REVIEW 6 cited by
The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models
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
Signed reviews
read the original abstract
Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT) methods significantly decreases its fairness awareness with thousands of samples. To address this issue, inspired by the information theory, we introduce a training-free method to \textbf{S}uppress the \textbf{P}rivacy and fa\textbf{I}rness coupled \textbf{N}eurons (\textbf{SPIN}), which theoretically and empirically decrease the mutual information between fairness and privacy awareness. Extensive experimental results demonstrate that SPIN eliminates the trade-off phenomenon and significantly improves LLMs' fairness and privacy awareness simultaneously without compromising general capabilities, \eg improving Qwen-2-7B-Instruct's fairness awareness by 12.2\% and privacy awareness by 14.0\%. More crucially, SPIN remains robust and effective with limited annotated data or even when only malicious fine-tuning data is available, whereas SFT methods may fail to perform properly in such scenarios. Furthermore, we show that SPIN could generalize to other potential trade-off dimensions. We hope this study provides valuable insights into concurrently addressing fairness and privacy concerns in LLMs and can be integrated into comprehensive frameworks to develop more ethical and responsible AI systems. Our code is available at https://github.com/ChnQ/SPIN.
Forward citations
Cited by 6 Pith papers
-
Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
Reasoning tokens like 'Hmm' and 'Wait' mark steps where a model's internal state carries unusually high dependence with the correct answer, and suppressing them hurts accuracy.
-
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
Cross-lingual privacy leakage in LLMs is driven by a mix of language-universal and language-specific neurons, and deactivating those neurons lowers measured leakage by 23.3% to 31.6%.
-
Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
TELLME edits an LLM's hidden representations so similar behaviors cluster and different behaviors separate, improving safety monitoring and detoxification while preserving general ability.
-
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
A new white-box attack edits MLP matrices of safety-aligned open-source LLMs to remove safety-critical transformations, achieving 84.86% average jailbreak success without prompt modification.
-
Towards AI-$45^{\circ}$ Law: A Roadmap to Trustworthy AGI
The paper proposes the AI-45 degree law, a Causal Ladder framework, and five trustworthiness levels as a roadmap toward trustworthy AGI.
-
Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
A survey maps the field of MLLM explainability and interpretability into data, model, and training and inference perspectives.
Discussion (0). Continue with ORCID to comment.