers across the Elicit database & your uploads - Combine papers across queries - Chat with papers - Select papers to

7

21

127

@elicitorg

Elicit

2 years

Language model-based tools are new technologies with exciting potential but some current limitations. This is V0 of sharing how Elicit works & where it doesn't so that researchers know how to integrate it into their workflows and what to expect from it.

Tweet card media

How to use Elicit responsibly | Ought

How Elicit works and where it doesn't

3

22

113

@elicitorg

Elicit

4 months

We’ve completely overhauled Elicit’s semantic search! Quality has almost doubled in some cases - Elicit search results will now contain 78% more relevant papers, if you are searching for papers for a systematic review. Across all Elicit searches, you will find 40% more relevant

Tweet media one

3

13

79

@elicitorg

Elicit

2 years

Elicit is surging in popularity! We've just had a big influx of new users in the last couple of hours 👋. Unfortunately, that means we've started hitting our rate-limits with some underlying service providers, causing slowness and some timeouts.

2

2

58

@elicitorg

Elicit

2 years

1/ Elicit now uses a custom-built semantic search engine that searches over 175 million titles and abstracts. This engine finds papers that are relevant to your query even if there is no keyword match. (The previous model was a keyword-semantic hybrid)

1

8

43

@elicitorg

Elicit

9 months

Elicit Plus now uses tables from papers for viewing & extracting data! 🧵

1

8

37

@elicitorg

Elicit

2 years

One underrated workflow in Elicit: build out a literature review starting from 1 paper. Instead of copying & pasting references or dealing with tab explosion as you're reading, you can collect a bunch of papers, then organize your "read next" list.

Tweet card media

Turn one paper into a literature review

Use Elicit to find and organize papers that cite each other. Sign up at: https://elicit.org/In this video, we cover how you can build a literature review wit...

www.youtube.com

3

6

34

@elicitorg

Elicit

8 months

While helping teams with systematic reviews and data extraction, we compared Elicit's accuracy to manual work by trained research assistants and staff (whatever the status quo was). For a fraction of the time and cost, we were able to significantly improve accuracy. We're hoping

Tweet media one

1

4

35

@elicitorg

Elicit

2 years

Elicit is featured in @nytimes !

Tweet media one

1

3

34

@elicitorg

Elicit

3 years

We're collecting datasets that researchers have tagged – like categorizing survey responses or types of AI orgs – to make a new NLP benchmark. If you want to advance ML research for tasks people care about and have a dataset to share, let us know!

Tweet card media

Raft Leaderboard - a Hugging Face Space by ought

0

7

33

@elicitorg

Elicit

4 months

We're continually working to put new search technologies to work for you. Our infrastructure engineer @VivaLaPanda_ walks through many of the traditional and machine learning approaches to semantic search in our latest blog post:

Tweet card media

From grep to SPLADE: a journey through semantic search

Full-text search, BERT, embeddings, query expansion, and more—what an app developer needs to know about modern search technologies.

blog.elicit.com

0

5

30

@elicitorg

Elicit

3 months

To make sure Elicit delivers the most trustworthy research results, we must constantly evaluate it, and we must do that *at scale*. In this post @etiennefd describes how we evaluate LLM output, the tradeoffs between trust, scale, and flexibility and how we find our way around

Tweet media one

7

7

30

@elicitorg

Elicit

1 year

Lastly, we're thrilled to be adding @fiftyyears @BasisSet @Julian @MythosVentures , Illusian, @arashf @mojombo @blakeweb @JeffDean @noahdgoodman @bentossell @labenz and other incredible angels to our team

Tweet card media

Elicit is building a tool to automate scientific literature review | TechCrunch

Elicit aims to develop a tool to automate the more tedious parts of the scientific literature review process.

