task-vectors

Tag

Cards List
#task-vectors

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets

arXiv cs.AI · 2026-07-10 Cached

Introduces 'overthinking', a technique that amplifies reasoning weights from reasoning-distilled models to induce disclosure of hidden information in language models, demonstrating up to 10x greater secret leakage across 2B-32B models.

0 favorites 0 likes
#task-vectors

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

arXiv cs.LG · 2026-06-18 Cached

The paper identifies 'Load-Bearing Wall' dimensions in pre-trained models that retain task-specific knowledge not fully captured by task vectors in model merging, and proposes PACT (PreserveAnchoredCores) to preserve these cores, achieving state-of-the-art performance across benchmarks.

0 favorites 0 likes
#task-vectors

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning

arXiv cs.CL · 2026-05-21 Cached

This paper proposes using distributional alignment between task vector-based and in-context learning inference as a criterion for designing task vectors, and introduces Linear Task Vector (LTV) that minimizes next-token probability discrepancy via closed-form linear mapping. LTV achieves 9.2% average accuracy improvement over baselines across eight benchmarks and five LLMs.

0 favorites 0 likes
← Back to home

Submit Feedback