Yamil Velez | Lightnews

Yamil Ricardo Velez

@yamilrvelez.bsky.social

2.3K followers 1.1K following 110 posts

political scientist at Columbia | MIA ✈️ NYC | tailored surveys and experiments

Videos

Political science 41%

Sociology 29%

Posts Replies Media Videos

Yamil Ricardo Velez @yamilrvelez.bsky.social · 6d

Thanks, Dan!

Reposted by Yamil Velez

Jay Van Bavel, PhD @jayvanbavel.bsky.social · 7d

An AI Voter bot improves knowledge about politics
But, the AI bot has weak effects on downstream outcomes like vote preferences and party evaluations among respondents whose primary issue position aligns closely with one of the parties.
Partisan action is hard to change.
www.pnas.org/doi/10.1073/...

Yamil Ricardo Velez @yamilrvelez.bsky.social · 12d

Though LLMs as persuasion tools are (rightly) getting attention, their most valuable civic use may be retrieval: grounded answers with links to the source material using language that is accessible to users. Positive use cases aren’t dominating the discourse, but that’s where I think the upside is.

Yamil Ricardo Velez @yamilrvelez.bsky.social · 12d

In ongoing work w/ Alec Ewig, we explore how RAG can enhance measures of representation by retrieving relevant legislation from a 15,000+ bill database mapped to voter preferences. RAG + agentic workflows can uncover info buried in dense policy docs and answer complex queries with citations.

www.dropbox.com

Yamil Ricardo Velez @yamilrvelez.bsky.social · 12d

We used retrieval-augmented generation (RAG), a method that pulls relevant text from curated sources directly into prompts. A vector database, multiple API calls, and a lot of trial and error later, it substantially reduced errors and preserved issue-specific language from party platforms.

Yamil Ricardo Velez @yamilrvelez.bsky.social · 12d

When we started this project, standard LLMs weren't up to the task. They produced plausible-sounding answers but regularly hallucinated policy stances, especially on niche or novel issues. For a voting advice application, accuracy was critical, so we had to build a more involved approach.

Reposted by Efrén O. Pérez, Scott Clifford, David Darmofal

Yamil Ricardo Velez @yamilrvelez.bsky.social · 12d

This paper was a blast to work on. The challenge: present party positions across many issues, in real time, using language voters actually use. 🧵 on why we went with a more involved retrieval-based approach and where I think these tools are headed.

Semra Sevi @semrasevi.bsky.social · 16d

🚨Excited to share our new paper published in PNAS (joint with @yamilrvelez.bsky.social and Don Green)! AI can enhance political knowledge and provide balanced information about politics with proper guardrails and vetted sources (e.g., party platforms).

www.pnas.org/doi/full/10....

Yamil Ricardo Velez @yamilrvelez.bsky.social · 14d

Congrats, Damien!

Reposted by Hugo Mercier, Efrén O. Pérez, Ben Worthy , and 3 more Hugo Mercier, Efrén O. Pérez, Ben Worthy, Yamil Velez, Stuart J. Turnbull‐Dugarte, David Darmofal

Semra Sevi @semrasevi.bsky.social · 16d

Yamil Ricardo Velez @yamilrvelez.bsky.social · 16d

I have a 2024 pre-election Verasight survey I carried out with Alec Ewig that used an adaptive survey method to create a kind of dynamic CES. Happy to chat offline if you think it would be useful!

Reposted by Yamil Velez

Lisa Argyle @lpargyle.bsky.social · 20d

Looking for a tl;dr for these two excellent papers? I've got you covered: www.science.org/doi/10.1126/...

Reposted by Joanna Bryson, Gordon Pennycook, Adam J. Berinsky , and 6 more Joanna Bryson, Gordon Pennycook, Adam J. Berinsky, Ben Worthy, Yamil Velez, Stefan M. Herzog, Dean Eckles, Johannes Breuer, Greg Linden

David Rand @dgrand.bsky.social · 20d

🚨 New in Nature+Science!🚨
AI chatbots can shift voter attitudes on candidates & policies, often by 10+pp
🔹Exps in US Canada Poland & UK
🔹More “facts”→more persuasion (not psych tricks)
🔹Increasing persuasiveness reduces "fact" accuracy
🔹Right-leaning bots=more inaccurate

Yamil Ricardo Velez @yamilrvelez.bsky.social · 20d

All of this is to say that I hope I’m also invited to the party, not only because I care about identifying causal effects, but because I also care about measuring theoretical constructs with a level of precision that quasi-experimental and field experimental designs simply can’t deliver.

Yamil Ricardo Velez @yamilrvelez.bsky.social · 20d

As we increasingly interact with GUIs via LLMs, targeted ads, and social media, survey experiments are *even more* fit for the task of understanding human behavior, and I hope we continue relying on them to sort through thorny causal questions.

Yamil Ricardo Velez @yamilrvelez.bsky.social · 20d

That’s a useful distinction. Another way to put it is whether a treatment *intervenes* on an outcome. On its face, your standard persuasion experiment looks a lot like “do you prefer [Joe/Jose] for this job?,” but the latter design isn’t trying to shift Y. It’s a measurement exercise.

Yamil Ricardo Velez @yamilrvelez.bsky.social · Nov 24

It's likely not a problem *yet*

Yamil Ricardo Velez @yamilrvelez.bsky.social · Nov 24

Thanks for flagging! I know Brave has several privacy layers. Will look into it.

