iiinova — where your digital self keeps evolving

Reposted by Matthew Finlayson

Kyle Mahowald @kmahowald.bsky.social · 30/09/2026

AI agents say things like ARGH and OH MY GOD in their chains of thought. Good reason to think it's not just imitation but that these words play functional roles for doing reasoning. What comes after "oops" is very different than what comes after "aha"...

021

Matthew Finlayson @mattf.nl · 23/06/2025

I didn't believe when I first saw, but: We trained a prompt stealing model that gets >3x SoTA accuracy. The secret is representing LLM outputs *correctly* 🚲 Demo/blog: mattf1n.github.io/pils 📄: arxiv.org/abs/2506.17090 🤖: huggingface.co/dill-lab/pi... 🧑‍💻: github.com/dill-lab/PILS

1110

Reposted by Matthew Finlayson

David Marx @digthatdata.bsky.social · 11/06/2025

I wish the ML community would stop trying to turn every technique into a brand name. Just give the thing a descriptive name and call it what it is. Forced backronyms like this are counter productive.

171

Matthew Finlayson @mattf.nl · 04/06/2025

It appears that the only fonts with optical sizes that work with pdflatex are the computer/latin modern fonts. I would kill for a free pdflatex-compatible Times clone with optical sizes so my small text can look good in ArXiv/conference submissions.

020

Matthew Finlayson @mattf.nl · 16/03/2025

If you are writing a paper for #colm2025 and LaTeX keeps increasing your line height to accommodate things like superscripts, consider using $\smash{2^d}$, but beware of character overlaps.

Screenshot of inconsistent line height to make way for a superscript.

Screenshot of text with consistent line height.

2120

Matthew Finlayson @mattf.nl · 25/02/2025

This project was made feasible by the excellent open-source LLM training library @fairseq2.bsky.social; I highly recommend giving it a look! It made both SFT and DPO a piece of cake 🍰

0103

Matthew Finlayson @mattf.nl · 25/02/2025

🧵 Adapting your LLM for new tasks is dangerous! A bad training set degrades models by encouraging hallucinations and other misbehavior. Our paper remedies this for RAG training by replacing gold responses with self-generated demonstrations. Check it out here: arxiv.org/abs/2502.10

2181

Matthew Finlayson @mattf.nl · 12/12/2024

Putting together an unofficial usc Beamer template, I noticed that the USC style guide lists 4 formats for “cardinal red” but each of them is different: PMS 201 C is #9D2235 CMYK: 7, 100, 65, 32 is #A1003D RGB: 135, 27, 30 is #991B1E HEX: #990000 Is this normal? The CMYK is especially egregious.

The usc style guide list of formats for “cardinal” (see main post for list)

The rgb and CMYK colors side by side. The CMYK is considerably pinker

000

Matthew Finlayson @mattf.nl · 09/12/2024

In Vancouver for NeurIPS but don't have Taylor Swift tickets? You can still spend the day going through our tutorial reading list: cmu-l3.github.io/neurips2024-... Tuesday December 10, 1:30-4:00pm @ West Exhibition Hall C, NeurIPS

A diagram demonstrating text generation with beam search. One of the paths reads “Taylor Swift is the only person to…”

0292

Matthew Finlayson @mattf.nl · 06/12/2024

Curious about all this inference-time scaling hype? Attend our NeurIPS tutorial: Beyond Decoding: Meta-Generation Algorithms for LLMs (Tue. 1:30)! We have a top-notch panelist lineup. Our website: cmu-l3.github.io/neurips2024-...

