Tal Haklay
@talhaklay.bsky.social
NLP | Interpretability | PhD student at the Technion
Pinned
Tal Haklay
@talhaklay.bsky.social
· Mar 6
1/13 LLM circuits tell us where the computation happens inside the model—but the computation varies by token position, a key detail often ignored!
We propose a method to automatically find position-aware circuits, improving faithfulness while keeping circuits compact. 🧵👇
We propose a method to automatically find position-aware circuits, improving faithfulness while keeping circuits compact. 🧵👇
Our paper "Position-Aware Automatic Circuit Discovery" got accepted to ACL! 🎉
Huge thanks to my collaborators🙏
@hadasorgad.bsky.social
@davidbau.bsky.social
@amuuueller.bsky.social
@boknilev.bsky.social
See you in Vienna! 🇦🇹 #ACL2025 @aclmeeting.bsky.social
Huge thanks to my collaborators🙏
@hadasorgad.bsky.social
@davidbau.bsky.social
@amuuueller.bsky.social
@boknilev.bsky.social
See you in Vienna! 🇦🇹 #ACL2025 @aclmeeting.bsky.social
May 22, 2025 at 8:11 AM
Our paper "Position-Aware Automatic Circuit Discovery" got accepted to ACL! 🎉
Huge thanks to my collaborators🙏
@hadasorgad.bsky.social
@davidbau.bsky.social
@amuuueller.bsky.social
@boknilev.bsky.social
See you in Vienna! 🇦🇹 #ACL2025 @aclmeeting.bsky.social
Huge thanks to my collaborators🙏
@hadasorgad.bsky.social
@davidbau.bsky.social
@amuuueller.bsky.social
@boknilev.bsky.social
See you in Vienna! 🇦🇹 #ACL2025 @aclmeeting.bsky.social
Reposted by Tal Haklay
🚨 We're looking for more reviewers for the workshop!
📆 Review period: May 24-June 7
If you're passionate about making interpretability useful and want to help shape the conversation, we'd love your input.
💡🔍 Self-nominate here:
docs.google.com/forms/d/e/1F...
📆 Review period: May 24-June 7
If you're passionate about making interpretability useful and want to help shape the conversation, we'd love your input.
💡🔍 Self-nominate here:
docs.google.com/forms/d/e/1F...
May 20, 2025 at 12:05 AM
🚨 We're looking for more reviewers for the workshop!
📆 Review period: May 24-June 7
If you're passionate about making interpretability useful and want to help shape the conversation, we'd love your input.
💡🔍 Self-nominate here:
docs.google.com/forms/d/e/1F...
📆 Review period: May 24-June 7
If you're passionate about making interpretability useful and want to help shape the conversation, we'd love your input.
💡🔍 Self-nominate here:
docs.google.com/forms/d/e/1F...
We knew many of you wanted to submit to our Actionable Interpretability workshop, but we didn’t expect to crash Overleaf! 😏🍃
Only 5 days left ⏰!
Got a paper accepted to ICML that fits our theme?
Submit it to our conference track!
👉 @actinterp.bsky.social
Only 5 days left ⏰!
Got a paper accepted to ICML that fits our theme?
Submit it to our conference track!
👉 @actinterp.bsky.social
May 14, 2025 at 1:04 PM
We knew many of you wanted to submit to our Actionable Interpretability workshop, but we didn’t expect to crash Overleaf! 😏🍃
Only 5 days left ⏰!
Got a paper accepted to ICML that fits our theme?
Submit it to our conference track!
👉 @actinterp.bsky.social
Only 5 days left ⏰!
Got a paper accepted to ICML that fits our theme?
Submit it to our conference track!
👉 @actinterp.bsky.social
Reposted by Tal Haklay
This was a huge collaboration with many great folks! If you get a chance, be sure to talk to Atticus Geiger, @sarah-nlp.bsky.social, @danaarad.bsky.social, Iván Arcuschin, @adambelfki.bsky.social, @yiksiu.bsky.social, Jaden Fiotto-Kaufmann, @talhaklay.bsky.social, @michaelwhanna.bsky.social, ...
April 23, 2025 at 6:15 PM
This was a huge collaboration with many great folks! If you get a chance, be sure to talk to Atticus Geiger, @sarah-nlp.bsky.social, @danaarad.bsky.social, Iván Arcuschin, @adambelfki.bsky.social, @yiksiu.bsky.social, Jaden Fiotto-Kaufmann, @talhaklay.bsky.social, @michaelwhanna.bsky.social, ...
