FIELD NOTES TOPIC
language model fine-tuning
2 notes, newest first.
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
The paper introduces MADA-RL, a method for fine-tuning compact language models with limited budgets. It specializes the models into generator and critic roles and trains them using a debate-aware learning signal. The…
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
The study shows that Language Models (LLMs) fine-tuned for security classification can have vulnerabilities missed during standard evaluation because they learn token-level indicator semantics that work well on their…
