Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection
cs.LG, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/logix-project/logix2https:
Terminology
Sources
- QLESS: A Quantized Approach for Data Valuation and Selection in Large Language Model Fine-Tuning
- Studying Large Language Model Generalization with Influence Functions
- Interaction-Aware Influence Functions for Group Attribution
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution
- Pointer Sentinel Mixture Models
- 2 OLMo 2 Furious
- HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation
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