0

2

29

@elicitorg

Elicit

14 days

🚨 Exciting news! We just launched the biggest shift in how you can use Elicit with your colleagues and friends to date. Introducing: Sharable Notebooks! 🎉

1

8

28

@elicitorg

Elicit

2 months

🚨 We’ve substantially improved Elicit’s answers across the app: - Summaries of top papers now have 78% fewer errors - Abstract summaries better follow your query with 88% fewer errors - Standard custom columns now have 37% fewer errors than before All the features above

1

4

27

@elicitorg

Elicit

1 year

2/ You can now upload up to 100 of your own papers to extract data from. Great for automating the screening or extraction steps of systematic reviews and meta-analyses.

1

2

27

@elicitorg

Elicit

1 year

4/ The most computationally intensive new workflow is "List of concepts." "List of concepts" searches across 200MM+ papers, finds examples of what you're looking for in each paper, then groups papers by concept. You can create lists of: - Datasets for medical imaging

Tweet media one

1

1

25

@elicitorg

Elicit

3 years

Together with @huggingface we're launching the RAFT benchmark to test the few-shot capabilities of language models on real-world tasks 📊. If you perform well, we may implement your solution in Elicit to help researchers! Find out more at .

Tweet card media

RAFT | Real-world Annotated Few-shot Tasks

RAFT is a few-shot classification benchmark that tests language models across multiple domains on economically valuable classification tasks with evaluation that mirrors deployment.

raft.elicit.org

1

6

24

@elicitorg

Elicit

1 year

Elicit raises $9 million and becomes a public benefit corporation

We're excited to share that Elicit has raised $9 million in seed funding. Elicit was born at Ought, a non-profit research organization, and is now an independent public benefit corporation. Like...

blog.elicit.com

1

5

23

@elicitorg

Elicit

4 years

Bet suggestion: If Biden gets between 328 and 382 electoral college votes, @FiveThirtyEight should pay @TheEconomist $6400. Otherwise, @TheEconomist should pay @FiveThirtyEight $3600. How did we generate this bet? 1/5

1

6

18

@elicitorg

Elicit

1 year

3/ The papers you upload are saved in your library (only visible to you) so that you don't have to keep uploading them. Eventually, you'll be able to upload 10,000+ papers, run more operations on them, organize into projects, and share collections with teammates.

Tweet media one

1

1

19

@elicitorg

Elicit

1 year

Introducing High-accuracy mode in Elicit! Data from papers can now be extracted at half the error rate and with much more customization.

Tweet media one

1

5

19

@elicitorg

Elicit

9 months

1/ You can now add natural language filters in your Elicit queries! If you try a query like "papers about the benefits of taking l-theanine published after 2020" Elicit will automatically filter to papers published after 2020.

1

7

18

@elicitorg

Elicit

1 year

7/ There is so much left to do! Help us build intuitive and general interfaces that can run language models at high accuracy and superhuman scale to automate important research -

Tweet media one

1

2

16

@elicitorg

Elicit

8 months

New tutorial explaining how to use Elicit to screen papers & extract data for systematic reviews and meta-analyses!

1

3

16

@elicitorg

Elicit

9 months

What's new in semantic search and retrieval? Informal tech talk by @elicitorg ML engineer Justin Reppert

1

3

16

@elicitorg

Elicit

1 year

- and a particularly exciting one: findings & ideas that generalize across domains From the earliest days of Elicit, researchers have been begging us to help them translate across domains

Tweet media one

2

2

16

@elicitorg

Elicit

5 months

Want a peek under the hood on how Elicit's magic works? 𝗟𝗶𝘃𝗶𝗻𝗴 𝗱𝗼𝗰𝘂𝗺𝗲𝗻𝘁𝘀 𝗮𝘀 𝗮 𝗨𝗫 𝗽𝗮𝘁𝘁𝗲𝗿𝗻 𝗶𝗻 𝗔𝗜 It's about systematic review, and the design challenges of using AI to create an editable document with everything science knows

Tweet card media

Living documents as an AI UX pattern

Design challenges in using LLMs to create an editable document with everything science knows about a topic.

blog.elicit.com

1

2

15

@elicitorg

Elicit

8 months

How to import papers from Zotero into Elicit!

