Adaptive Unlearning suppresses package hallucinations in code-generating LLMs by 81% while preserving benchmark performance, using model-generated data and no human labels.
In Advances in Neural Information Processing Systems, Vol
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CausalSynth combines structural causal models with LLMs and iterative verification to produce synthetic data that respects given causal structures while remaining linguistically natural.
citing papers explorer
-
LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning
Adaptive Unlearning suppresses package hallucinations in code-generating LLMs by 81% while preserving benchmark performance, using model-generated data and no human labels.
-
CasualSynth: Generating Structurally Sound Synthetic Data
CausalSynth combines structural causal models with LLMs and iterative verification to produce synthetic data that respects given causal structures while remaining linguistically natural.