Papers with perturbation-based methods
Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods (2023.emnlp-main)
Copied to clipboard
| Challenge: | Feature attribution scores are used to explain the prediction of a text classifier to users by highlighting a k number of tokens. |
| Approach: | They propose to determine the number of optimal k tokens that should be displayed from sequential properties of attribution scores. |
| Outcome: | The proposed method is dynamic across sentences, method-agnostic, and deals with sentence length bias. |
Context Attribution with Multi-Armed Bandit Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to augmenting attribution with retrieval-augmented generation (RAG) focus on training models to explicitly cite context segments during generation, but their reliability remains unverifiable. |
| Approach: | They propose a framework that formulates context attribution as a combinatorial multi-armed bandit problem by using Linear Thompson Sampling to efficiently identify the most influential context segments while minimizing the number of model queries. |
| Outcome: | The proposed method reduces model queries by 30% while matching or exceeding the attribution quality of existing approaches. |
MoPe: Model Perturbation based Privacy Attacks on Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows that Large Language Models can unintentionally leak sensitive information . a new method to identify with high confidence if a given text is in training data is proposed . |
| Approach: | They propose a method to detect if a given text is in a pre-trained language model . they show that MoPe is more effective than existing loss-based attacks . |
| Outcome: | The proposed method is more effective than loss-based attacks and perturbation-based methods. |