🚨 Call for Papers is Out!
The First Workshop on 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐥𝐞 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲 will be held at ICML 2025 in Vancouver!
📅 Submission Deadline: May 9
Follow us >> @ActInterp
🧠Topics of interest include: 👇
The First Workshop on 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐥𝐞 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲 will be held at ICML 2025 in Vancouver!
📅 Submission Deadline: May 9
Follow us >> @ActInterp
🧠Topics of interest include: 👇
April 7, 2025 at 1:51 PM
🚨 Call for Papers is Out!
The First Workshop on 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐥𝐞 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲 will be held at ICML 2025 in Vancouver!
📅 Submission Deadline: May 9
Follow us >> @ActInterp
🧠Topics of interest include: 👇
The First Workshop on 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐥𝐞 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲 will be held at ICML 2025 in Vancouver!
📅 Submission Deadline: May 9
Follow us >> @ActInterp
🧠Topics of interest include: 👇
Amazing news: our workshop was accepted to ICML 2025!
Interpretability research sheds light on how models work—but too often, those insights don’t translate into actions that improve them.
Our workshop aims to challenge the interpretability community to go further.
Interpretability research sheds light on how models work—but too often, those insights don’t translate into actions that improve them.
Our workshop aims to challenge the interpretability community to go further.
🎉 Our Actionable Interpretability workshop has been accepted to #ICML2025! 🎉
> Follow @actinterp.bsky.social
> Website actionable-interpretability.github.io
@talhaklay.bsky.social @anja.re @mariusmosbach.bsky.social @sarah-nlp.bsky.social @iftenney.bsky.social
Paper submission deadline: May 9th!
> Follow @actinterp.bsky.social
> Website actionable-interpretability.github.io
@talhaklay.bsky.social @anja.re @mariusmosbach.bsky.social @sarah-nlp.bsky.social @iftenney.bsky.social
Paper submission deadline: May 9th!
March 31, 2025 at 6:29 PM
Amazing news: our workshop was accepted to ICML 2025!
Interpretability research sheds light on how models work—but too often, those insights don’t translate into actions that improve them.
Our workshop aims to challenge the interpretability community to go further.
Interpretability research sheds light on how models work—but too often, those insights don’t translate into actions that improve them.
Our workshop aims to challenge the interpretability community to go further.
1/13 LLM circuits tell us where the computation happens inside the model—but the computation varies by token position, a key detail often ignored!
We propose a method to automatically find position-aware circuits, improving faithfulness while keeping circuits compact. 🧵👇
We propose a method to automatically find position-aware circuits, improving faithfulness while keeping circuits compact. 🧵👇
March 6, 2025 at 10:15 PM
1/13 LLM circuits tell us where the computation happens inside the model—but the computation varies by token position, a key detail often ignored!
We propose a method to automatically find position-aware circuits, improving faithfulness while keeping circuits compact. 🧵👇
We propose a method to automatically find position-aware circuits, improving faithfulness while keeping circuits compact. 🧵👇
Reposted by Tal Haklay
🚨🚨 New preprint 🚨🚨
Ever wonder whether verbalized CoTs correspond to the internal reasoning process of the model?
We propose a novel parametric faithfulness approach, which erases information contained in CoT steps from the model parameters to assess CoT faithfulness.
arxiv.org/abs/2502.14829
Ever wonder whether verbalized CoTs correspond to the internal reasoning process of the model?
We propose a novel parametric faithfulness approach, which erases information contained in CoT steps from the model parameters to assess CoT faithfulness.
arxiv.org/abs/2502.14829
Measuring Faithfulness of Chains of Thought by Unlearning Reasoning Steps
When prompted to think step-by-step, language models (LMs) produce a chain of thought (CoT), a sequence of reasoning steps that the model supposedly used to produce its prediction. However, despite mu...
arxiv.org
February 21, 2025 at 12:43 PM
🚨🚨 New preprint 🚨🚨
Ever wonder whether verbalized CoTs correspond to the internal reasoning process of the model?
We propose a novel parametric faithfulness approach, which erases information contained in CoT steps from the model parameters to assess CoT faithfulness.
arxiv.org/abs/2502.14829
Ever wonder whether verbalized CoTs correspond to the internal reasoning process of the model?
We propose a novel parametric faithfulness approach, which erases information contained in CoT steps from the model parameters to assess CoT faithfulness.
arxiv.org/abs/2502.14829