Sathvik
@sathvik.bsky.social
computational psycholinguistics @ umd
he/him
he/him
Pinned
Sathvik
@sathvik.bsky.social
· Mar 25
hsp2025.github.io
I’ll be at #HSP2025! I’m presenting a poster in session 4 on how semantic factors might affect timing data from a speeded cloze task (w @virmalised.us, Philip Resnik, and @colinphillips.bsky.social)
hsp2025.github.io/abstracts/19...
hsp2025.github.io/abstracts/19...
Reposted by Sathvik
We captured so many great moments from Language Science Day, thanks to Andrea Zukowski! We wish we could share them all here, but you can see the full gallery on our Flickr page. Click here to check them out: flickr.com/photos/umd-l...
October 22, 2025 at 2:16 PM
We captured so many great moments from Language Science Day, thanks to Andrea Zukowski! We wish we could share them all here, but you can see the full gallery on our Flickr page. Click here to check them out: flickr.com/photos/umd-l...
If any friends are at Cog Sci, I’ll be in SF tomorrow! Let me know if you’d like to meet!
August 1, 2025 at 3:24 AM
If any friends are at Cog Sci, I’ll be in SF tomorrow! Let me know if you’d like to meet!
Reposted by Sathvik
The sycophantic tone of ChatGPT always sounded familiar, and then I recognized where I'd heard it before: author response letters to reviewer comments.
"You're exactly right, that's a great point!"
"Thank you so much for this insight!"
Also how it always agrees even when it contradicts itself.
"You're exactly right, that's a great point!"
"Thank you so much for this insight!"
Also how it always agrees even when it contradicts itself.
July 9, 2025 at 9:24 AM
The sycophantic tone of ChatGPT always sounded familiar, and then I recognized where I'd heard it before: author response letters to reviewer comments.
"You're exactly right, that's a great point!"
"Thank you so much for this insight!"
Also how it always agrees even when it contradicts itself.
"You're exactly right, that's a great point!"
"Thank you so much for this insight!"
Also how it always agrees even when it contradicts itself.
Reposted by Sathvik
When it comes to text prediction, where does one LM outperform another? If you've ever worked on LM evals, you know this question is a lot more complex than it seems. In our new #acl2025 paper, we developed a method to find fine-grained differences between LMs:
🧵1/9
🧵1/9
June 9, 2025 at 1:47 PM
When it comes to text prediction, where does one LM outperform another? If you've ever worked on LM evals, you know this question is a lot more complex than it seems. In our new #acl2025 paper, we developed a method to find fine-grained differences between LMs:
🧵1/9
🧵1/9
Reposted by Sathvik
NEW paper! 💭🖥️
“Combining Psychology with Artificial Intelligence: What could possibly go wrong?”
— Brief review paper by @olivia.science & myself, highlighting traps to avoid when combining Psych with AI, and why this is so important. Check out our proposed way forward! 🌟💡
osf.io/preprints/ps...
“Combining Psychology with Artificial Intelligence: What could possibly go wrong?”
— Brief review paper by @olivia.science & myself, highlighting traps to avoid when combining Psych with AI, and why this is so important. Check out our proposed way forward! 🌟💡
osf.io/preprints/ps...
May 14, 2025 at 9:23 PM
NEW paper! 💭🖥️
“Combining Psychology with Artificial Intelligence: What could possibly go wrong?”
— Brief review paper by @olivia.science & myself, highlighting traps to avoid when combining Psych with AI, and why this is so important. Check out our proposed way forward! 🌟💡
osf.io/preprints/ps...
“Combining Psychology with Artificial Intelligence: What could possibly go wrong?”
— Brief review paper by @olivia.science & myself, highlighting traps to avoid when combining Psych with AI, and why this is so important. Check out our proposed way forward! 🌟💡
osf.io/preprints/ps...
