7 papers
The Role of Feedback Alignment in Self-Distillation
Semih Kara, OÄuzhan Ersoy
Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains the model to retain this impr…
IR3DE: A Linear Router for Large Language Models
Eros Fanì, OÄuzhan Ersoy
Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialized tasks via domain-expert LL…
Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO
Nikolay Blagoev, OÄuzhan Ersoy, Lydia Yiyu Chen
Group Relative Policy Optimization (GRPO) has demonstrated wide adoption in the post-training of Large Language Models (LLMs). In GRPO, prompts are answered by the model and prefer…
All is Not Lost: LLM Recovery without Checkpoints
Nikolay Blagoev, OÄuzhan Ersoy, Lydia Yiyu Chen
Training LLMs on decentralized nodes or on-spot instances, lowers the training cost and enables model democratization. The inevitable challenge here is the transient churns of node…
Backdoor Attacks on Decentralised Post-Training
OÄuzhan Ersoy, Nikolay Blagoev, Jona te Lintelo +3
Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training c…
Verde: Verification via Refereed Delegation for Machine Learning Programs
Arasu Arun, Adam St. Arnaud, Alexey Titov +6
Machine learning programs, such as those performing inference, fine-tuning, and training of LLMs, are commonly delegated to untrusted compute providers. To provide correctness guar…