Elinor🎗️
@elinorpd.bsky.social
MIT // researching fairness, equity, & pluralistic alignment in LLMs
previously @ MIT media lab, mila / mcgill
i like language and dogs and plants and ultimate frisbee and baking and sunsets
https://elinorp-d.github.io
previously @ MIT media lab, mila / mcgill
i like language and dogs and plants and ultimate frisbee and baking and sunsets
https://elinorp-d.github.io
Pinned
What makes dialogue 💬 constructive 🫂?
We address this question in our #EMNLP2025 paper investigating how **responsivity** can characterize conversation quality ✨
Brandon Roy will be presenting our work (Oral) on Nov 7, Room A109 at 10:30.
🧵👇
https://aclanthology.org/2025.emnlp-main.1798/
We address this question in our #EMNLP2025 paper investigating how **responsivity** can characterize conversation quality ✨
Brandon Roy will be presenting our work (Oral) on Nov 7, Room A109 at 10:30.
🧵👇
https://aclanthology.org/2025.emnlp-main.1798/
Reposted by Elinor🎗️
It’s grad school application season, and I wanted to give some public advice.
Caveats:
-*-*-*-*
> These are my opinions, based on my experiences, they are not secret tricks or guarantees
> They are general guidelines, not meant to cover a host of idiosyncrasies and special cases
Caveats:
-*-*-*-*
> These are my opinions, based on my experiences, they are not secret tricks or guarantees
> They are general guidelines, not meant to cover a host of idiosyncrasies and special cases
November 6, 2025 at 2:55 PM
It’s grad school application season, and I wanted to give some public advice.
Caveats:
-*-*-*-*
> These are my opinions, based on my experiences, they are not secret tricks or guarantees
> They are general guidelines, not meant to cover a host of idiosyncrasies and special cases
Caveats:
-*-*-*-*
> These are my opinions, based on my experiences, they are not secret tricks or guarantees
> They are general guidelines, not meant to cover a host of idiosyncrasies and special cases
Reposted by Elinor🎗️
🧵Excited to present our work at #EMNLP2025 “Analyzing Dialectal Biases in LLMs for Knowledge and Reasoning Benchmarks”!
Paper 📄 arxiv.org/abs/2510.00962
w/ Eileen Pan, Skyler Seto, @allisonkoe.bsky.social @maartjeterhoeve.bsky.social
Paper 📄 arxiv.org/abs/2510.00962
w/ Eileen Pan, Skyler Seto, @allisonkoe.bsky.social @maartjeterhoeve.bsky.social
November 6, 2025 at 12:08 AM
🧵Excited to present our work at #EMNLP2025 “Analyzing Dialectal Biases in LLMs for Knowledge and Reasoning Benchmarks”!
Paper 📄 arxiv.org/abs/2510.00962
w/ Eileen Pan, Skyler Seto, @allisonkoe.bsky.social @maartjeterhoeve.bsky.social
Paper 📄 arxiv.org/abs/2510.00962
w/ Eileen Pan, Skyler Seto, @allisonkoe.bsky.social @maartjeterhoeve.bsky.social
it's crazy how typos are impossible to catch until *after* you submit a paper, after which they become glaringly noticeable
November 6, 2025 at 1:23 AM
it's crazy how typos are impossible to catch until *after* you submit a paper, after which they become glaringly noticeable
Reposted by Elinor🎗️
Which, whose, and how much knowledge do LLMs represent?
I'm excited to share our preprint answering these questions:
"Epistemic Diversity and Knowledge Collapse in Large Language Models"
📄Paper: arxiv.org/pdf/2510.04226
💻Code: github.com/dwright37/ll...
1/10
I'm excited to share our preprint answering these questions:
"Epistemic Diversity and Knowledge Collapse in Large Language Models"
📄Paper: arxiv.org/pdf/2510.04226
💻Code: github.com/dwright37/ll...
1/10
October 13, 2025 at 11:25 AM
Which, whose, and how much knowledge do LLMs represent?
I'm excited to share our preprint answering these questions:
"Epistemic Diversity and Knowledge Collapse in Large Language Models"
📄Paper: arxiv.org/pdf/2510.04226
💻Code: github.com/dwright37/ll...
1/10
I'm excited to share our preprint answering these questions:
"Epistemic Diversity and Knowledge Collapse in Large Language Models"
📄Paper: arxiv.org/pdf/2510.04226
💻Code: github.com/dwright37/ll...