Reposted by Sathvik
A bit late but since I really like this paper, a bit of self-advertising! I am presenting at CMCL today work showing that metrics measuring how a Minimalist Grammar parser modulates memory usage can help us model Self-paced reading data for SRC/ORC contrasts: aclanthology.org/2025.cmcl-1.5/
Capturing Online SRC/ORC Effort with Memory Measures from a Minimalist Parser
Aniello De Santo. Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics. 2025.
aclanthology.org
May 3, 2025 at 4:43 PM
A bit late but since I really like this paper, a bit of self-advertising! I am presenting at CMCL today work showing that metrics measuring how a Minimalist Grammar parser modulates memory usage can help us model Self-paced reading data for SRC/ORC contrasts: aclanthology.org/2025.cmcl-1.5/
Reposted by Sathvik
New preprint on controlled generation from LMs!
I'll be presenting at NENLP tomorrow 12:50-2:00pm
Longer thread coming soon :)
I'll be presenting at NENLP tomorrow 12:50-2:00pm
Longer thread coming soon :)
April 10, 2025 at 7:19 PM
New preprint on controlled generation from LMs!
I'll be presenting at NENLP tomorrow 12:50-2:00pm
Longer thread coming soon :)
I'll be presenting at NENLP tomorrow 12:50-2:00pm
Longer thread coming soon :)
Reposted by Sathvik
another day another minicons update (potentially a significant one for psycholinguists?)
"Word" scoring is now a thing! You just have to supply your own splitting function!
pip install -U minicons for merriment
"Word" scoring is now a thing! You just have to supply your own splitting function!
pip install -U minicons for merriment
![from minicons import scorer
from nltk.tokenize import TweetTokenizer
lm = scorer.IncrementalLMScorer("gpt2")
# your own tokenizer function that returns a list of words
# given some sentence input
word_tokenizer = TweetTokenizer().tokenize
# word scoring
lm.word_score_tokenized(
["I was a matron in France", "I was a mat in France"],
bos_token=True, # needed for GPT-2/Pythia and NOT needed for others
tokenize_function=word_tokenizer,
bow_correction=True, # Oh and Schuler correction
surprisal=True,
base_two=True
)
'''
First word = -log_2 P(word | <beginning of text>)
[[('I', 6.1522440910339355),
('was', 4.033324718475342),
('a', 4.879510402679443),
('matron', 17.611848831176758),
('in', 2.5804288387298584),
('France', 9.036953926086426)],
[('I', 6.1522440910339355),
('was', 4.033324718475342),
('a', 4.879510402679443),
('mat', 19.385351181030273),
('in', 6.76780366897583),
('France', 10.574726104736328)]]
'''](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:njnapclhkbrhe3hsq44q2e4w/bafkreibw7fjs4zeocjmfvpr4fo7wikiqenbdz7b3clwq2rolckpoqwkssu@jpeg)
April 2, 2025 at 3:35 AM
another day another minicons update (potentially a significant one for psycholinguists?)
"Word" scoring is now a thing! You just have to supply your own splitting function!
pip install -U minicons for merriment
"Word" scoring is now a thing! You just have to supply your own splitting function!
pip install -U minicons for merriment
I’ll also be presenting a talk based on this work Friday afternoon at HSP. Very excited to share it with a psycholinguistics-focused audience!
Language models can identify who did what to whom, but they may not be using human-like mechanisms, based on materials from different psycholinguistic studies finding systematic patterns in human processing.
(with Rosa Lee & Naomi Feldman)
aclanthology.org/2024.finding...
(with Rosa Lee & Naomi Feldman)
aclanthology.org/2024.finding...
A Psycholinguistic Evaluation of Language Models’ Sensitivity to Argument Roles
Eun-Kyoung Rosa Lee, Sathvik Nair, Naomi Feldman. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
aclanthology.org
March 25, 2025 at 11:21 PM
I’ll also be presenting a talk based on this work Friday afternoon at HSP. Very excited to share it with a psycholinguistics-focused audience!
I’ll be at #HSP2025! I’m presenting a poster in session 4 on how semantic factors might affect timing data from a speeded cloze task (w @virmalised.us, Philip Resnik, and @colinphillips.bsky.social)
hsp2025.github.io/abstracts/19...
hsp2025.github.io/abstracts/19...
hsp2025.github.io
March 25, 2025 at 11:08 PM
I’ll be at #HSP2025! I’m presenting a poster in session 4 on how semantic factors might affect timing data from a speeded cloze task (w @virmalised.us, Philip Resnik, and @colinphillips.bsky.social)
hsp2025.github.io/abstracts/19...
hsp2025.github.io/abstracts/19...
