REVIEW 7 cited by
Towards Safer Large Language Models through Machine Unlearning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The rapid advancement of Large Language Models (LLMs) has demonstrated their vast potential across various domains, attributed to their extensive pretraining knowledge and exceptional generalizability. However, LLMs often encounter challenges in generating harmful content when faced with problematic prompts. To address this problem, existing work attempted to implement a gradient ascent based approach to prevent LLMs from producing harmful output. While these methods can be effective, they frequently impact the model utility in responding to normal prompts. To address this gap, we introduce Selective Knowledge negation Unlearning (SKU), a novel unlearning framework for LLMs, designed to eliminate harmful knowledge while preserving utility on normal prompts. Specifically, SKU is consisted of two stages: harmful knowledge acquisition stage and knowledge negation stage. The first stage aims to identify and acquire harmful knowledge within the model, whereas the second is dedicated to remove this knowledge. SKU selectively isolates and removes harmful knowledge in model parameters, ensuring the model's performance remains robust on normal prompts. Our experiments conducted across various LLM architectures demonstrate that SKU identifies a good balance point between removing harmful information and preserving utility.
Forward citations
Cited by 7 Pith papers
-
Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
An MLLM unlearning method and benchmark that aim to erase targeted private facts while preserving image understanding.
-
Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
DiPO is a distribution-level unlearning method that constructs preference distributions from the model's own high-confidence logits and achieves state-of-the-art forget quality on TOFU while preserving utility.
-
Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
Water4MU tunes an invisible watermark on data so that machine unlearning algorithms can remove requested images more effectively, beating prior methods on 'challenging forgets'.
-
LLM Unlearning Should Be Form-Independent
Existing LLM unlearning is form-dependent; the new ORT benchmark measures this, and the training-free ROCR edit reduces it by redirecting concept representations.
-
Merge to Mix: Mixing Datasets via Model Merging
Merge to Mix shows that the performance of a parameter-averaged model predicts the performance of a model fine-tuned on any dataset mixture, enabling fast and accurate dataset mixture selection.
-
SoK: Machine Unlearning for Large Language Models
A new taxonomy for LLM unlearning distinguishes removal-intended from suppression-intended methods, and argues that gradient ascent methods functionally behave like suppression.
-
Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey
A survey organizes current research on trustworthy RAG into six pillars, reliability, privacy, safety, fairness, explainability, and accountability, and maps methods, metrics, and open problems for each.
Discussion (0). Continue with ORCID to comment.