Ben Lipkin
@benlipkin.bsky.social
Pinned
Ben Lipkin
@benlipkin.bsky.social
· May 13
Many LM applications may be formulated as text generation conditional on some (Boolean) constraint.
Generate a…
- Python program that passes a test suite.
- PDDL plan that satisfies a goal.
- CoT trajectory that yields a positive reward.
The list goes on…
How can we efficiently satisfy these? 🧵👇
Generate a…
- Python program that passes a test suite.
- PDDL plan that satisfies a goal.
- CoT trajectory that yields a positive reward.
The list goes on…
How can we efficiently satisfy these? 🧵👇
Reposted by Ben Lipkin
Humans largely learn language through speech. In contrast, most LLMs learn from pre-tokenized text.
In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech.
Poster P6, tomorrow (Aug 19) at 1:30 pm, Foyer 2.2!
In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech.
Poster P6, tomorrow (Aug 19) at 1:30 pm, Foyer 2.2!
August 19, 2025 at 1:12 AM
Humans largely learn language through speech. In contrast, most LLMs learn from pre-tokenized text.
In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech.
Poster P6, tomorrow (Aug 19) at 1:30 pm, Foyer 2.2!
In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech.
Poster P6, tomorrow (Aug 19) at 1:30 pm, Foyer 2.2!
Reposted by Ben Lipkin
Is the Language of Thought == Language? A Thread 🧵
New Preprint (link: tinyurl.com/LangLOT) with @alexanderfung.bsky.social, Paris Jaggers, Jason Chen, Josh Rule, Yael Benn, @joshtenenbaum.bsky.social, @spiantado.bsky.social, Rosemary Varley, @evfedorenko.bsky.social
1/8
New Preprint (link: tinyurl.com/LangLOT) with @alexanderfung.bsky.social, Paris Jaggers, Jason Chen, Josh Rule, Yael Benn, @joshtenenbaum.bsky.social, @spiantado.bsky.social, Rosemary Varley, @evfedorenko.bsky.social
1/8
Evidence from Formal Logical Reasoning Reveals that the Language of Thought is not Natural Language
Humans are endowed with a powerful capacity for both inductive and deductive logical thought: we easily form generalizations based on a few examples and draw conclusions from known premises. Humans al...
tinyurl.com
August 3, 2025 at 8:18 PM
Is the Language of Thought == Language? A Thread 🧵
New Preprint (link: tinyurl.com/LangLOT) with @alexanderfung.bsky.social, Paris Jaggers, Jason Chen, Josh Rule, Yael Benn, @joshtenenbaum.bsky.social, @spiantado.bsky.social, Rosemary Varley, @evfedorenko.bsky.social
1/8
New Preprint (link: tinyurl.com/LangLOT) with @alexanderfung.bsky.social, Paris Jaggers, Jason Chen, Josh Rule, Yael Benn, @joshtenenbaum.bsky.social, @spiantado.bsky.social, Rosemary Varley, @evfedorenko.bsky.social
1/8
Reposted by Ben Lipkin
1/7 If you're at CogSci 2025, I'd love to see you at my talk on Friday 1pm PDT in Nob Hill A! I'll be talking about our work towards an implemented computational model of noisy-channel comprehension (with @postylem.bsky.social, Ted Gibson, and @rplevy.bsky.social).
July 31, 2025 at 5:56 PM
1/7 If you're at CogSci 2025, I'd love to see you at my talk on Friday 1pm PDT in Nob Hill A! I'll be talking about our work towards an implemented computational model of noisy-channel comprehension (with @postylem.bsky.social, Ted Gibson, and @rplevy.bsky.social).
Many LM applications may be formulated as text generation conditional on some (Boolean) constraint.
Generate a…
- Python program that passes a test suite.
- PDDL plan that satisfies a goal.
- CoT trajectory that yields a positive reward.
The list goes on…
How can we efficiently satisfy these? 🧵👇
Generate a…
- Python program that passes a test suite.
- PDDL plan that satisfies a goal.
- CoT trajectory that yields a positive reward.
The list goes on…
How can we efficiently satisfy these? 🧵👇
May 13, 2025 at 2:22 PM
Many LM applications may be formulated as text generation conditional on some (Boolean) constraint.
Generate a…
- Python program that passes a test suite.
- PDDL plan that satisfies a goal.
- CoT trajectory that yields a positive reward.
The list goes on…
How can we efficiently satisfy these? 🧵👇
Generate a…
- Python program that passes a test suite.
- PDDL plan that satisfies a goal.
- CoT trajectory that yields a positive reward.
The list goes on…
How can we efficiently satisfy these? 🧵👇
Reposted by Ben Lipkin
#ICLR2025 Oral
How can we control LMs using diverse signals such as static analyses, test cases, and simulations?
