Irina Bigoulaeva
@ibigoulaeva.bsky.social
PhD student @ukplab.bsky.social | LLM Explainability, Reasoning, and Instruction Tuning
Reposted by Irina Bigoulaeva
🚀 New paper out in TMLR!
“Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning”
📃 Paper: openreview.net/forum?id=10Q...
💻 Code: github.com/UKPLab/tmlr2...
“Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning”
📃 Paper: openreview.net/forum?id=10Q...
💻 Code: github.com/UKPLab/tmlr2...
October 15, 2025 at 7:59 AM
🚀 New paper out in TMLR!
“Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning”
📃 Paper: openreview.net/forum?id=10Q...
💻 Code: github.com/UKPLab/tmlr2...
“Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning”
📃 Paper: openreview.net/forum?id=10Q...
💻 Code: github.com/UKPLab/tmlr2...
Reposted by Irina Bigoulaeva
🧠 How good are today’s LLMs at reasoning – really?
In the latest issue of hoch³, the university magazine of TU Darmstadt, @igurevych.bsky.social and @ibigoulaeva.bsky.social from the UKP Lab examine the performance of DeepSeek-R1 and R1-Zero.
(1/ 🧵)
In the latest issue of hoch³, the university magazine of TU Darmstadt, @igurevych.bsky.social and @ibigoulaeva.bsky.social from the UKP Lab examine the performance of DeepSeek-R1 and R1-Zero.
(1/ 🧵)
May 15, 2025 at 1:19 PM
🧠 How good are today’s LLMs at reasoning – really?
In the latest issue of hoch³, the university magazine of TU Darmstadt, @igurevych.bsky.social and @ibigoulaeva.bsky.social from the UKP Lab examine the performance of DeepSeek-R1 and R1-Zero.
(1/ 🧵)
In the latest issue of hoch³, the university magazine of TU Darmstadt, @igurevych.bsky.social and @ibigoulaeva.bsky.social from the UKP Lab examine the performance of DeepSeek-R1 and R1-Zero.
(1/ 🧵)