2

1

15

@elicitorg

Elicit

8 months

At Elicit, we're advancing transparent and systematic approaches to AI so that we can improve the quality of reasoning in science, policy and beyond. Now Elicit is collaborating with the National Institute of Standards and Technology (NIST) in the Artificial Intelligence Safety

0

6

14

@elicitorg

Elicit

1 year

- Machine learning techniques, like reducing hallucination in language models

1

1

14

@elicitorg

Elicit

4 years

In the last few weeks, the @PredictIt price for voter turnout > 160M has almost doubled. If you want to get alerts when markets change, set custom PredictIt notifications at

0

5

13

@elicitorg

Elicit

4 months

One of our primary goals is to make quality research faster while exceeding human levels of accuracy, so we're especially excited about some recent quality improvements to Elicit: - Data extraction in columns without high-accuracy enabled is now 15% more accurate - Using

Tweet media one

1

1

14

@elicitorg

Elicit

4 months

We've added a filter for journal quality to help you restrict your searches to only top-ranked journals any time you want. Simply move this quality slider to gradually narrow in on higher ranked journals, quartile by quartile. 🙌

Tweet media one

1

3

14

@elicitorg

Elicit

1 year

- ecological interventions

Tweet media one

1

1

13

@elicitorg

Elicit

8 months

Elicit now lets you filter papers by any criteria, including effect direction, population studied, technique used, and more! Add a column and filter by keywords mentioned in the column. Learn more about filtering with columns here:

1

6

13

@elicitorg

Elicit

10 months

We added 19 more columns that you can use to extract details from over 200 million academic papers, or any PDF that you upload! These will work much better for fields like: - Social science - Economics and business studies - Computer science

Tweet media one

Tweet media two

1

3

13

@elicitorg

Elicit

7 months

Elicit for Health Economics & Outcomes Research (HEOR)! Use Elicit to estimate the market for a health intervention, costs, burden of illness, and more. Search through 125 million public papers (including PubMed) and extract details about datasets used, study methodologies,

4

3

12

@elicitorg

Elicit

1 year

6/ You’ll still get the Elicit you know and love in the "Find papers" workflow!

1

1

12

@elicitorg

Elicit

4 years

It's interesting how much narrower and peakier @TheEconomist 's prediction for Dem Electoral College votes is compared to @PredictIt , @metaculus , and @FiveThirtyEight

0

5

11

@elicitorg

Elicit

8 months

New in Elicit: Summary columns, including for uploaded papers! Now you can summarize any paper that you upload to Elicit. We also added "Summary of introduction" and "Summary of discussion". "Summary of introduction" can show how a paper fits into the literature on a research

Tweet media one

Tweet media two

Tweet media three

2

2

12

@elicitorg

Elicit

2 years

This week's updates: 1. Add "DOI" & "Detailed study design" to your table. "Detailed study design" is useful for identifying methodologies beyond randomized controlled trials, reviews, and meta-analyses (shown in "Study type").

Tweet media one

1

5

11

@elicitorg

Elicit

4 months

Our head of engineering @james_elicit outlined how we hire for AI engineers, from skillset to hiring process. On the latest @latentspacepod , he discusses the surprising chaotic qualities of language models and how pre-AI chaos engineering skills can play a role.

0

3

11

@elicitorg

Elicit

3 years

"Powerful generalizable language-based AI tools like Elicit are here, and they are just the tip of the iceberg; multimodal foundation model-based tools are poised to transform business in ways that are still difficult to predict." - @rossgritz

0

3

11

@elicitorg

Elicit

2 years

1/ Last week, we launched question & answering over the full text of open access papers. This query extracts the inclusion criteria from inside a systematic review. Clicking on the cell shows the source from inside the paper. You can also flag mistakes.

1

0

11

@elicitorg

Elicit

2 years

You can skip steps 2-6 by doing this directly on the home page! Click on the button that says "Brainstorm questions for..." underneath the search bar. @MushtaqBilalPhD

@MushtaqBilalPhD

Mushtaq Bilal, PhD

@MushtaqBilalPhD

2 years

In the search bar, type in the question you just selected.

Tweet media one

1

6

44

1

3

10

@elicitorg

Elicit

6 months

If you're curious about how Machine Learning and LLMs work--it's not magic or the robot uprising!--we've compiled a comprehensive reading list that we share with new Elicit employees. We find the Applications in Science section particularly interesting:

0

0

10

@elicitorg

Elicit

4 months

We got to launch one of our most requested features in Elicit this morning: Custom tags for your uploaded PDFs Starting today, you can now create and add tags for uploaded papers in your library. Group papers by project, category, favorites, reviewed status, step, or anything

Tweet media one

1

2

10

@elicitorg

Elicit

2 years

1/ We've integrated the "Brainstorm Research Questions" task with the "Lit Review" workflow as suggested queries! Brainstorm Research Questions is the second most popular task in Elicit, after Lit Review. Many users were already copying research questions into Lit Review.

1

3

10

@elicitorg

Elicit

5 months

We've been experimenting with some interesting use cases for Chat with Papers: -How papers relate to each other -How authors define certain terms -General context about what's being discussed in the papers -What a single paper did in detail

Tweet card media

Chat with papers you find or upload

You can now chat with papers in Elicit! This new workflow is part of Elicit Notebooks. Elicit Notebooks are a new way to navigate academic literature, broade...

www.youtube.com

0

1

9

@elicitorg

Elicit

4 months

In addition to more relevant results, you can now run advanced searches using 14 filters. That means you can search based on: • Title • Journal • Author • Keywords • PubMed ID • DOI • Publication year • Open access status • Citation count And more. Here's an example

Tweet media one

1

0

9

@elicitorg

Elicit

3 months

So what we need is automated evaluation, but with human supervision. Benchmarks are a way to achieve this, but they’re not easy to adapt to specific tasks. Instead we use LLM-based auto-evals with human supervision. We come up with an eval process, where we grade typical outputs

1

0

9

@elicitorg

Elicit

2 years

We're working to urgently increase those limits and/or find workarounds to get our user experience back to where it should be. Our apologies for any disruption – we'll update our status page as we work through the problem.

0

1

8

@elicitorg

Elicit

5 months

Elicit can be your best friend in sourcing a large body of papers for your research. Search citation trails, filter results based on your inclusion criteria, and run multiple queries quickly to broaden your results!

0

1

6

@elicitorg

Elicit

7 months

Check out tutorials on new features & workflows here:

Tweet card media

Introducing Elicit Notebooks!

Elicit is launching Notebooks! Elicit Notebooks are a new way to navigate academic literature, broader and deeper than before. These new workflows include:1....

www.youtube.com

0

0

8

@elicitorg

Elicit

4 months

For the full list of filters and how you can use them to control your search, check out this post: And kudos to Justin Reppert, @BenRachbach @VivaLaPanda_ for leading this massive project!

0

0

8

@elicitorg

Elicit

3 months

The Elicit Basic plan is now completely, indefinitely free. It’s designed for students and casual users. You can run as many searches as you want, create as many summaries of papers as you want, and chat with papers as much as you want. You can try some data extraction.

Tweet media one

1

0

8

@elicitorg

Elicit

1 year

Tweet media one

@TheEconomist

The Economist

1 year

From forecasting weather to searching for new materials for batteries and solar panels and controlling nuclear-fusion reactions, AI is making research faster, better, and more productive

5

9

28

0

2

8

@elicitorg

Elicit

3 years

Over 150 students and researchers in Indonesia are now using Elicit to support their research thanks to this incredible presentation by @manda_ngo

Tweet card media

Explore Research with Elicit: AI Research Assistant

Kajian Publikasi Ilmiah PSPI Seri 10 x Ought.org - Amanda Ngo

www.youtube.com

1

2

8

@elicitorg

Elicit

6 months

New episode on @latentspacepod for those who are interested in what's under the Elicit hood

@swyx

swyx

6 months

Cost v Reliability v Performance: Choose Three! 🆕 pod: w/ @jungofthewon and @stuhlmueller How do you improve prompt engineering and ai agents? The emerging paradigm is sometimes called "Flow engineering", but @elicitorg has reinvented the Notebook, in

Tweet media one

Tweet media two

Tweet media three

Tweet media four

1

9

84

1

1

7

@elicitorg

Elicit

3 months

Elicit Pro is an entirely new plan designed for researchers extracting data across a large number of papers, typically for systematic reviews. With Pro, you can extract data from up to 1200 papers at any point over the course of the year. The annual version of this plan is

Tweet media one

2

1

7

@elicitorg

Elicit

4 years

Coming soon: We’re launching binary predictions on Elicit! You’ll be able to make questions, predict on others’ questions, compare predictions, share groups of questions, track updates, and see your calibration. Sign up to get notified when we launch -->

Tweet media one

1

1

7

@elicitorg

Elicit

7 months

"How do we as a society want to turn compute into more work? One answer is we train larger and larger models and hope for the best...We are working towards a different answer." New episode on The Cognitive Revolution digging into the Elicit product philosophy and architecture!

@TurpentineMedia

Turpentine

@TurpentineMedia

7 months

In this episode of The Cognitive Revolution: @NathanLabenz sits down with @elicitorg co-founders @stuhlmueller and @jungofthewon to discuss their mission to make AI-assisted research more accessible and reliable. Learn about their unique approach to task decomposition, which

2

3

12

0

3

7

@elicitorg

Elicit

3 months

Elicit Plus is for serious researchers like graduate students and professors. You get everything in Basic but over more papers. You can also extract data from 300 papers at once if you get the annual plan. (The monthly plan splits the 300 across 12 months.) If you want to

Tweet media one

1

0

7

@elicitorg

Elicit

9 months

Handout at Full video at

Tweet card media

What's new in semantic search and retrieval? Elicit Tech Talk

Elicit machine learning engineer Justin Reppert talks about new techniques for semantic search and retrieval. Learn more about working with us at https://eli...

www.youtube.com

1

0

7

@elicitorg

Elicit

1 year

How @azeem and @Chantaljmsmith use Elicit and other AI tools as their second-brain

Tweet card media

🐙 Promptpack: How to build a second brain (featuring AI)

A step-by-step guide to using AI to collect and store knowledge

www.exponentialview.co

0

4

7

@elicitorg

Elicit

6 months

In one Elicit Notebook, you can: -Find papers -Extract data from PDFs -Generate a list of concepts across a topic -Narrow your results with filters -Chat with papers -Summarize multiple abstracts -Create custom columns Start building a Notebook for free!

1

0

7

@elicitorg

Elicit

3 months

We’ve found that auto-evals using the latest LLMs allow us to quickly iterate at scale, without sacrificing too much trust or flexibility. But this isn’t easy and there are always challenges! We must constantly refine our evaluation process as we refine Elicit’s features and

6

0

7

@elicitorg

Elicit

2 years

1/ We added 3 new columns in Elicit: funding source, limitations, and question-relevant summary. Funding source & limitations usually need the full text of papers so filter for "Has PDF" to see results for these columns. Try in Elicit:

1

0

7

@elicitorg

Elicit

3 months

Evaluation is the process determining the quality of LLM output. But there are tradeoffs. At one extreme, you can have experts look up all outputs: high trust, but abysmal scalability. At the other extreme, you just let LLMs evaluate their own outputs

Tweet card media

Trust at scale: Auto-evaluation for high-stakes LLM accuracy

Elicit’s mission is to scale up good reasoning. Large language models (LLMs) are currently the most promising technology to achieve this goal, and we use them extensively to help our users search and...

blog.elicit.com

1

0

6

@elicitorg

Elicit

3 months

New in Elicit: Confidence ratings When Elicit is extracting data from papers, you'll now see a ✓ when Elicit is confident in the accuracy of the answer.

Tweet media one

1

1

6

@elicitorg

Elicit

3 months

Each tier has a particular researcher in mind and is designed to give that specific researcher an unlimited experience at the quality and scale they need. Sign up for free at and choose the plan that supports your research. Or upgrade from your settings

Tweet card media

Elicit: The AI Research Assistant

Use AI to search, summarize, extract data from, and chat with over 125 million papers. Used by over 2 million researchers in academia and industry.

1

1

6

@elicitorg

Elicit

7 months

Thanks for the shout out @CBinsights !

Tweet media one

0

1

6

@elicitorg

Elicit

10 months

Welcome to the team @k1bird !

@jungofthewon

Jungwon

10 months

2024 is off to an amazing start because @k1bird joined us this week as Head of Product! As the first PM at Nubank, Kevin deeply understands hypergrowth and building a transformative product that users love. Kevin helped scale Nubank from 45,000 to 80 MILLION users. He helped

Tweet media one

4

0

16

0

0

5

@elicitorg

Elicit

5 months

If you export a table from Elicit, it'll include not just the citation information for papers but also any columns you added to the table, including abstract summaries, main findings, limitations, and more. Even custom columns!

Tweet media one

1

0

6

@elicitorg

Elicit

4 years

. @PredictIt currently implies a 61% chance of a Biden victory. @FiveThirtyEight believes the odds are 87%. The largest gap this election season. To get alerts when markets change, set custom PredictIt notifications at

1

0

6

@elicitorg

Elicit

6 months

New in Elicit! 1. Delete notebooks Once you have a Notebook open, go to the top left and click on the three dots next to the Notebook name. This will declutter your Notebook history. 2. Delete notebook steps For each step in a Notebook, click on the trash can button next to the

Tweet media one

Tweet media two

Tweet media three

0

2

6

@elicitorg

Elicit

6 months

Have you taken a Speedrun with Elicit? 30-45 minute live sessions that demonstrate just how far you can get into your research topic quickly. Check out past Speedruns for ideas on how to expedite your research with Elicit:

Tweet card media

Infant sleep training - Science speedrun with Elicit

Andreas (Elicit CEO) speed researches random topics he's interested in. Suggest topics or questions in the comments or chat!

www.youtube.com

0

1

5

@elicitorg

Elicit

8 months

Finding ways for market forces to *pull* or *demand* AI alignment will go so much further than imposing alignment as a tax that companies have to pay. Elicit is an example of this. Elicit’s success as a company and product depends not just on what the product does but how it’s

@james_elicit

James Brady

8 months

New post! When I was getting into AI alignment, one of my main concerns was that many of the leading figures had not personally been through the ups-and-downs of tech startups: they hadn't been through a boom and bust cycle with all the attendant chaos,

3

2

13

1

2

5

@elicitorg

Elicit

1 year

Apologies if any of you are seeing errors on Elicit! We're investigating a possible service provider (AWS) outage that seems to be affecting many companies right now.

0

0

4

@elicitorg

Elicit

3 months

For more information check out this guide: If your team has an even bigger project or other custom requirements, please reach out to sales @elicit .com.

0

1

5

@elicitorg

Elicit

3 years

Some of our favorite moments last year with the incredible team amplifying researchers with AI & bringing you new features every week. We'd love to have you at our dinner tables, hikes and friendsgivings this year:

Tweet card media

Our favorite memories from retreats, birthday celebrations, and general shenanigans in 2021 :) #retreat #tahoe #utah #teambuilding #skiing

www.youtube.com

0

2

5

@elicitorg

Elicit

4 years

If you want to compare two predictions, Elicit now tells you a set of summary stats and generates a fair bet – like this one between @PredictIt and @FiveThirtyEight :

0

1

5

@elicitorg

Elicit

3 years

RAFT is a new benchmark that aims to test language models on classification tasks that mirror scenarios one finds in real-world NLP applications such as Elicit. Track performance on the leaderboard: See details in the paper:

Tweet card media

RAFT: A Real-World Few-Shot Text Classification Benchmark

Large pre-trained language models have shown promise for few-shot learning, completing text-based tasks given only a few task-specific examples. Will models soon solve classification tasks that...

