RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/chuanpupig/RESCUE
Terminology
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
- Localizing Model Behavior with Path Patching
- Qwen3 Technical Report
- Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks