NPO enables stable unlearning of 50%+ training data in LLMs on TOFU by making collapse exponentially slower than gradient ascent, preserving sensible outputs where prior methods fail.
arXiv preprint arXiv:2205.12628 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Pythia releases 16 identically trained LLMs with full checkpoints and data tools to study training dynamics, scaling, memorization, and bias in language models.
BEAVER is the first practical deterministic verifier that maintains sound probability bounds on LLM safety properties using token tries and frontier data structures, finding 2-3x more violations than sampling at 1/10 the compute.
PrivUn shows privacy unlearning in LLMs produces gradient-driven ripple effects and only shallow forgetting across layers, with new strategies proposed for deeper removal.
LLMs propagate misinformation more in lower-resource languages and lower-HDI countries, with input safety classifiers and retrieval-augmented fact-checking showing cross-lingual and regional gaps.
citing papers explorer
-
Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
NPO enables stable unlearning of 50%+ training data in LLMs on TOFU by making collapse exponentially slower than gradient ascent, preserving sensible outputs where prior methods fail.
-
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
Pythia releases 16 identically trained LLMs with full checkpoints and data tools to study training dynamics, scaling, memorization, and bias in language models.
-
BEAVER: An Efficient Deterministic LLM Verifier
BEAVER is the first practical deterministic verifier that maintains sound probability bounds on LLM safety properties using token tries and frontier data structures, finding 2-3x more violations than sampling at 1/10 the compute.
-
PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
PrivUn shows privacy unlearning in LLMs produces gradient-driven ripple effects and only shallow forgetting across layers, with new strategies proposed for deeper removal.
-
To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs
LLMs propagate misinformation more in lower-resource languages and lower-HDI countries, with input safety classifiers and retrieval-augmented fact-checking showing cross-lingual and regional gaps.