1

0

5

@elicitorg

Elicit

8 months

New in Elicit Plus: You can now export Elicit results as a .ris file to import into reference managers like Endnote & Mendeley! Subscribe to Elicit Plus by going to

Tweet media one

0

1

5

@elicitorg

Elicit

4 years

Feedback loops are key to getting better at forecasting. We've launched a rapid tournament to help with this – all questions resolve in a week, and you'll get back scores and calibration info. Forecast here:

Tweet media one

0

2

5

@elicitorg

Elicit

4 months

Or for this query: “Randomized controlled trials of cognitive behavioral therapy plus standard care versus standard care alone for persistent aggression in adults with schizophrenia" We see more papers specifically comparing CBT to standard of care, and about persistent

Tweet media one

1

1

5

@elicitorg

Elicit

4 months

What about papers above a certain citation count or published after a certain date?

Tweet media one

1

0

5

@elicitorg

Elicit

5 months

Elicit has several export options to take your research with you: -Export Find Papers steps in .csv, .bib, or .ris format -Export Extract Data from PDFs and List of Concepts steps in .csv format.

0

1

4

@elicitorg

Elicit

3 months

Read the post for more detail. And if the challenge of scaling trust appeals to you, apply to join our team!

Tweet card media

Careers at Elicit

We are hiring for several technical and non-technical roles, and we're open to remote employees. Take a look at our open roles!

0

0

5

@elicitorg

Elicit

3 months

In case you missed it, Elicit's search recently became much more powerful and precise! Here are some hidden filtering options in Elicit you may not know about:

@elicitorg

Elicit

4 months

In addition to more relevant results, you can now run advanced searches using 14 filters. That means you can search based on: • Title • Journal • Author • Keywords • PubMed ID • DOI • Publication year • Open access status • Citation count And more. Here's an example

Tweet media one

1

0

9

1

2

5

@elicitorg

Elicit

4 months

Compare the results for the query "Studies of antimicrobial stewardship interventions with multidisciplinary teams published 2010 or later." The new search shows more results that match the "multidisciplinary teams" criteria.

Tweet media one

1

0

5

@elicitorg

Elicit

3 months

We also, when possible, evaluate based on gold standards. Gold standards are high-quality answers to a set of representative questions users ask Elicit. The evaluation then asks whether the LLM outputs match the gold standards. This works because LLMs are better at validating a

Tweet media one

1

0

5

@elicitorg

Elicit

5 months

Excited to launch one of our most requested features! Save your custom columns in Elicit to reuse across all of your tables and Notebooks. No more defining custom columns for each table 🎉

Tweet media one

0

0

5

@elicitorg

Elicit

2 years

What do AI alignment researchers do and how can tools like Elicit help?

@oughtinc

Ought

2 years

We're creating a dataset of alignment research tasks (ART 🎨) to guide AI research towards helping with alignment. Each contribution is eligible for a $200-$2000 prize!

1

5

25

0

1

5

@elicitorg

Elicit

4 months

“What are the benefits of taking l-theanine?” will show more papers directly referencing the benefits

Tweet media one

1

1

5

@elicitorg

Elicit

4 months

Now try filtering for papers that are both open access and have a lot of citations:

Tweet media one

1

0

5

@elicitorg

Elicit

2 years

Glad you saw it! Was just about to tag you in a tweet as well :)

@wataru_hirota

Wataru Hirota

2 years

Today I got an exciting newsletter from @elicitorg . Now I see satisfying results for that query! has been improving (at a much faster pace than I had expected, to be honest) and I really enjoy using it.

Tweet media one

1

0

5

0

0

4