arXiv Machine Learning
RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 5
Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators
arXiv:2608. 02712v1 Announce Type: cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness through pipelines that couple LLMs with agentic reinforcement learning and evolutionary search.
arXiv AI
Jul 22
Circuit Claims Depend on What Is Extracted and How It Is Compared
arXiv:2607. 18921v1 Announce Type: cross Abstract: Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior.
arXiv AI
Jun 9
Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
arXiv:2605. 28860v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) frequently induces catastrophic forgetting of prior capabilities.
arXiv AI
Jul 28
A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning
arXiv:2601. 09624v2 Announce Type: replace-cross Abstract: Machine unlearning is becoming essential for building trustworthy and compliant language models.
arXiv Machine Learning
1d ago
Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability
The paper investigates mechanistic interpretability, focusing on how automated circuit discovery is evaluated. It shows that the commonly used faithfulness objective can favor circuits that reproduce a model’s behavior poorly, creating an objective-level recovery gap. Experiments on four human-reference tasks and InterpBench reveal that many discovery methods misrank candidate circuits, and that restoring excluded signals can correct most of these misrankings without altering the circuits’ behavior.
arXiv AI
Sep 15
Tool Use Reduces Depth-Induced Collapse in OOD Reasoning
arXiv:2602.21061v2 Announce Type: replace Abstract: Many current paths to more advanced AI depend on the assumption that large language models (LLMs) can generalize learned relationships to solve com...