Reposted by Sathvik
I’ll be presenting a poster at HSP 2025 in about a week. It’s on memory for pronominal clitic placement in Spanish, come stop by and say hi if you can!
March 22, 2025 at 10:33 PM
I’ll be presenting a poster at HSP 2025 in about a week. It’s on memory for pronominal clitic placement in Spanish, come stop by and say hi if you can!
Reposted by Sathvik
🎬🎥🍿 Video of my keynote at MathPsych2024 now available online www.youtube.com/watch?v=WrwN...
#CogSci #CriticalAI #AIhype #AGI #PsychSci #PhilSci 🧪
#CogSci #CriticalAI #AIhype #AGI #PsychSci #PhilSci 🧪
Iris van Rooij keynote at MathPsych/ICCM 2024
YouTube video by Society for Mathematical Psychology
www.youtube.com
January 11, 2025 at 5:34 PM
🎬🎥🍿 Video of my keynote at MathPsych2024 now available online www.youtube.com/watch?v=WrwN...
#CogSci #CriticalAI #AIhype #AGI #PsychSci #PhilSci 🧪
#CogSci #CriticalAI #AIhype #AGI #PsychSci #PhilSci 🧪
Reposted by Sathvik
What do YOU mean by "intelligence", and does ChatGPT fit your definition?
We collected the major criteria used in CogSci and other fields, and designed a survey to find out!
Access link: www.survey-xact.dk/collect
Code: 4S7V-SN4M-S536
Time: 5-10 mins
We collected the major criteria used in CogSci and other fields, and designed a survey to find out!
Access link: www.survey-xact.dk/collect
Code: 4S7V-SN4M-S536
Time: 5-10 mins
Perspectives on Intelligence: Community Survey
Research survey exploring how NLP/ML/CogSci researchers define and use the concept of intelligence.
bertramhojer.github.io
December 4, 2024 at 7:48 AM
What do YOU mean by "intelligence", and does ChatGPT fit your definition?
We collected the major criteria used in CogSci and other fields, and designed a survey to find out!
Access link: www.survey-xact.dk/collect
Code: 4S7V-SN4M-S536
Time: 5-10 mins
We collected the major criteria used in CogSci and other fields, and designed a survey to find out!
Access link: www.survey-xact.dk/collect
Code: 4S7V-SN4M-S536
Time: 5-10 mins
Reposted by Sathvik
starter pack for the Computational Linguistics and Information Processing group at the University of Maryland - get all your NLP and data science here!
go.bsky.app/V9qWjEi
go.bsky.app/V9qWjEi
December 10, 2024 at 5:14 PM
starter pack for the Computational Linguistics and Information Processing group at the University of Maryland - get all your NLP and data science here!
go.bsky.app/V9qWjEi
go.bsky.app/V9qWjEi
Reposted by Sathvik
@kanishka.bsky.social and I have made a starter pack for researchers working broadly on linguistic interpretability and LLMs!
go.bsky.app/F9qzAUn
Please message me or comment on this post if you've noticed someone who we forgot or would like to be added yourself!
go.bsky.app/F9qzAUn
Please message me or comment on this post if you've noticed someone who we forgot or would like to be added yourself!
November 26, 2024 at 2:49 PM
@kanishka.bsky.social and I have made a starter pack for researchers working broadly on linguistic interpretability and LLMs!
go.bsky.app/F9qzAUn
Please message me or comment on this post if you've noticed someone who we forgot or would like to be added yourself!
go.bsky.app/F9qzAUn
Please message me or comment on this post if you've noticed someone who we forgot or would like to be added yourself!
