The paper defines a new problem: persona unlearning, where the goal is to edit a model's weights so that a specific undesirable behavior pattern (like sycophancy, impoliteness, or hallucination) becomes difficult to activate, even with explicit prompts. Current unlearning methods fail because they either cannot fully suppress the persona or they break the model's ability to generate useful responses. The authors propose PaCE, which finds an internal direction representing the target persona in the model's activations, then trains the model to avoid that direction while steering it toward a desirable counterpart response. On their new , PaCE consistently suppresses target personas while maintaining high response quality, with only moderate cost to general utility.
Method to permanently erase unwanted LLM personas via weight edits
A new benchmark and contrastive erasure technique suppress target personas while preserving utility across six models and five personas.
Big Tech
Kemou Li · Zhuan Shi · Qizhou Wang · Fengpeng Li · Negar Rostamzadeh · Golnoosh Farnadi · +1 more
University of Macau · Mila – Québec AI Institute · McGill University · RIKEN AIP · King Abdullah University of Science and Technology
Research Digest··3 min read
In one line
PaCE suppresses LLM personas like sycophancy by editing weights to make them hard to elicit.
Before you read this
Three ideas this paper builds onlarge language modelA neural network trained on massive text corpora to generate coherent text and perform diverse language tasks.329 papers →benchmarkA standard set of tasks or data used to evaluate and compare the performance of AI systems.366 papers →activation steeringActivation steering modifies a model's internal vector representations during inference to shift behavior, such as editing outputs, removing capabilities, or controlling trust.83 papers →
Read it as
Li et al. introduce persona unlearning, a weight-level edit that makes a designated persona difficult to elicit on unseen prompts.
The authors formalize persona unlearning as a distinct behavior-level editing problem.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.