In our paper “Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo” (w/ @benlipkin.bsky.social,
@alexlew.bsky.social, @xtimv.bsky.social) we:
How can we control LMs using diverse signals such as static analyses, test cases, and simulations?
In our paper “Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo” (w/ @benlipkin.bsky.social,
@alexlew.bsky.social, @xtimv.bsky.social) we:
April 25, 2025 at 7:33 PM
#ICLR2025 Oral
How can we control LMs using diverse signals such as static analyses, test cases, and simulations?
In our paper “Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo” (w/ @benlipkin.bsky.social,
@alexlew.bsky.social, @xtimv.bsky.social) we:
How can we control LMs using diverse signals such as static analyses, test cases, and simulations?
In our paper “Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo” (w/ @benlipkin.bsky.social,
@alexlew.bsky.social, @xtimv.bsky.social) we:
Reposted by Ben Lipkin
I might be able to hire a postdoc for this fall in computational linguistics at UT Austin. Topics in the general LLM + cognitive space (particularly reasoning, chain of thought, LLMs + code) and LLM + linguistic space. If this could be of interest, feel free to get in touch!
April 21, 2025 at 3:56 PM
I might be able to hire a postdoc for this fall in computational linguistics at UT Austin. Topics in the general LLM + cognitive space (particularly reasoning, chain of thought, LLMs + code) and LLM + linguistic space. If this could be of interest, feel free to get in touch!
Reposted by Ben Lipkin
Jason Eisner & Li Du’s “Syntactic and semantic control of large language models via sequential Monte Carlo” with @joaoloula.bsky.social, @benlipkin.bsky.social, @yahyaemara.bsky.social, @alexlew.bsky.social, @xtimv.bsky.social, & more presents an architecture for controlled LM generation: (11/12)
Syntactic and Semantic Control of Large Language Models via...
A wide range of LM applications require generating text that conforms to syntactic or semantic constraints. Imposing such constraints can be naturally framed as _probabilistic conditioning_, but...
openreview.net
April 21, 2025 at 4:44 PM
Jason Eisner & Li Du’s “Syntactic and semantic control of large language models via sequential Monte Carlo” with @joaoloula.bsky.social, @benlipkin.bsky.social, @yahyaemara.bsky.social, @alexlew.bsky.social, @xtimv.bsky.social, & more presents an architecture for controlled LM generation: (11/12)
Reposted by Ben Lipkin
New paper! 🧠 **The cerebellar components of the human language network**
with: @hsmall.bsky.social @moshepoliak.bsky.social @gretatuckute.bsky.social @benlipkin.bsky.social @awolna.bsky.social @aniladmello.bsky.social and @evfedorenko.bsky.social
www.biorxiv.org/content/10.1...
1/n 🧵
with: @hsmall.bsky.social @moshepoliak.bsky.social @gretatuckute.bsky.social @benlipkin.bsky.social @awolna.bsky.social @aniladmello.bsky.social and @evfedorenko.bsky.social
www.biorxiv.org/content/10.1...
1/n 🧵
The cerebellar components of the human language network
The cerebellum's capacity for neural computation is arguably unmatched. Yet despite evidence of cerebellar contributions to cognition, including language, its precise role remains debated. Here, we sy...
www.biorxiv.org
April 21, 2025 at 3:19 PM
New paper! 🧠 **The cerebellar components of the human language network**
with: @hsmall.bsky.social @moshepoliak.bsky.social @gretatuckute.bsky.social @benlipkin.bsky.social @awolna.bsky.social @aniladmello.bsky.social and @evfedorenko.bsky.social
www.biorxiv.org/content/10.1...
1/n 🧵
with: @hsmall.bsky.social @moshepoliak.bsky.social @gretatuckute.bsky.social @benlipkin.bsky.social @awolna.bsky.social @aniladmello.bsky.social and @evfedorenko.bsky.social
www.biorxiv.org/content/10.1...
1/n 🧵
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 Ben Lipkin
I defended my PhD at MIT Brain&Cog last week--so much gratitude to my advisor @evfedorenko.bsky.social, as well as my committee @nancykanwisher.bsky.social, @joshhmcdermott.bsky.social and Yoon Kim. Thank you to all my brilliant collaborators and the MIT community. I have loved this journey so much.
December 15, 2024 at 3:13 PM
I defended my PhD at MIT Brain&Cog last week--so much gratitude to my advisor @evfedorenko.bsky.social, as well as my committee @nancykanwisher.bsky.social, @joshhmcdermott.bsky.social and Yoon Kim. Thank you to all my brilliant collaborators and the MIT community. I have loved this journey so much.
Reposted by Ben Lipkin
If you're interested in a PhD at the intersection of machine learning and programming languages, consider applying to Yale CS!