1/10
What makes dialogue 💬 constructive 🫂?
We address this question in our #EMNLP2025 paper investigating how **responsivity** can characterize conversation quality ✨
Brandon Roy will be presenting our work (Oral) on Nov 7, Room A109 at 10:30.
🧵👇
https://aclanthology.org/2025.emnlp-main.1798/
We address this question in our #EMNLP2025 paper investigating how **responsivity** can characterize conversation quality ✨
Brandon Roy will be presenting our work (Oral) on Nov 7, Room A109 at 10:30.
🧵👇
https://aclanthology.org/2025.emnlp-main.1798/
November 3, 2025 at 10:41 PM
What makes dialogue 💬 constructive 🫂?
We address this question in our #EMNLP2025 paper investigating how **responsivity** can characterize conversation quality ✨
Brandon Roy will be presenting our work (Oral) on Nov 7, Room A109 at 10:30.
🧵👇
https://aclanthology.org/2025.emnlp-main.1798/
We address this question in our #EMNLP2025 paper investigating how **responsivity** can characterize conversation quality ✨
Brandon Roy will be presenting our work (Oral) on Nov 7, Room A109 at 10:30.
🧵👇
https://aclanthology.org/2025.emnlp-main.1798/
Reposted by Elinor🎗️
Great piece by @natolambert.bsky.social on the current state of human exhaustion in the AI world. Makes this important point:
October 25, 2025 at 3:05 PM
Great piece by @natolambert.bsky.social on the current state of human exhaustion in the AI world. Makes this important point:
Reposted by Elinor🎗️
This paper underscores how “misinformation” is not easily operationalized as single pieces of factually untrue content, but often takes shape through the motivated amplification of specific evidence (often true evidence) that serves to build and reinforce misleading frames.
October 22, 2025 at 11:37 AM
This paper underscores how “misinformation” is not easily operationalized as single pieces of factually untrue content, but often takes shape through the motivated amplification of specific evidence (often true evidence) that serves to build and reinforce misleading frames.
Really proud bc I finished my first crochet sweater! It’s pretty cool wearing something you made by hand, every single stitch, mistakes and all
October 15, 2025 at 4:02 PM
Really proud bc I finished my first crochet sweater! It’s pretty cool wearing something you made by hand, every single stitch, mistakes and all
Reposted by Elinor🎗️
MIT rejects "compact" proposed by the Trump administration.
MIT prez wrote: it "would restrict freedom of expression and our independence as an institution" and "is inconsistent with our core belief that scientific funding should be based on scientific merit alone."
orgchart.mit.edu/letters/rega...
MIT prez wrote: it "would restrict freedom of expression and our independence as an institution" and "is inconsistent with our core belief that scientific funding should be based on scientific merit alone."
orgchart.mit.edu/letters/rega...
Regarding the Compact | MIT Organization Chart
orgchart.mit.edu
October 10, 2025 at 1:20 PM
MIT rejects "compact" proposed by the Trump administration.
MIT prez wrote: it "would restrict freedom of expression and our independence as an institution" and "is inconsistent with our core belief that scientific funding should be based on scientific merit alone."
orgchart.mit.edu/letters/rega...
MIT prez wrote: it "would restrict freedom of expression and our independence as an institution" and "is inconsistent with our core belief that scientific funding should be based on scientific merit alone."
orgchart.mit.edu/letters/rega...
Reposted by Elinor🎗️
Hello #COLM2025! Excited to be kicking off the NLP4Democracy workshop this morning. We are in 520E (behind A/B/C) - check out our amazing program! sites.google.com/andrew.cmu.e...
NLP 4 Democracy - COLM 2025
sites.google.com
October 10, 2025 at 1:20 PM
Hello #COLM2025! Excited to be kicking off the NLP4Democracy workshop this morning. We are in 520E (behind A/B/C) - check out our amazing program! sites.google.com/andrew.cmu.e...
Reposted by Elinor🎗️
💡We kicked off the SoLaR workshop at #COLM2025 with a great opinion talk by @michelleding.bsky.social & Jo Gasior Kavishe (joint work with @victorojewale.bsky.social and
@geomblog.bsky.social
) on "Testing LLMs in a sandbox isn't responsible. Focusing on community use and needs is."
@geomblog.bsky.social
) on "Testing LLMs in a sandbox isn't responsible. Focusing on community use and needs is."
