Sign in

Chara Podimata

@charapod.bsky.social
120 followers 128 following 18 posts

Assistant Professor of Operations Research and Statistics, MIT. Interested in social computing, human-in-the-loop of AI decision making, recommendation systems, and AI policy.

PostsRepliesMedia
Chara Podimata @charapod.bsky.social · 11/09/2026
If you would like to get in touch with us about the dashboard, the audit instrument, our planned analyses of the full dataset, or any other comments/discussion, please reach out at contact@llmelectionobservatory.org or here on bluesky. n/n
000
Chara Podimata @charapod.bsky.social · 11/09/2026
I also want to shout out once again the team behind the 2024 election audit (arxiv.org/pdf/2509.18446), from which we drew great inspiration @sarahcen.bsky.social, @aifi.bsky.social, Hedi Driss, @dataspen.bsky.social, and @aleksmadry.bsky.social 8/n
arxiv.org
100
Chara Podimata @charapod.bsky.social · 11/09/2026
I'm grateful for an absolutely stellar interdisciplinary collaboration on a project that's near and dear to my heart. 7/n
100
Chara Podimata @charapod.bsky.social · 11/09/2026
The full dataset will be released publicly on Hugging Face after the election season is complete. If you're interested in learning more, please visit our dashboard: llmelectionobservatory.org, where you can read more about our methodology and even see the exact model responses. 6/n
llmelectionobservatory.org
Election LLM Observatory
100
Chara Podimata @charapod.bsky.social · 11/09/2026
We are documenting the data live, and we include preliminary analyses of, among many other things, the different words picked up by models when discussing a topic, the sources models cite as they try to answer, and the confidence with which they state their conclusions. 5/n
100
Chara Podimata @charapod.bsky.social · 11/09/2026
Each question is also asked as-is and under a set of "framings" (what we call prompt steers) to every model. These prompt steers are designed to generally reflect some ways that people may choose to qualify questions based on their own political standpoints or demographics. 4/n
110
Chara Podimata @charapod.bsky.social · 11/09/2026
Our audit survey consists of a fixed bank of questions related to different aspects of the 2026 midterms, ranging from general information about election processes to information about specific candidates in battleground states. 3/n
110
Chara Podimata @charapod.bsky.social · 11/09/2026
A bit on our project: We are running a large-scale longitudinal audit of the responses that frontier LLMs are providing to 2026 midterm election-related queries. 2/n
110
Chara Podimata @charapod.bsky.social · 11/09/2026
We’re launching the LLM Election Observatory: llmelectionobservatory.org, a research project with @adamberinsky.bsky.social, Charles Stewart, Nicolas Emmenegger, Young-Kyung Kim, and Alessandro Morosini on how LLMs respond to election-related questions. @nytimes.com wrote a story about it. 1/n 1/n
nytimes.com
Voters Are Asking A.I. About Elections. The Answers Can Vary by User. (Gift Article)
Artificial intelligence is quickly becoming a go-to stop for voters looking for information about political races. Researchers are studying the effects.
163
Chara Podimata @charapod.bsky.social · 17/06/2026
@radniazadeh.bsky.social and I are co-organizing the EC mentoring workshop this year, and we're so excited about the fantastic speakers that are joining us! Please spread the word to your students. The registration form will remain open until tomorrow EOD.
041
Chara Podimata @charapod.bsky.social · 12/01/2026
🔈 Asu Ozdaglar and I are hiring a postdoc for next year to work on adaptive, ethically-informed decision systems, human–AI collaboration, and decision-making under uncertainty. More info here: charapodimata.com/postdoc_anno...
charapodimata.com
Chara Podimata
Chara Podimata
063
Chara Podimata @charapod.bsky.social · 29/09/2025
At my side-gig as a podcaster, I recently had the joy of interviewing Sam Hopkins!
061
Reposted by Chara Podimata
let-all.com @let-all.com · 29/09/2025
We've got the next episode of the learning theory podcast, Probably Approximately Correct Learners! This episode is with Samuel B. Hopkins at MIT -- check it out! www.youtube.com/watch?v=1oeA...
youtube.com
Ep. 3: Sam Hopkins
YouTube video by Learning Theory Alliance (LeT-All)
1134
Chara Podimata @charapod.bsky.social · 25/09/2025
This was a massive effort spearheaded by @sarahcen.bsky.social , and in collaboration with @aifi.bsky.social , Hedi Driss, Charlotte Park, @dataspen.bsky.social , and @aleksmadry.bsky.social. Happy to discuss further with anyone who's interested in learning more! (6/6)
010
Chara Podimata @charapod.bsky.social · 25/09/2025
(iii) interrogate the models’ beliefs about candidates’ attributes, and (iv) reveal the models’ implicit predictions of the election outcome. We’re making the dataset publicly available and invite researchers to run their own analyses on it: huggingface.co/datasets/sar.... (5/6)
huggingface.co
sarahcen/llm-election-data-2024 · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
110
Chara Podimata @charapod.bsky.social · 25/09/2025
Using this dataset, we perform 4 analyses of the dataset that (i) study the longitudinal variation of model behavior during election season, (ii) illustrate the sensitivity of election-related responses to demographic steering, (4/6)
110
Chara Podimata @charapod.bsky.social · 25/09/2025
Our design systematically varies question content and format, resulting in a rich dataset that enables analyses of the models’ behavior over time (e.g., across model updates), sensitivity to steering, responsiveness to instructions, election-related knowledge and “beliefs.” (3/6)
110
Chara Podimata @charapod.bsky.social · 25/09/2025
We conducted a large-scale, longitudinal study of 12 models, queried using a structured survey with over 12,000 questions on a near-daily cadence from July through November 2024. (2/6)
110
Chara Podimata @charapod.bsky.social · 25/09/2025
We have a new paper out today, and I’m so proud of it and the work that went into creating it! Link here: arxiv.org/pdf/2509.184.... The 2024 US presidential election was the first major election in the US since the popularization of LLMs. (1/6)
1113
Reposted by Chara Podimata
Juba Ziani @jubaz.bsky.social · 11/08/2025
Check out our @let-all.com blog post on strategic classification and around recent work with Valia and @charapod.bsky.social!
052