Panelist photos: Rishabh Agarwal (Google, McGill), Noam Brown (OpenAl), Beidi Chen (CMU), Nouha Dziri (AI2), Jakob Foerster (Oxford, Meta)

1273

Reposted by Matthew Finlayson

Hamish Ivison @hamishivi.bsky.social · 26/11/2024

What's that? A fully open LM competitive with Gemma and Qwen*? Happy to have helped a bit with this release (Tulu 3 recipe used here)! OLMo-2 13B actually beats Tulu 3 8B on these evals, making it a SOTA fully open LM!!! (*on the benchmarks we looked at, see tweet for more)

1101

Matthew Finlayson @mattf.nl · 26/11/2024

These folks have had a huge impact on my research

030

Reposted by Matthew Finlayson

Michael Saxon @saxon.me · 22/11/2024

#socalnlp is the biggest it's ever been in 2024! We have 3 poster sessions up from 2! How many years until it's a two-day event?? 🤯

1263

Matthew Finlayson @mattf.nl · 22/11/2024

This is niche but the LLM360 logo always reminds me of the 2014 iOS game Oquonie

Screenshot from Oquonie with a long-necked character.

030

Matthew Finlayson @mattf.nl · 22/11/2024

Hottest new research challenge: find the lost LLM head!

090

Matthew Finlayson @mattf.nl · 22/11/2024

Everyone follow Sean! He's been working nonstop to perfect our upcoming NeurIPS tutorial

060

Reposted by Matthew Finlayson

Michael Saxon @saxon.me · 21/11/2024

As "X is all you need" and "Transformers are Y" paper titles have died, I propose that we similarly retire: - X of thought - Chain of Y - "[topic] a comprehensive survey" where [topic] is exclusively post-2022 papers - Claims of reasoning/world model/planning based on private defns of one

9515

Matthew Finlayson @mattf.nl · 17/11/2024

I made a map! Thank you to my 2019 self for providing the code github.com/mattf1n/Reli...

A relief map of Los Angeles rendered in Blender giving it a 3D appearance.

2170

Matthew Finlayson @mattf.nl · 15/11/2024

Today I learned you can add a citation link to your GitHub repo. citation-file-format.github.io

citation-file-format.github.io

0100

Reposted by Matthew Finlayson

Yoav Artzi @yoavartzi.com · 15/11/2024

Oh my, USC is an empire!

191

Reposted by Matthew Finlayson

Swabha @swabhs.bsky.social · 14/11/2024

And we're having a great time at #EMNLP2024, come talk to us!

0152

Matthew Finlayson @mattf.nl · 14/11/2024

I’m proud of this tikz drawing I made today for our upcoming NeurIPS tutorial on decoding (our paper: arxiv.org/abs/2406.16838)

A diagram of how beam search works. The graphic is a tree with “Taylor swift is” at the root and possible continuations branching off.

0151

Reposted by Matthew Finlayson

Marco @mcognetta.bsky.social · 09/11/2024

I'll be presenting "Distributional Properties of Subword Regularization" with @zouharvi.bsky.social and Naoaki Okazaki at #EMNLP. arxiv.org/abs/2408.11443 The idea is that stochastic variants of BPE/MaxMatch produce very biased tokenization distributions, which is probably bad for modeling. #NLP

1132

Matthew Finlayson @mattf.nl · 12/11/2024

USC NLP folks are on Bluesky! Follow my amazing colleagues here go.bsky.app/KUwSZ6W

3175

Reposted by Matthew Finlayson

Maria Antoniak @mariaa.bsky.social · 04/11/2024

A starter pack for #NLP #NLProc researchers! 🎉 go.bsky.app/SngwGeS

4525199

Reposted by Matthew Finlayson

numble.bsky.social @numble.bsky.social · 22/10/2024

How many times did the 14 LA Metro board members + CEO use their Metro TAP cards in the 4.5 years from 1/1/20 to 6/30/24? 2,259 times. 33.5 taps per person per year. 1112 workdays in period. If CEO tapped 2x/workday, 14 board members in total tapped 35 times in 4.5 years.

4268

Matthew Finlayson @mattf.nl · 07/10/2024

Just landed in Philly for COLM where I’ll be presenting my work on extracting secrets from LLM APIs at the Wednesday afternoon poster sesh. Please reach out if you wanna hang and talk about sneaky LLM API hacks, accountability, and the geometry of LLM representations! arxiv.org/abs/2403.09539

arxiv.org

Logits of API-Protected LLMs Leak Proprietary Information

The commercialization of large language models (LLMs) has led to the common practice of high-level API-only access to proprietary models. In this work, we show that even with a conservative assumption...