October 10, 2025 at 2:31 PM
💡We kicked off the SoLaR workshop at #COLM2025 with a great opinion talk by @michelleding.bsky.social & Jo Gasior Kavishe (joint work with @victorojewale.bsky.social and
@geomblog.bsky.social
) on "Testing LLMs in a sandbox isn't responsible. Focusing on community use and needs is."
@geomblog.bsky.social
) on "Testing LLMs in a sandbox isn't responsible. Focusing on community use and needs is."
Reposted by Elinor🎗️
Hi #COLM2025! 🇨🇦 I will be presenting a talk on the importance of community-driven LLM evaluations based on an opinion abstract I wrote with Jo Kavishe, @victorojewale.bsky.social and @geomblog.bsky.social tomorrow at 9:30am in 524b for solar-colm.github.io
Hope to see you there!
Hope to see you there!
Third Workshop on Socially Responsible Language Modelling Research (SoLaR) 2025
COLM 2025 in-person Workshop, October 10th at the Palais des Congrès in Montreal, Canada
solar-colm.github.io
October 9, 2025 at 7:32 PM
Hi #COLM2025! 🇨🇦 I will be presenting a talk on the importance of community-driven LLM evaluations based on an opinion abstract I wrote with Jo Kavishe, @victorojewale.bsky.social and @geomblog.bsky.social tomorrow at 9:30am in 524b for solar-colm.github.io
Hope to see you there!
Hope to see you there!
Important keynote by Nicholas Carlini with important calls to action for the research community!
Ty for the helpful summary @mariaa.bsky.social
Ty for the helpful summary @mariaa.bsky.social
"What problems you're scared of depend on how good you think the LLMs will get"
"Please be willing to change your mind."
"This is COLM. We made the models, it's our job to fix it. How are you going to change your research agenda?"
#COLM2025
"Please be willing to change your mind."
"This is COLM. We made the models, it's our job to fix it. How are you going to change your research agenda?"
#COLM2025
October 9, 2025 at 3:59 PM
Important keynote by Nicholas Carlini with important calls to action for the research community!
Ty for the helpful summary @mariaa.bsky.social
Ty for the helpful summary @mariaa.bsky.social
Reposted by Elinor🎗️
COLM word cloud. Yoav says it’s the year of reasoning, but evaluation is also huge.
October 7, 2025 at 12:55 PM
COLM word cloud. Yoav says it’s the year of reasoning, but evaluation is also huge.
I’m at #COLM2025! Would love to chat about anything related to pluralistic alignment, fairness evaluations, societal impacts of LLMs, etc 😊
You can also find me at the NLP4Democracy workshop giving a talk about my work analyzing democratic deliberation with LLMs Oct 10th!
You can also find me at the NLP4Democracy workshop giving a talk about my work analyzing democratic deliberation with LLMs Oct 10th!
October 7, 2025 at 2:43 AM
I’m at #COLM2025! Would love to chat about anything related to pluralistic alignment, fairness evaluations, societal impacts of LLMs, etc 😊
You can also find me at the NLP4Democracy workshop giving a talk about my work analyzing democratic deliberation with LLMs Oct 10th!
You can also find me at the NLP4Democracy workshop giving a talk about my work analyzing democratic deliberation with LLMs Oct 10th!
Reposted by Elinor🎗️
Alright the evening sky, you’re utterly wondrous and fantastical, we get it, geez
October 6, 2025 at 6:35 PM
Alright the evening sky, you’re utterly wondrous and fantastical, we get it, geez
Reposted by Elinor🎗️
October 6, 2025 at 8:26 PM
Reposted by Elinor🎗️
I will be at #COLM2025 this week, and would love to connect with folks interested in applications (and critiques) of language modeling in social science research!
And join us for the NLP4Democracy workshop on Friday!
sites.google.com/andrew.cmu.e...
#NLP #NLProc #LLM #ComputationalSocialScience
And join us for the NLP4Democracy workshop on Friday!
sites.google.com/andrew.cmu.e...
#NLP #NLProc #LLM #ComputationalSocialScience
NLP 4 Democracy - COLM 2025
sites.google.com
October 6, 2025 at 7:31 PM
I will be at #COLM2025 this week, and would love to connect with folks interested in applications (and critiques) of language modeling in social science research!
And join us for the NLP4Democracy workshop on Friday!
sites.google.com/andrew.cmu.e...