We're exploring new approaches to building software that draws inferences and makes predictions. See alexlew.net for details & apply at gsas.yale.edu/admissions/ by Dec. 15
We're exploring new approaches to building software that draws inferences and makes predictions. See alexlew.net for details & apply at gsas.yale.edu/admissions/ by Dec. 15
December 8, 2024 at 4:27 PM
If you're interested in a PhD at the intersection of machine learning and programming languages, consider applying to Yale CS!
We're exploring new approaches to building software that draws inferences and makes predictions. See alexlew.net for details & apply at gsas.yale.edu/admissions/ by Dec. 15
We're exploring new approaches to building software that draws inferences and makes predictions. See alexlew.net for details & apply at gsas.yale.edu/admissions/ by Dec. 15
Lots of folks talking about scaling LLM inference over this last year
Internally, I’ve been developing and using a library that makes this extremely easy, and I decided to open-source it
Meet the decoding library: github.com/benlipkin/de...
1/7
Internally, I’ve been developing and using a library that makes this extremely easy, and I decided to open-source it
Meet the decoding library: github.com/benlipkin/de...
1/7
GitHub - benlipkin/decoding: Composable inference algorithms with LLMs and programmable logic
Composable inference algorithms with LLMs and programmable logic - benlipkin/decoding
github.com
November 25, 2024 at 4:19 PM
Lots of folks talking about scaling LLM inference over this last year
Internally, I’ve been developing and using a library that makes this extremely easy, and I decided to open-source it
Meet the decoding library: github.com/benlipkin/de...
1/7
Internally, I’ve been developing and using a library that makes this extremely easy, and I decided to open-source it
Meet the decoding library: github.com/benlipkin/de...
1/7
Reposted by Ben Lipkin
✨ Now out in Psychological Review! ✨
We present a new account of relevance that weighs both *epistemic* and *decision-theoretic* utility: statements are relevant if they improve the accuracy of listener’s beliefs *and* their future decision-making.
www.tedsumers.info/_files/ugd/2...
We present a new account of relevance that weighs both *epistemic* and *decision-theoretic* utility: statements are relevant if they improve the accuracy of listener’s beliefs *and* their future decision-making.
www.tedsumers.info/_files/ugd/2...
September 5, 2023 at 1:10 PM
✨ Now out in Psychological Review! ✨
We present a new account of relevance that weighs both *epistemic* and *decision-theoretic* utility: statements are relevant if they improve the accuracy of listener’s beliefs *and* their future decision-making.
www.tedsumers.info/_files/ugd/2...
We present a new account of relevance that weighs both *epistemic* and *decision-theoretic* utility: statements are relevant if they improve the accuracy of listener’s beliefs *and* their future decision-making.
www.tedsumers.info/_files/ugd/2...
Reposted by Ben Lipkin
First post and big news - I am starting as an Assistant Professor in Psychology at Georgia Tech in Jan 2024!
www.language-intelligence-thought.net
www.language-intelligence-thought.net
LIT Lab
Our goal is to understand the relationship between language and human thought.
How does the language network in the brain interact with other systems to interpret meaning in the world?
Can models...
www.language-intelligence-thought.net
November 6, 2023 at 4:52 PM
First post and big news - I am starting as an Assistant Professor in Psychology at Georgia Tech in Jan 2024!
www.language-intelligence-thought.net
www.language-intelligence-thought.net
Reposted by Ben Lipkin
To researchers doing LLM evaluation: prompting is *not a substitute* for direct probability measurements. Check out the camera-ready version of our work, to appear at EMNLP 2023! (w/ @rplevy.bsky.social)
Paper: arxiv.org/abs/2305.13264
Original thread: twitter.com/_jennhu/stat...
Paper: arxiv.org/abs/2305.13264
Original thread: twitter.com/_jennhu/stat...
October 24, 2023 at 3:03 PM
To researchers doing LLM evaluation: prompting is *not a substitute* for direct probability measurements. Check out the camera-ready version of our work, to appear at EMNLP 2023! (w/ @rplevy.bsky.social)
Paper: arxiv.org/abs/2305.13264
Original thread: twitter.com/_jennhu/stat...
Paper: arxiv.org/abs/2305.13264
Original thread: twitter.com/_jennhu/stat...
Reposted by Ben Lipkin
🚀 We've officially landed on Bluesky! Excited to join this vibrant new platform and (re)connect with all of you!
🗣️💬 Help us spread the word by retweeting and following.
🗣️💬 Help us spread the word by retweeting and following.
October 7, 2023 at 12:37 PM
🚀 We've officially landed on Bluesky! Excited to join this vibrant new platform and (re)connect with all of you!
🗣️💬 Help us spread the word by retweeting and following.
🗣️💬 Help us spread the word by retweeting and following.