Anna Hedström

AI Fellow @eth_ai_center | PhD ML @TUBerlin | evaluation-centric interpretability and AI alignment

[Anna Hedström @anna_hedstroem]

Almost forgot to share — last month, I defended my thesis, with distinction!

Feeling deeply grateful for the learnings, collaborations and friendships along the way.

New chapter at @ETH_AI_Center 🚀

[Understandable Machine Intelligence Lab @UMI_Lab_AI]

🔊 Not to miss …. last month @anna_hedstroem defended her PhD “Evaluation-centric advances in neural model interpretability” at TU Berlin — with distinction! ✨🧠💻☕️

Here’s a thread of a selection of Anna’s evaluation-centric interpretability work + what comes next. 🧵

[Anna Hedström @anna_hedstroem]

PRISM got accepted at @NeurIPSConf 2025! Congrats to the team ✨

@lkopf_ml
@nfelnlp
@kirill_bykov
@BommerPhiline
@Marina_MCV
@EberleOliver

[Laura Kopf @lkopf_ml]

Happy to share that our PRISM paper has been accepted at #NeurIPS2025 🎉

In this work, we introduce a multi-concept feature description framework that can identify and score polysemantic features.

📄 Paper: https://t.co/7HE1JGhnvD

#NeurIPS #MechInterp #XAI

[Anna Hedström @anna_hedstroem]

@MatthewKowal9 Amazing work!

[Anna Hedström @anna_hedstroem]

Couldn’t be more proud and happy for my labmate @kirill_bykov who made it to the other side!

Congrats again to the fantastic body of work produced!

[Understandable Machine Intelligence Lab @UMI_Lab_AI]

🎉 Huge congratulations to @kirill_bykov, the very first PhD student of our lab, who successfully defended his thesis “Explaining Representations in Deep Neural Networks” this Monday with summa cum laude! 👏

🧵 In the next tweets, we’ll highlight some of his key works:

[Anna Hedström @anna_hedstroem]

My brilliant co-author @salim_amk0 is presenting our work on Mechanistic Error Reduction with Abstention (MERA) now at ICML in Vancouver! 🚀

If you’re at ICML, come by East Exhibition Hall A-B, E-2605 at 4:30 pm (Vancouver, BC).

We’d love to hear what you think!

[Salim Amoukou @salim_amk0]

🚀 I'll be presenting our #ICML paper this afternoon!

You’ve probably heard of Mechanistic Steering, the idea of modifying internal activations of a language model at inference-time (e.g., adding a vector) to influence its behaviour, often for alignment.

But we take a different angle:
👉 We use it for error reduction.

If you've explored this space, you know it’s full of heuristics: Which vector to use? How long should it be? When to steer at all?

🎯 In our work, we bring principled answers to these questions, with provable guarantees. We introduce MERA (Mechanistic Error Reduction with Abstention for Language Models), a method for reducing errors in LLMs at inference-time by:

✅ Steering only when necessary
✅ Adapting how much to steer
✅ Abstaining unless confident improvement

And the best part? MERA is modular. You can plug it into any existing steering method to make it more effective and safer.

📍Catch me at @icmlconf
📌 Poster Location: East Exhibition Hall A-B, E-2605 at 4:30 pm.
🧠 Paper: https://t.co/cRWLsqqXp3

Big thanks to my amazing co-authors: @anna_hedstroem, @tom_bewley, Saumitra Mishra, and Manuela Veloso.

#ICML2025 #LLMs #MechanisticSteering #InferenceTime #LLMSafety #ResponsibleAI #TrustworthyAI #AIResearch

[Anna Hedström @anna_hedstroem]

Endless gratitude to brilliant @salim_amk0, @tom_bewley, and our fantastic collaborators at JP Morgan

#ICML25

[Anna Hedström @anna_hedstroem]

Couldn’t be more excited to share our latest paper — accepted to ICML 2025 @icmlconf — with JP Morgan AI Research.

It explores a simple question:

To safely and effectively mitigate errors post-training, when (and how much) should we steer large language models?

🧵

[Anna Hedström @anna_hedstroem]

4/ What’s fascinating is not just the outcome but how concepts like "error" show up inside LLMs.

This opens the door to more general forms of lightweight, post-training control — we're curious where else MERA may help.

Paper https://t.co/KRzyzGWelP

https://t.co/G64xYT3fp6

[Anna Hedström @anna_hedstroem]

@lkopf_ml @kirill_bykov @nfelnlp @BommerPhiline @Marina_MCV @EberleOliver

[Anna Hedström @anna_hedstroem]

Very excited to share this preprint on labelling polysemantic neurons!

Have a read https://t.co/zrjqf5o8b0

And happy midsummer!

[Laura Kopf @lkopf_ml]

🔍 When do neurons encode multiple concepts?

We introduce PRISM, a framework for extracting multi-concept feature descriptions to better understand polysemanticity.

📄 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
https://t.co/7HE1JGhnvD
🧵

[Anna Hedström @anna_hedstroem]

@spacecadet_kels You’re amazing!! Congrats

[Anna Hedström @anna_hedstroem]

@saprmarks Agreed!

[Anna Hedström @anna_hedstroem]

If you're at #AAAI2025 don't miss our poster today (alignment track)!

Paper 📘: https://t.co/1kDjrX3OaM
Code 👩‍💻: https://t.co/SiVfRWRhx0

Team work with @eirasf and @Marina_MCV

[Carlos Eiras @eirasf]

At 12:30 I'll be happy to take questions about our poster presentation at #AAAI2025. Is your explanation for a model's prediction better than the alternatives? "Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution" introduces QGE... 1/4

[Anna Hedström @anna_hedstroem]

I couldn’t be more proud and happy to share that our paper also got awarded survey certification for "exceptionally thorough/ insightful survey” of interpretability evaluation

Grateful to my brilliant co-authors @BommerPhiline @tfburns @SLapuschkin @WojciechSamek @Marina_MCV

[Understandable Machine Intelligence Lab @UMI_Lab_AI]

Our recently accepted TMLR paper has been awarded:

🔥 Survey certification 🔥

"For an exceptionally thorough or insightful survey of interpretability evaluation."

📖 Read: https://t.co/o2BYsQ0V15
💻 Code: https://t.co/MDUzlyWNi5

[Anna Hedström @anna_hedstroem]

Our new paper is out!

"Evaluating Interpretable Methods via Geometric Alignment of Functional Distortions"

📖 Read: https://t.co/kOO1MNG7MF
💻 Code: https://t.co/yqo7k0IBld

Thanks to my best collaborators
@BommerPhiline
@tfburns
@SLapuschkin
@WojciechSamek
@Marina_MCV

[Understandable Machine Intelligence Lab @UMI_Lab_AI]

🚨 New paper alert! 🚨

We’re excited to share our latest work on interpretability evaluation:

"Evaluating Interpretable Methods via Geometric Alignment of Functional Distortions"

📜 Accepted at TMLR 🎉
🔥 Survey certification 🔥
📖 Read: https://t.co/o2BYsQ0V15

[Anna Hedström @anna_hedstroem]

@SatyaScribbles so well deserved!!!!