#NLP #NLProc #LLM #ComputationalSocialScience
And join us for the NLP4Democracy workshop on Friday!
sites.google.com/andrew.cmu.e...
#NLP #NLProc #LLM #ComputationalSocialScience
Reposted by Elinor🎗️
Very excited that my paper with @katakeith.bsky.social is now out in @polanalysis.bsky.social. We investigate whether LLMs actually follow the instructions/definitions provided in codebooks, propose some diagnostics, and release a new evaluation dataset.
www.cambridge.org/core/journal...
www.cambridge.org/core/journal...
Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts | Political Analysis | Cambridge Core
Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts
www.cambridge.org
September 19, 2025 at 1:45 PM
Very excited that my paper with @katakeith.bsky.social is now out in @polanalysis.bsky.social. We investigate whether LLMs actually follow the instructions/definitions provided in codebooks, propose some diagnostics, and release a new evaluation dataset.
www.cambridge.org/core/journal...
www.cambridge.org/core/journal...
Reposted by Elinor🎗️
I wish students understood in most empirical AI research there’s a huge scientific advantage from being constitutionally excited by math vs intimidated, but very little additional gain from being actually “good” at math. Maybe they’d be less intimidated if they didn’t feel they had to be “good”.
September 19, 2025 at 7:00 PM
I wish students understood in most empirical AI research there’s a huge scientific advantage from being constitutionally excited by math vs intimidated, but very little additional gain from being actually “good” at math. Maybe they’d be less intimidated if they didn’t feel they had to be “good”.
🚨 New preprint! 🚨
Excited to share my work: An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies 🤖🗳️
I’ll be presenting this at @colmweb.org in the NLP4Democracy workshop!
🔗 arxiv.org/abs/2509.12577
Excited to share my work: An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies 🤖🗳️
I’ll be presenting this at @colmweb.org in the NLP4Democracy workshop!
🔗 arxiv.org/abs/2509.12577
An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies
In an era of increasing societal fragmentation, political polarization, and erosion of public trust in institutions, representative deliberative assemblies are emerging as a promising democratic forum...
arxiv.org
September 17, 2025 at 5:40 PM
🚨 New preprint! 🚨
Excited to share my work: An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies 🤖🗳️
I’ll be presenting this at @colmweb.org in the NLP4Democracy workshop!
🔗 arxiv.org/abs/2509.12577
Excited to share my work: An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies 🤖🗳️
I’ll be presenting this at @colmweb.org in the NLP4Democracy workshop!
🔗 arxiv.org/abs/2509.12577
"This suggests that LLM benchmark behavior may generalize less and less to non-benchmark settings, raising new concerns about ecological validity."
super interesting
super interesting
🚨 New #EMNLP2025 paper!
Do LLMs exhibit distinct behavior when the prompt looks similar to common evaluation prompts? 👀
We show that prompts that signal bias evaluation can flip the measured bias. See below ⬇️
Do LLMs exhibit distinct behavior when the prompt looks similar to common evaluation prompts? 👀
We show that prompts that signal bias evaluation can flip the measured bias. See below ⬇️
September 15, 2025 at 5:25 PM
"This suggests that LLM benchmark behavior may generalize less and less to non-benchmark settings, raising new concerns about ecological validity."
super interesting
super interesting
Reposted by Elinor🎗️
This paper yields the same conclusion as what @mustafasuleymanai.bsky.social recently posted on the danger of 'seemingly conscious AI'.
mustafa-suleyman.ai/seemingly-co...
mustafa-suleyman.ai/seemingly-co...
We must build AI for people; not to be a person
mustafa-suleyman.ai
September 15, 2025 at 3:03 PM
This paper yields the same conclusion as what @mustafasuleymanai.bsky.social recently posted on the danger of 'seemingly conscious AI'.
mustafa-suleyman.ai/seemingly-co...
mustafa-suleyman.ai/seemingly-co...
When reading papers, especially reviewing, I like to print and annotate as I read. I wish I could upload this to open review so authors can see smaller suggestions (typos, formatting errors) as well as smaller positive notes eg things I appreciated or found useful/interesting
September 14, 2025 at 7:54 PM
When reading papers, especially reviewing, I like to print and annotate as I read. I wish I could upload this to open review so authors can see smaller suggestions (typos, formatting errors) as well as smaller positive notes eg things I appreciated or found useful/interesting