Actionable Interpretability Workshop ICML2025 retweetledi
Actionable Interpretability Workshop ICML2025
47 posts
Actionable Interpretability Workshop ICML2025
@ActInterp
🛠️ Actionable Interpretability🔎 @icmlconf 2025 | Bridging the gap between insights and actions ✨ https://t.co/4zRMTbzwDc
Katılım Mart 2025
12 Takip Edilen319 Takipçiler
Actionable Interpretability Workshop ICML2025 retweetledi
We’re extending the Actionable Interpretability workshop @ActInterp submission deadline by 3 days!
New deadline: June 24th.
Looking forward to your submissions ;) Link in thread
English
Actionable Interpretability Workshop ICML2025 retweetledi
Submit your work! The 2nd Workshop on 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐥𝐞 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲 will be held at COLM 2026 in San Francisco!
Submission Deadline: June 21, 2026
@ActInterp
English
Actionable Interpretability Workshop ICML2025 retweetledi
🤔What happens when LLM agents choose between achieving their goals and avoiding harm to humans in realistic management scenarios? Are LLMs pragmatic or prefer to avoid human harm?
🚀 New paper out: ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs🚀🧵
English
Actionable Interpretability Workshop ICML2025 retweetledi
Opportunities to join my group in fall 2026:
* PhD applications direct or via @ELLISforEurope (ellis.eu/news/ellis-phd…)
* Post-doc applications direct or via Azrieli @azrielifdn (azrielifoundation.org/fellows/intern…) or Zuckerman @stem_program (zuckermanstem.org/ourprograms/po…)
English
Actionable Interpretability Workshop ICML2025 retweetledi
Many thanks to the @ActInterp organisers for highlighting our work - and congratulations to Pedro, Alex and the other awardees! Sad not to have been there in person, it looked like a fantastic workshop. @AmsterdamNLP @EdinburghNLP
Actionable Interpretability Workshop ICML2025@ActInterp
Big congrats to Alex McKenzie, Pedro Ferreira, and their collaborators on receiving Outstanding Paper Awards!👏👏 and thanks for the fantastic oral presentations! Check out the papers here 👇
English
1⃣Detecting High-Stakes Interactions with Activation Probes - arxiv.org/abs/2506.10805
2⃣ Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations - arxiv.org/abs/2504.05294
English
Big congrats to Alex McKenzie, Pedro Ferreira, and their collaborators on receiving Outstanding Paper Awards!👏👏
and thanks for the fantastic oral presentations!
Check out the papers here 👇
English
Actionable Interpretability Workshop ICML2025 retweetledi
Great to present what’s coming next for NDIF at the @actinterp workshop at #ICML2025!
If you missed us, let’s chat after the conference. Reach out here: forms.gle/AhTSBNNttA11JV…
English
English
Actionable Interpretability Workshop ICML2025 retweetledi
maybe I will live tweet the actionable interp workshop panel
English
Huge thanks to Sarah Schwettmann for a fascinating keynote on "AI Investigators for Understanding AI Systems" 🤖 @cogconfluence @TransluceAI
English
Grab a ☕️ and join us for a keynote by @RICEric22: Explanations for Experts via Guarantees and Domain Knowledge: From Attributions to Reasoning
English
➡️ Join us for the keynote by @byron_c_wallace: “What (if anything) can interpretability do for healthcare?”
English
The second poster session is starting now!🙌🏻
English
Actionable Interpretability Workshop ICML2025 retweetledi
Come see our poster about how to predict side effects of unlearning and Fine-Tuning at @ActInterp
English
Actionable Interpretability Workshop ICML2025 retweetledi
Crazy amount of cool work concentrated in one room
Actionable Interpretability Workshop ICML2025@ActInterp
The first poster session is happening now!
English
The first poster session is happening now!
English