Reposted by Sathvik
"Hey everyone! 👋 I’ve created a starter pack of South Asian artists, authors, academics, activists, and orgs. I’ll keep it updated—DM me or reply if you or someone you know should be added! ✨" go.bsky.app/GGd6dxU
November 23, 2024 at 1:50 PM
"Hey everyone! 👋 I’ve created a starter pack of South Asian artists, authors, academics, activists, and orgs. I’ll keep it updated—DM me or reply if you or someone you know should be added! ✨" go.bsky.app/GGd6dxU
I’ll be presenting two posters on (psycho)linguistically motivated perspectives on LM generalization at #EMNLP2024!
1. Sensitivity to Argument Roles - Session 2 & #BlackBoxNLP
2. Learning & Filler-Gap Dependencies - #CoNLL
Excited to chat with other folks interested in compling x cogsci!
papers⬇️
1. Sensitivity to Argument Roles - Session 2 & #BlackBoxNLP
2. Learning & Filler-Gap Dependencies - #CoNLL
Excited to chat with other folks interested in compling x cogsci!
papers⬇️
November 11, 2024 at 1:00 AM
I’ll be presenting two posters on (psycho)linguistically motivated perspectives on LM generalization at #EMNLP2024!
1. Sensitivity to Argument Roles - Session 2 & #BlackBoxNLP
2. Learning & Filler-Gap Dependencies - #CoNLL
Excited to chat with other folks interested in compling x cogsci!
papers⬇️
1. Sensitivity to Argument Roles - Session 2 & #BlackBoxNLP
2. Learning & Filler-Gap Dependencies - #CoNLL
Excited to chat with other folks interested in compling x cogsci!
papers⬇️
5-gram of the day: "language models from computational linguistics"
June 6, 2024 at 3:17 PM
5-gram of the day: "language models from computational linguistics"
Today I learned that I may not have a successful psycholinguistics career because I got a B in databases.
April 16, 2024 at 6:13 PM
Today I learned that I may not have a successful psycholinguistics career because I got a B in databases.
Panicked after seeing AGI on my tax form
March 30, 2024 at 4:31 AM
Panicked after seeing AGI on my tax form
Reposted by Sathvik
This sums it up perfectly. It’s not a conversation.
March 4, 2024 at 2:20 AM
This sums it up perfectly. It’s not a conversation.
yelled about lexicalism in my NLU seminar do i get a prize
February 22, 2024 at 7:38 PM
yelled about lexicalism in my NLU seminar do i get a prize
Reposted by Sathvik
LLMs are so weird because one side is people with five PhDs who have been studying neuron activations for the past three decades and on the other side is someone called leetm5n with an anime avatar just casually releasing increasingly better performing fine tunes of mistral
December 31, 2023 at 1:32 AM
LLMs are so weird because one side is people with five PhDs who have been studying neuron activations for the past three decades and on the other side is someone called leetm5n with an anime avatar just casually releasing increasingly better performing fine tunes of mistral
Reposted by Sathvik
We’re excited about our first paper looking at speech encoding in single neurons across the depth of human cortex. Out today in @nature! www.nature.com/articles/s41... [1/6]
Large-scale single-neuron speech sound encoding across the depth of human cortex - Nature
High-density single-neuron recordings show diverse tuning for acoustic and phonetic features across layers in human auditory speech cortex.
www.nature.com
December 13, 2023 at 4:48 PM
We’re excited about our first paper looking at speech encoding in single neurons across the depth of human cortex. Out today in @nature! www.nature.com/articles/s41... [1/6]
Honored my paper was accepted to Findings of #EMNLP2023! Many psycholinguistics studies use LLMs to estimate the probability of words in context. But LLMs process statistically derived subword tokens, while human processing doesn't. Does this matter? (w/Philip Resnik) 🧵
arxiv.org/abs/2310.17774
arxiv.org/abs/2310.17774
November 2, 2023 at 10:20 PM
Honored my paper was accepted to Findings of #EMNLP2023! Many psycholinguistics studies use LLMs to estimate the probability of words in context. But LLMs process statistically derived subword tokens, while human processing doesn't. Does this matter? (w/Philip Resnik) 🧵
arxiv.org/abs/2310.17774
arxiv.org/abs/2310.17774