Yamil Ricardo Velez @yamilrvelez.bsky.social · Nov 24

Thanks! Have to channel my existential panic into something!

Yamil Ricardo Velez @yamilrvelez.bsky.social · Nov 24

Surveys are going to need new ways to establish human presence as AI gets faster and harder to detect. Pulse is one step in that direction.

Special thanks to @seanwestwood1.bsky.social who flagged several spoofing paths. This is exactly the kind of scrutiny we’ll need as we adapt to this new era.

Yamil Ricardo Velez @yamilrvelez.bsky.social · Nov 24

This doesn’t solve the “verify-then-handoff” problem. But it does filter out the most aggressive headless-browser attacks and gives us a first layer of defense in an era where attention checks and gotcha questions fail.

Demo and QSF download here: columbiauniversity.qualtrics.com/jfe/form/SV_...

Qualtrics Survey | Qualtrics Experience Management

The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.

columbiauniversity.qualtrics.com

Yamil Ricardo Velez @yamilrvelez.bsky.social · Nov 24

I'm currently working on Pulse, a “proof-of-life” approach compatible with Qualtrics that uses a simple finger-on-lens verification task to confirm human presence. This approach avoids privacy concerns tied to capturing faces or living environments, and it works on laptops and smartphones.

Reposted by Hugo Mercier, Scott Clifford, Erika Franklin Fowler , and 2 more Hugo Mercier, Scott Clifford, Erika Franklin Fowler, Alessandro Nai, David Darmofal

Yamil Ricardo Velez @yamilrvelez.bsky.social · Nov 24

As @seanjwestwood.bsky.social's terrifying new PNAS article demonstrates, LLMs can now pass almost every attention check, mirror personas, stay consistent across pages, and systematically bias responses in the aggregate.

So here’s a different angle: verify physical presence, not text.

Reposted by Yamil Velez

Cambridge University Press Political Science & IR @cambup-polsci.cambridge.org · Oct 8

#OpenAccess from @polanalysis.bsky.social -

Crowdsourced Adaptive Surveys - https://cup.org/4pNclb0

- @yamilrvelez.bsky.social

An abstract from Political Analysis discussing a Crowd-Sourced Adaptive Survey System (CSAS) for enhancing public opinion surveys with natural language processing and adaptive algorithms.

Yamil Ricardo Velez @yamilrvelez.bsky.social · Oct 6

I used to believe that survey aesthetics have minimal effects on completion rates and attentiveness… until I saw that slime-green color scheme

Reposted by Yamil Velez, David Darmofal

Political Analysis @polanalysis.bsky.social · Sep 29

The latest issue of PA is out now. We have a great collection of papers by @yamilrvelez.bsky.social, @sysilviakim.bsky.social, @mattblackwell.bsky.social, @sophieehill.bsky.social, @dwlee.bsky.social, @melissazrogers.bsky.social, @kaipingchen.bsky.social, @samuelbaltz.bsky.social (1/2)

Julia M. Rohrer @dingdingpeng.the100.ci · Aug 25

Ever stared at a table of regression coefficients & wondered what you're doing with your life?

Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social)
Preprint: doi.org/10.31234/osf...
Website: j-rohrer.github.io/marginal-psy...

Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities

Abstract
Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models).

Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve.

A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals).

Illustrated are
1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals
2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and
3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.

Reposted by Yamil Velez, David Szakonyi

Ethan Porter @ethanvporter.bsky.social · Aug 18

Today, @catiebailard.bsky.social and I take the reins at GW's Institute for Data, Democracy + Politics! We'll work to make IDDP a one-stop shop for research on misinfo, platform manipulation, and threats to democratic ideals. To follow our work + learn about opportunities, visit: bit.ly/45GLggi

signup.e2ma.net

Reposted by Yamil Velez

Yamil Ricardo Velez @yamilrvelez.bsky.social · Aug 6

Thrilled to see my paper with Patrick Liu in the APSR!

We address a crucial question in political psychology — whether persuasive attempts targeting deeply held issues cause attitudes to grow more extreme or encourage moderation — using tailored AI-powered surveys.

Confronting Core Issues: A Critical Assessment of Attitude Polarization Using Tailored Experiments | American Political Science Review | Cambridge Core

Confronting Core Issues: A Critical Assessment of Attitude Polarization Using Tailored Experiments

www.cambridge.org

Reposted by Yamil Velez

Cambridge University Press Political Science & IR @cambup-polsci.cambridge.org · Feb 12

#OpenAccess from @polanalysis.bsky.social -

Crowdsourced Adaptive Surveys - cup.org/4aY2OH4

- @yamilrvelez.bsky.social

"This paper introduces a crowdsourced adaptive survey methodology (CSAS) that unites advances in natural language processing and adaptive algorithms..."

#FirstView

The image features the text "POLITICAL ANALYSIS" in large white letters on a crimson background, with "#OpenAccess" in smaller white letters above a yellow bar below.

Reposted by Yamil Velez

SICSS-Penn @sicsspenn.bsky.social · Jul 7

@yamilrvelez.bsky.social from @columbiauniversity.bsky.social opened the second week of SICSS-Penn 2025 with his talk, "Generative AI and Respondent-Centered Social Science."

Add to Home Screen

Light up
your news

Add to Home Screen

Light upyour news

Sign in to Lightnews

Sign up to start reading

Connect Bluesky

Connect with Bluesky

Light up
your news