Elinor

@elinorpd_

phd @MIT_CSAIL // LLM societal impacts & pluralistic value alignment // prev @medialab @Mila_Quebec // i like language, frisbees and sunsets (she/her)

elinorp-d.github.io

Joined May 2022

688 Following

1,195 Followers

Replies Reposts Media

Pinned
Elinor
@elinorpd_
Jul 23
Pluralistic alignment is thriving as a research agenda yet failing at its goal: making the AI systems people actually use more pluralistic🌈 🚨New position paper: we argue adoption in deployed models should be the fields main goal & we provide a roadmap of how to get there 🧵1/
7
Elinor
@elinorpd_
Oct 27
‼️ "my fear and worry in this moment is a lot less about Al or "the value of human intelligence" and much more about how concentration of power has a very reliable history of being very dangerous to large numbers of affected people!" rlly salient quote worth highlighting imo
Omar Khattab
@lateinteraction
Oct 27
it’s my nature to keep posts rather impersonal, so i have to work extra hard to tweet this sort of personal testimony below from time to time as i think the reminder in it around AI and the “value of human intelligence” is worth it as of the end of Oct 2026, i have not (yet -
Elinor
@elinorpd_
Oct 14
awesome work! llm pushback always seemed like a weak solution to address sycophancy to me, and this directly investigates why + how. and more importantly, what end-users actually understand / believe also fantastic to see studies beyond english-only speakers/cultures 👏
Lucy Li
@lucy3_li
Oct 14
Models are sycophantic, and when they do challenge faulty or incorrect inputs, they're ambiguous and ineffective. In a new paper w/ multilingual co-authors, we find that people may view LM responses that push back, yet still end up believing false content is true.
1
Elinor
@elinorpd_
Oct 14
cool work investigating the interaction effect of different values in alignment posttraining!
Andy Liu
@uilydna
Oct 13
LLM developers train their models to follow prosocial values, but post-training can influence model behavior in unexpected ways. In “Predicting Alignment Generalization with Value Representations”, we ask whether downstream effects of value alignment can be predicted in advance.
Elinor
@elinorpd_
Oct 7
"What happens when nobody’s replying to messages on forums any more, and everyone instead gets their information from scrupulously post-trained AI models?" ^ a question ive been thinking a lot about
Seth Lazar
@sethlazar
Oct 7
This paper (camera-ready copy coming to arxiv soon) was accepted at @COLM_conf and the poster will be presented by @cameronajpatt with @LorenzoManuali, my brilliant co-authors, on Thursday at 1pm in Poster Session 5. Please go along and chat with them—since we put out this
1

Elinor

Elinor’s posts