022

Reposted by Matthew Finlayson

Maria Antoniak @mariaa.bsky.social · 06/10/2024

Ooh we got the answer from Steven Bird! Sorry to link to Twitter, but the story is worth reading. x.com/StevenBird/s... "I got the idea at SIGMOD'99... I had been living in West Africa and experienced inequities of access... I wanted ours to be a society that made its content free to all."

0126

Matthew Finlayson @mattf.nl · 13/03/2024

“Media companies aren't on their workers' side in just the same way that Amazon wasn't on publishers' side. The promise of a new, broader copyright [for AI] is like the promise of DRM: it's a prison pretending to be a fortress” pluralistic.net/2024/03/13/h...

010

Matthew Finlayson @mattf.nl · 06/02/2024

Please help me, probabilists of the internet: what is the probability that an unfair m-sided dice rolls its most-likely value more times than any of its other values after n rolls?

000

Reposted by Matthew Finlayson

Yoav Artzi @yoavartzi.com · 23/01/2024

We are pleased to announce that the first Conference on Language Modeling will be held at the University of Pennsylvania in Philadelphia at the Zellerbach Theatre. Thanks so much to UPenn CS as well as Mark Yatskar and Zachary Ives for facilitating the amazing venue.

0123

Reposted by Matthew Finlayson

Jacob Eisenstein @jacobeisenstein.bsky.social · 23/01/2024

Cross posting to tell you that I am looking forward to speaking (virtually) at Stanford NLP seminar this thursday! I’ll be talking about Trustworthy NLP. When: 01/25 Thurs 11am PT Non-Stanford affiliates registration form (closed at 9am PT on the talk day): forms.gle/j8DQDDvgyLTSZB…

161

Reposted by Matthew Finlayson

Naomi Saphra @nsaphra.bsky.social · 12/01/2024

FINALLY 🤖https://aclweb.org/adminwiki/images/5/56/ACL_Anonymity_Policy.pdf

0155

Reposted by Matthew Finlayson

Naomi Saphra @nsaphra.bsky.social · 05/01/2024

I decided what we need to make blueskAI happen is a feed. Reply here to get added to the whitelist! Whitelisted users can post to the feed by adding the following keywords to a post: 🤖 bskAI blueskAI

624317

Reposted by Matthew Finlayson

Ana Marasović @anamarasovic.bsky.social · 27/10/2023

Utah is hiring tenure-track/tenured faculty & a priority area is NLP! Please reach out over email if you have questions about the school and Salt Lake City, happy to share my experience so far. utah.peopleadmin.com/postings/154...

043

Matthew Finlayson @mattf.nl · 25/10/2023

A cute TikZ diagram for your enjoyment: (I spent too much time making this for a presentation)

A TikZ diagram of the standard 3-simplex

040

Matthew Finlayson @mattf.nl · 11/10/2023

Nucleus and top-k sampling are ubiquitous, but why do they work so well? We explain the theory and give a method to address model errors at their source (the softmax bottleneck). 📄 arxiv.org/abs/2310.01693 🧑‍💻 github.com/mattf1n/basi... 1/🧵

Title and figure 1 for the paper "Closing the Curious Case of Neural Text Degeneration". The figure depicts the next-token distribution according to an LM. Our method is able to pick out high quality next-token candidates while discarding low-quality ones, even when the low-quality tokens have higher probability than the high-quality ones.

182

Reposted by Matthew Finlayson

Michael Saxon @saxon.me · 08/10/2023

Highly doubt any followers on here are planning to apply for GRFP, but I want to support the X alternative 😂 so... If you know anyone planning to apply for NSF GRFP this cycle, please pass on my statements, CV, and feedback from my successful app for a DL/ML/Speech ECE GRFP app from 2019 to them!

saxon.me

PhD and NSF GRFP Application Tips

Links to my statements and reviews from my successful NSF GRFP application in deep learning and language.

131